From 051f856113ab3b7be70fe7fca3dc185fb3540a0f Mon Sep 17 00:00:00 2001
From: Paul Bakaus <paul.bakaus@gmail.com>
Date: Sat, 11 Jul 2026 17:35:28 -0700
Subject: [PATCH] finish the mode migration: brand.md/product.md become
 redirect stubs

Answering the obvious question the family-depth framing dodged: with
modes derived per task, files named for the old two-register taxonomy
had no architectural reason to exist. brand.md's surviving depth (lane
test + inverse test, reflex-reject lanes, color discipline, layout
moves, permissions) folds into new-work.md, where all of it belonged:
it is new-identity Persuade/Experience guidance. product.md's content
moves unchanged to operate.md, its true name. Both old files remain as
one-line redirect stubs because register: brand|product in existing
PRODUCT.md files and older links point there. All cross-references
retargeted (SKILL.md modes intro, context.mjs REGISTER hint, live.md,
typeset.md); 85 tests green.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---
 .agents/skills/impeccable/SKILL.md            |  2 +-
 .agents/skills/impeccable/reference/brand.md  | 43 +------------
 .agents/skills/impeccable/reference/live.md   |  6 +-
 .../skills/impeccable/reference/new-work.md   | 10 +++
 .../skills/impeccable/reference/operate.md    | 60 ++++++++++++++++++
 .../skills/impeccable/reference/product.md    | 61 +------------------
 .../skills/impeccable/reference/typeset.md    |  2 +-
 .agents/skills/impeccable/scripts/context.mjs |  2 +-
 .claude/skills/impeccable/SKILL.md            |  2 +-
 .claude/skills/impeccable/reference/brand.md  | 43 +------------
 .claude/skills/impeccable/reference/live.md   |  6 +-
 .../skills/impeccable/reference/new-work.md   | 10 +++
 .../skills/impeccable/reference/operate.md    | 60 ++++++++++++++++++
 .../skills/impeccable/reference/product.md    | 61 +------------------
 .../skills/impeccable/reference/typeset.md    |  2 +-
 .claude/skills/impeccable/scripts/context.mjs |  2 +-
 .cursor/skills/impeccable/SKILL.md            |  2 +-
 .cursor/skills/impeccable/reference/brand.md  | 43 +------------
 .cursor/skills/impeccable/reference/live.md   |  6 +-
 .../skills/impeccable/reference/new-work.md   | 10 +++
 .../skills/impeccable/reference/operate.md    | 60 ++++++++++++++++++
 .../skills/impeccable/reference/product.md    | 61 +------------------
 .../skills/impeccable/reference/typeset.md    |  2 +-
 .cursor/skills/impeccable/scripts/context.mjs |  2 +-
 .gemini/skills/impeccable/SKILL.md            |  2 +-
 .gemini/skills/impeccable/reference/brand.md  | 43 +------------
 .gemini/skills/impeccable/reference/live.md   |  6 +-
 .../skills/impeccable/reference/new-work.md   | 10 +++
 .../skills/impeccable/reference/operate.md    | 60 ++++++++++++++++++
 .../skills/impeccable/reference/product.md    | 61 +------------------
 .../skills/impeccable/reference/typeset.md    |  2 +-
 .gemini/skills/impeccable/scripts/context.mjs |  2 +-
 .github/skills/impeccable/SKILL.md            |  2 +-
 .github/skills/impeccable/reference/brand.md  | 43 +------------
 .github/skills/impeccable/reference/live.md   |  6 +-
 .../skills/impeccable/reference/new-work.md   | 10 +++
 .../skills/impeccable/reference/operate.md    | 60 ++++++++++++++++++
 .../skills/impeccable/reference/product.md    | 61 +------------------
 .../skills/impeccable/reference/typeset.md    |  2 +-
 .github/skills/impeccable/scripts/context.mjs |  2 +-
 .kiro/skills/impeccable/SKILL.md              |  2 +-
 .kiro/skills/impeccable/reference/brand.md    | 43 +------------
 .kiro/skills/impeccable/reference/live.md     |  6 +-
 .kiro/skills/impeccable/reference/new-work.md | 10 +++
 .kiro/skills/impeccable/reference/operate.md  | 60 ++++++++++++++++++
 .kiro/skills/impeccable/reference/product.md  | 61 +------------------
 .kiro/skills/impeccable/reference/typeset.md  |  2 +-
 .kiro/skills/impeccable/scripts/context.mjs   |  2 +-
 .opencode/skills/impeccable/SKILL.md          |  2 +-
 .../skills/impeccable/reference/brand.md      | 43 +------------
 .opencode/skills/impeccable/reference/live.md |  6 +-
 .../skills/impeccable/reference/new-work.md   | 10 +++
 .../skills/impeccable/reference/operate.md    | 60 ++++++++++++++++++
 .../skills/impeccable/reference/product.md    | 61 +------------------
 .../skills/impeccable/reference/typeset.md    |  2 +-
 .../skills/impeccable/scripts/context.mjs     |  2 +-
 .pi/skills/impeccable/SKILL.md                |  2 +-
 .pi/skills/impeccable/reference/brand.md      | 43 +------------
 .pi/skills/impeccable/reference/live.md       |  6 +-
 .pi/skills/impeccable/reference/new-work.md   | 10 +++
 .pi/skills/impeccable/reference/operate.md    | 60 ++++++++++++++++++
 .pi/skills/impeccable/reference/product.md    | 61 +------------------
 .pi/skills/impeccable/reference/typeset.md    |  2 +-
 .pi/skills/impeccable/scripts/context.mjs     |  2 +-
 .qoder/skills/impeccable/SKILL.md             |  2 +-
 .qoder/skills/impeccable/reference/brand.md   | 43 +------------
 .qoder/skills/impeccable/reference/live.md    |  6 +-
 .../skills/impeccable/reference/new-work.md   | 10 +++
 .qoder/skills/impeccable/reference/operate.md | 60 ++++++++++++++++++
 .qoder/skills/impeccable/reference/product.md | 61 +------------------
 .qoder/skills/impeccable/reference/typeset.md |  2 +-
 .qoder/skills/impeccable/scripts/context.mjs  |  2 +-
 .rovodev/skills/impeccable/SKILL.md           |  2 +-
 .rovodev/skills/impeccable/reference/brand.md | 43 +------------
 .rovodev/skills/impeccable/reference/live.md  |  6 +-
 .../skills/impeccable/reference/new-work.md   | 10 +++
 .../skills/impeccable/reference/operate.md    | 60 ++++++++++++++++++
 .../skills/impeccable/reference/product.md    | 61 +------------------
 .../skills/impeccable/reference/typeset.md    |  2 +-
 .../skills/impeccable/scripts/context.mjs     |  2 +-
 .trae-cn/skills/impeccable/SKILL.md           |  2 +-
 .trae-cn/skills/impeccable/reference/brand.md | 43 +------------
 .trae-cn/skills/impeccable/reference/live.md  |  6 +-
 .../skills/impeccable/reference/new-work.md   | 10 +++
 .../skills/impeccable/reference/operate.md    | 60 ++++++++++++++++++
 .../skills/impeccable/reference/product.md    | 61 +------------------
 .../skills/impeccable/reference/typeset.md    |  2 +-
 .../skills/impeccable/scripts/context.mjs     |  2 +-
 .trae/skills/impeccable/SKILL.md              |  2 +-
 .trae/skills/impeccable/reference/brand.md    | 43 +------------
 .trae/skills/impeccable/reference/live.md     |  6 +-
 .trae/skills/impeccable/reference/new-work.md | 10 +++
 .trae/skills/impeccable/reference/operate.md  | 60 ++++++++++++++++++
 .trae/skills/impeccable/reference/product.md  | 61 +------------------
 .trae/skills/impeccable/reference/typeset.md  |  2 +-
 .trae/skills/impeccable/scripts/context.mjs   |  2 +-
 plugin/skills/impeccable/SKILL.md             |  2 +-
 plugin/skills/impeccable/reference/brand.md   | 43 +------------
 plugin/skills/impeccable/reference/live.md    |  6 +-
 .../skills/impeccable/reference/new-work.md   | 10 +++
 plugin/skills/impeccable/reference/operate.md | 60 ++++++++++++++++++
 plugin/skills/impeccable/reference/product.md | 61 +------------------
 plugin/skills/impeccable/reference/typeset.md |  2 +-
 plugin/skills/impeccable/scripts/context.mjs  |  2 +-
 skill/SKILL.src.md                            |  2 +-
 skill/reference/brand.md                      | 43 +------------
 skill/reference/live.md                       |  6 +-
 skill/reference/new-work.md                   | 10 +++
 skill/reference/operate.md                    | 60 ++++++++++++++++++
 skill/reference/product.md                    | 61 +------------------
 skill/reference/typeset.md                    |  2 +-
 skill/scripts/context.mjs                     |  2 +-
 tests/context.test.mjs                        |  2 +-
 113 files changed, 1121 insertions(+), 1485 deletions(-)
 create mode 100644 .agents/skills/impeccable/reference/operate.md
 create mode 100644 .claude/skills/impeccable/reference/operate.md
 create mode 100644 .cursor/skills/impeccable/reference/operate.md
 create mode 100644 .gemini/skills/impeccable/reference/operate.md
 create mode 100644 .github/skills/impeccable/reference/operate.md
 create mode 100644 .kiro/skills/impeccable/reference/operate.md
 create mode 100644 .opencode/skills/impeccable/reference/operate.md
 create mode 100644 .pi/skills/impeccable/reference/operate.md
 create mode 100644 .qoder/skills/impeccable/reference/operate.md
 create mode 100644 .rovodev/skills/impeccable/reference/operate.md
 create mode 100644 .trae-cn/skills/impeccable/reference/operate.md
 create mode 100644 .trae/skills/impeccable/reference/operate.md
 create mode 100644 plugin/skills/impeccable/reference/operate.md
 create mode 100644 skill/reference/operate.md

diff --git a/.agents/skills/impeccable/SKILL.md b/.agents/skills/impeccable/SKILL.md
index 8c54e6343..18446b698 100644
--- a/.agents/skills/impeccable/SKILL.md
+++ b/.agents/skills/impeccable/SKILL.md
@@ -41,7 +41,7 @@ Calibration for this provider:
 
 ## Registers
 
-Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode. PRODUCT.md's `register` field names the family (`brand` covers Persuade and Experience; `product` covers Operate and Read), and `reference/brand.md` / `reference/product.md` carry extended depth for the two families.
+Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode; PRODUCT.md's `register` field survives only as a family hint (`brand` covers Persuade and Experience, `product` covers Operate and Read). Depth beyond the paragraphs below: [reference/new-work.md](reference/new-work.md) when inventing identity, [reference/operate.md](reference/operate.md) for substantial Operate and Read work.
 
 **Persuade** (landing pages, marketing, campaigns; design IS the product). The deliverable is an impression that stops the scroll, earns the click, converts. Spans every genre (tech, luxury, consumer); don't collapse them into one look. Briefs that imply imagery must ship real, verified imagery; a colored rectangle where a photo belongs reads as incomplete. New Persuade surfaces take their typeface procedure and reject list from [reference/new-work.md](reference/new-work.md).
 
diff --git a/.agents/skills/impeccable/reference/brand.md b/.agents/skills/impeccable/reference/brand.md
index 01af65d27..0f0184c0d 100644
--- a/.agents/skills/impeccable/reference/brand.md
+++ b/.agents/skills/impeccable/reference/brand.md
@@ -1,42 +1,3 @@
-# Brand family depth (Persuade and Experience surfaces)
+# Moved
 
-When design IS the product: brand sites, landing pages, campaign pages, portfolios, long-form content, about pages. The essentials live in SKILL.md (modes, craft floor) and, for new identity work, in [new-work.md](new-work.md); this file is extended depth for substantial brand work. Rules stated in those files are not repeated here.
-
-The register spans every genre. A tech brand, a luxury hotel, a restaurant, a band's album page, an agency portfolio. They share a stance (*communicate, not transact*) and diverge wildly in aesthetic. Don't collapse them into one look.
-
-## The aesthetic-lane test
-
-Before committing to moves, name the lane. A type-foundry specimen page is one lane; minimal-cool tech is another; acid-maximalism is another. Don't drift into editorial-magazine aesthetics on a brief that isn't editorial; a hiking brand with italic drop caps has the wrong register within the register.
-
-Then the inverse test: in one sentence, describe what you're about to build the way a competitor would describe theirs. If that sentence fits the modal landing page in the category, restart.
-
-### Reflex-reject aesthetic lanes
-
-Currently saturated aesthetic families that have flooded brand surfaces. If a brief lands in one of these lanes without a register reason that *requires* it (a literal magazine, a literal terminal), it's the second-order training reflex: the trap one tier deeper than a reflex font pick. Look further.
-
-- **Editorial-typographic.** Display serif (often italic) + small mono labels + ruled separators + monochromatic restraint. The fingerprint: three rule-separated columns, an italic serif headline, lowercase track-spaced metadata, no imagery.
-
-(Entries land and leave this list as families saturate and fade.)
-
-The reflex-reject lists apply to **new design choices**. When the existing brand has already committed to a font or a lane as part of its identity, identity-preservation wins.
-
-## Color
-
-- Name a real reference before picking a strategy; unnamed ambition becomes beige.
-- Palette IS voice. A calm brand and a restless brand should not share palette mechanics.
-- Don't converge across projects. Each brand surface differentiates from the last.
-- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
-
-## Layout
-
-- Asymmetric compositions are one option. Break the grid intentionally for emphasis.
-- Fluid spacing with `clamp()` that breathes on larger viewports.
-- For image-led briefs (hotels, restaurants, magazines, photography), full-bleed hero imagery with overlaid menu and centered headline is a canonical move; let the photograph be the design.
-
-## Brand permissions
-
-Brand can afford things product can't. Take them.
-
-- Ambitious first-load motion. Reveals and typographic choreography that earn their place; one orchestrated page-load beats scattered micro-interactions, and some brands skip entrance motion entirely, which is also a voice.
-- Single-purpose viewports. One dominant idea per fold, long scroll, deliberate pacing.
-- Art direction per section. Different sections can have different visual worlds if the narrative demands it. Consistency of voice beats consistency of treatment.
+The Persuade and Experience essentials are in SKILL.md; the depth for inventing new identity (typeface procedure, reject list and lanes, color discipline, layout moves, permissions) lives in [new-work.md](new-work.md). This stub remains because `PRODUCT.md` files with `register: brand` and older links point here.
diff --git a/.agents/skills/impeccable/reference/live.md b/.agents/skills/impeccable/reference/live.md
index bc1e3e9ea..87988e1b1 100644
--- a/.agents/skills/impeccable/reference/live.md
+++ b/.agents/skills/impeccable/reference/live.md
@@ -111,7 +111,7 @@ node .agents/skills/impeccable/scripts/live-insert.mjs --id EVENT_ID --count EVE
 - `--position` ← `event.insert.position` (`before` | `after`)
 - Anchor flags ← `event.insert.anchor` (same mapping as wrap: id, classes, tag, text)
 
-The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. Load `brand.md` or `product.md` (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
+The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. For Operate/Read surfaces load `operate.md`; Persuade/Experience surfaces use SKILL.md's mode guidance plus `new-work.md` when the variant invents identity (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
 
 For Svelte/SvelteKit targets, `live-insert.mjs` returns `previewMode: "svelte-component"` with `mode: "insert"`, `file` pointing at a temporary `node_modules/.impeccable-live/<id>/manifest.json`, `componentDir` pointing at the variant component files, and `sourceFile` pointing at the real `.svelte` route. Write each inserted variant as a real Svelte component (`v1.svelte`, `v2.svelte`, …) under `componentDir`. Insert variants must be non-empty net-new content with a single top-level root, no `data-impeccable-*` attributes, and CSS in each component's `<style>` block. Do **not** edit the route source during generation; the browser mounts the temporary component before/after the live anchor while the user cycles variants. On Accept, `live-accept.mjs` inserts the selected component markup into `sourceFile` immediately and deletes the temp session after the source write succeeds.
 
@@ -189,7 +189,7 @@ All three carry `fallback: "agent-driven"`. Follow **Handle fallback** below.
 
 ### 3. Load the action's reference
 
-If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded register reference (`brand.md` or `product.md`). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
+If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded mode depth (`operate.md` for Operate/Read; `new-work.md` when the variant invents identity). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
 
 Any other `event.action` (`bolder`, `quieter`, `distill`, `polish`, `typeset`, `colorize`, `layout`, `adapt`, `animate`, `delight`, `overdrive`): Read `reference/<action>.md` before planning. Each sub-command encodes a specific discipline; skipping its reference produces generic output. Those files may require specific params; layer them on top of the §7 budget, not instead of it.
 
@@ -254,7 +254,7 @@ Instead, work from the brand:
 
 1. Read PRODUCT.md's Brand Personality words. What physical, spatial, or material experiences would embody those words if design were not involved? (A personality described as "specific, earned, unmistakable" evokes a hand-stamped letter, a numbered print, a watchmaker's loupe. A personality described as "restless, loud, unfiltered" evokes a concert poster, a spray-painted wall, a megaphone.)
 2. From those physical experiences, derive three visual directions that are genuinely different from each other AND from the current surface you're departing.
-3. Avoid the **reflex-reject lanes** in [brand.md](brand.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
+3. Avoid the **reflex-reject lanes** in [new-work.md](new-work.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
 4. Each direction must be expressible in one concrete sentence that names a real-world referent ("a museum exhibition label system for a contemporary art gallery" not "clean and minimal"). If your sentence contains only adjectives, it's not concrete enough.
 5. **While planning each direction, also name its 2–3 parameter knobs** (per the §7 budget table). The same principle as default mode: decide "what's tunable" during planning, not after writing the HTML. A departure-mode hero with 0 parameters is not "bold creative vision," it's a missed opportunity for the user to fine-tune the direction they pick.
 
diff --git a/.agents/skills/impeccable/reference/new-work.md b/.agents/skills/impeccable/reference/new-work.md
index f71af8d3c..480c33fa5 100644
--- a/.agents/skills/impeccable/reference/new-work.md
+++ b/.agents/skills/impeccable/reference/new-work.md
@@ -24,6 +24,10 @@ Plan a compact token system in your reasoning: palette, type, layout concept in
 
 Pick a color strategy before picking colors: Restrained (neutrals + one accent; the default when the visitor came to operate or read) / Committed (one saturated color carries 30-60% of the surface) / Full palette (3-4 named roles) / Drenched (the surface IS the color). Persuade and Experience surfaces have permission for the bolder strategies; take them when the brief allows. Dark vs. light is never a default: write one sentence of physical scene (who uses this, where, under what light, in what mood) and let it force the answer. The warm cream near-white body background is the saturated AI default; where the axis is free, pick a background that is a choice.
 
+- Name a real reference before picking a strategy; unnamed ambition becomes beige.
+- Palette IS voice: a calm brand and a restless brand should not share palette mechanics, and each new surface differentiates from the last.
+- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
+
 ## Type and imagery for new Persuade and Experience surfaces
 
 Choose faces like objects from the brand's world; these training-data defaults mean you stopped looking: Fraunces, Playfair Display, Cormorant, Lora, Crimson, Newsreader, Syne, Space Grotesk, Space Mono, IBM Plex, Inter-as-display, DM Sans, DM Serif, Outfit, Plus Jakarta Sans, Instrument Sans. (For Operate and Read surfaces the opposite holds: system stacks and workhorse UI faces are legitimate and often correct.)
@@ -34,4 +38,10 @@ Imagery-implying briefs (food, travel, place, product, fashion) must ship real,
 
 AI-generated interfaces cluster around a few looks regardless of subject: warm cream + high-contrast serif + terracotta accent; near-black + one neon accent (acid green, cyan) + glowing edges; broadsheet-editorial hairlines + italic display serif + small tracked mono labels. All are legitimate when the brief calls for them; the brief always wins. Where the brief leaves the aesthetic free, landing in one of them means your self-check failed. Same one tier deeper: if someone could guess your aesthetic from the category alone, or from category-plus-avoidance, rework until neither answer is obvious.
 
+**Name the aesthetic lane, then test it.** Before committing to moves, say which lane this is (a specimen page, minimal-cool tech, acid maximalism...). Then the inverse test: describe what you're about to build the way a competitor would describe theirs; if that sentence fits the modal page in the category, restart. Currently saturated lanes count as reflexes, not choices, when the brief doesn't require them; the flooded one right now is editorial-typographic (display serif, often italic, small mono labels, ruled separators, monochromatic restraint, no imagery).
+
+## Persuade and Experience moves
+
+Layout: asymmetric compositions and intentional grid breaks are on the table; fluid spacing with `clamp()` that breathes on larger viewports; for image-led briefs, full-bleed hero imagery with overlaid navigation is a canonical move, letting the photograph be the design. Permissions the Operate world doesn't get: ambitious first-load motion (one orchestrated page-load beats scattered micro-interactions; skipping entrance motion entirely is also a voice), single-purpose viewports (one dominant idea per fold, deliberate pacing), and art direction per section when the narrative demands it; consistency of voice beats consistency of treatment.
+
 Before finishing, verify against SKILL.md's craft floor and run the detector; a bold page that ships mechanical defects is not done.
diff --git a/.agents/skills/impeccable/reference/operate.md b/.agents/skills/impeccable/reference/operate.md
new file mode 100644
index 000000000..04ee9d7d2
--- /dev/null
+++ b/.agents/skills/impeccable/reference/operate.md
@@ -0,0 +1,60 @@
+# Operate mode depth (and Read notes)
+
+When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
+
+## The product slop test
+
+Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
+
+Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
+
+## Typography
+
+- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
+- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
+- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
+- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
+
+## Color
+
+Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
+
+- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
+- Accent color used for primary actions, current selection, and state indicators only, not decoration.
+- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
+
+## Layout
+
+- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
+
+## Components
+
+Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
+
+- Skeleton states for loading, not spinners in the middle of content.
+- Empty states that teach the interface, not "nothing here."
+- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
+
+## Motion
+
+- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
+- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
+- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
+
+## Product bans (on top of the shared absolute bans)
+
+- Decorative motion that doesn't convey state.
+- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
+- Display fonts in UI labels, buttons, data.
+- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
+- Heavy color or full-saturation accents on inactive states.
+- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
+
+## Product permissions
+
+Product can afford things brand surfaces can't.
+
+- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
+- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
+- Density. Tables with many rows, panels with many labels, dense information when users need it.
+- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
diff --git a/.agents/skills/impeccable/reference/product.md b/.agents/skills/impeccable/reference/product.md
index 47d6c1373..ccd31d2c1 100644
--- a/.agents/skills/impeccable/reference/product.md
+++ b/.agents/skills/impeccable/reference/product.md
@@ -1,60 +1,3 @@
-# Product family depth (Operate and Read surfaces)
+# Moved
 
-When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
-
-## The product slop test
-
-Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
-
-Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
-
-## Typography
-
-- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
-- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
-- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
-- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
-
-## Color
-
-Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
-
-- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
-- Accent color used for primary actions, current selection, and state indicators only, not decoration.
-- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
-
-## Layout
-
-- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
-
-## Components
-
-Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
-
-- Skeleton states for loading, not spinners in the middle of content.
-- Empty states that teach the interface, not "nothing here."
-- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
-
-## Motion
-
-- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
-- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
-- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
-
-## Product bans (on top of the shared absolute bans)
-
-- Decorative motion that doesn't convey state.
-- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
-- Display fonts in UI labels, buttons, data.
-- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
-- Heavy color or full-saturation accents on inactive states.
-- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
-
-## Product permissions
-
-Product can afford things brand surfaces can't.
-
-- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
-- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
-- Density. Tables with many rows, panels with many labels, dense information when users need it.
-- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
+Operate and Read depth lives in [operate.md](operate.md). The mode essentials are in SKILL.md. This stub remains because `PRODUCT.md` files with `register: product` and older links point here.
diff --git a/.agents/skills/impeccable/reference/typeset.md b/.agents/skills/impeccable/reference/typeset.md
index 12df1f996..8bb46e2f7 100644
--- a/.agents/skills/impeccable/reference/typeset.md
+++ b/.agents/skills/impeccable/reference/typeset.md
@@ -185,7 +185,7 @@ Use `ch` units for character-based measure (`max-width: 65ch`). Line-height scal
 
 #### Font Selection & Pairing
 
-The tactical selection procedure and the reflex-reject list live in [reference/brand.md](brand.md) under **Font selection procedure** and **Reflex-reject list** (loaded for brand-register tasks). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
+The tactical selection procedure and the reflex-reject list live in [new-work.md](new-work.md) (loaded for new identity work). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
 
 ##### Anti-reflexes worth defending against
 
diff --git a/.agents/skills/impeccable/scripts/context.mjs b/.agents/skills/impeccable/scripts/context.mjs
index 15829a157..c13990ee0 100644
--- a/.agents/skills/impeccable/scripts/context.mjs
+++ b/.agents/skills/impeccable/scripts/context.mjs
@@ -940,7 +940,7 @@ async function cli() {
     );
   }
   if (register) {
-    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md; \`reference/${register}.md\` has extended depth for substantial work.`);
+    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md.`);
   }
   const platform = extractPlatform(ctx.product);
   const nativeRefs =
diff --git a/.claude/skills/impeccable/SKILL.md b/.claude/skills/impeccable/SKILL.md
index 8645c49ff..c84d959dd 100644
--- a/.claude/skills/impeccable/SKILL.md
+++ b/.claude/skills/impeccable/SKILL.md
@@ -41,7 +41,7 @@ Build to this floor without announcing it. The design detector (the project hook
 
 ## Registers
 
-Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode. PRODUCT.md's `register` field names the family (`brand` covers Persuade and Experience; `product` covers Operate and Read), and `reference/brand.md` / `reference/product.md` carry extended depth for the two families.
+Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode; PRODUCT.md's `register` field survives only as a family hint (`brand` covers Persuade and Experience, `product` covers Operate and Read). Depth beyond the paragraphs below: [reference/new-work.md](reference/new-work.md) when inventing identity, [reference/operate.md](reference/operate.md) for substantial Operate and Read work.
 
 **Persuade** (landing pages, marketing, campaigns; design IS the product). The deliverable is an impression that stops the scroll, earns the click, converts. Spans every genre (tech, luxury, consumer); don't collapse them into one look. Briefs that imply imagery must ship real, verified imagery; a colored rectangle where a photo belongs reads as incomplete. New Persuade surfaces take their typeface procedure and reject list from [reference/new-work.md](reference/new-work.md).
 
diff --git a/.claude/skills/impeccable/reference/brand.md b/.claude/skills/impeccable/reference/brand.md
index 01af65d27..0f0184c0d 100644
--- a/.claude/skills/impeccable/reference/brand.md
+++ b/.claude/skills/impeccable/reference/brand.md
@@ -1,42 +1,3 @@
-# Brand family depth (Persuade and Experience surfaces)
+# Moved
 
-When design IS the product: brand sites, landing pages, campaign pages, portfolios, long-form content, about pages. The essentials live in SKILL.md (modes, craft floor) and, for new identity work, in [new-work.md](new-work.md); this file is extended depth for substantial brand work. Rules stated in those files are not repeated here.
-
-The register spans every genre. A tech brand, a luxury hotel, a restaurant, a band's album page, an agency portfolio. They share a stance (*communicate, not transact*) and diverge wildly in aesthetic. Don't collapse them into one look.
-
-## The aesthetic-lane test
-
-Before committing to moves, name the lane. A type-foundry specimen page is one lane; minimal-cool tech is another; acid-maximalism is another. Don't drift into editorial-magazine aesthetics on a brief that isn't editorial; a hiking brand with italic drop caps has the wrong register within the register.
-
-Then the inverse test: in one sentence, describe what you're about to build the way a competitor would describe theirs. If that sentence fits the modal landing page in the category, restart.
-
-### Reflex-reject aesthetic lanes
-
-Currently saturated aesthetic families that have flooded brand surfaces. If a brief lands in one of these lanes without a register reason that *requires* it (a literal magazine, a literal terminal), it's the second-order training reflex: the trap one tier deeper than a reflex font pick. Look further.
-
-- **Editorial-typographic.** Display serif (often italic) + small mono labels + ruled separators + monochromatic restraint. The fingerprint: three rule-separated columns, an italic serif headline, lowercase track-spaced metadata, no imagery.
-
-(Entries land and leave this list as families saturate and fade.)
-
-The reflex-reject lists apply to **new design choices**. When the existing brand has already committed to a font or a lane as part of its identity, identity-preservation wins.
-
-## Color
-
-- Name a real reference before picking a strategy; unnamed ambition becomes beige.
-- Palette IS voice. A calm brand and a restless brand should not share palette mechanics.
-- Don't converge across projects. Each brand surface differentiates from the last.
-- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
-
-## Layout
-
-- Asymmetric compositions are one option. Break the grid intentionally for emphasis.
-- Fluid spacing with `clamp()` that breathes on larger viewports.
-- For image-led briefs (hotels, restaurants, magazines, photography), full-bleed hero imagery with overlaid menu and centered headline is a canonical move; let the photograph be the design.
-
-## Brand permissions
-
-Brand can afford things product can't. Take them.
-
-- Ambitious first-load motion. Reveals and typographic choreography that earn their place; one orchestrated page-load beats scattered micro-interactions, and some brands skip entrance motion entirely, which is also a voice.
-- Single-purpose viewports. One dominant idea per fold, long scroll, deliberate pacing.
-- Art direction per section. Different sections can have different visual worlds if the narrative demands it. Consistency of voice beats consistency of treatment.
+The Persuade and Experience essentials are in SKILL.md; the depth for inventing new identity (typeface procedure, reject list and lanes, color discipline, layout moves, permissions) lives in [new-work.md](new-work.md). This stub remains because `PRODUCT.md` files with `register: brand` and older links point here.
diff --git a/.claude/skills/impeccable/reference/live.md b/.claude/skills/impeccable/reference/live.md
index 8c2cccd0a..b20cee04a 100644
--- a/.claude/skills/impeccable/reference/live.md
+++ b/.claude/skills/impeccable/reference/live.md
@@ -109,7 +109,7 @@ node .claude/skills/impeccable/scripts/live-insert.mjs --id EVENT_ID --count EVE
 - `--position` ← `event.insert.position` (`before` | `after`)
 - Anchor flags ← `event.insert.anchor` (same mapping as wrap: id, classes, tag, text)
 
-The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. Load `brand.md` or `product.md` (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
+The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. For Operate/Read surfaces load `operate.md`; Persuade/Experience surfaces use SKILL.md's mode guidance plus `new-work.md` when the variant invents identity (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
 
 For Svelte/SvelteKit targets, `live-insert.mjs` returns `previewMode: "svelte-component"` with `mode: "insert"`, `file` pointing at a temporary `node_modules/.impeccable-live/<id>/manifest.json`, `componentDir` pointing at the variant component files, and `sourceFile` pointing at the real `.svelte` route. Write each inserted variant as a real Svelte component (`v1.svelte`, `v2.svelte`, …) under `componentDir`. Insert variants must be non-empty net-new content with a single top-level root, no `data-impeccable-*` attributes, and CSS in each component's `<style>` block. Do **not** edit the route source during generation; the browser mounts the temporary component before/after the live anchor while the user cycles variants. On Accept, `live-accept.mjs` inserts the selected component markup into `sourceFile` immediately and deletes the temp session after the source write succeeds.
 
@@ -187,7 +187,7 @@ All three carry `fallback: "agent-driven"`. Follow **Handle fallback** below.
 
 ### 3. Load the action's reference
 
-If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded register reference (`brand.md` or `product.md`). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
+If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded mode depth (`operate.md` for Operate/Read; `new-work.md` when the variant invents identity). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
 
 Any other `event.action` (`bolder`, `quieter`, `distill`, `polish`, `typeset`, `colorize`, `layout`, `adapt`, `animate`, `delight`, `overdrive`): Read `reference/<action>.md` before planning. Each sub-command encodes a specific discipline; skipping its reference produces generic output. Those files may require specific params; layer them on top of the §7 budget, not instead of it.
 
@@ -252,7 +252,7 @@ Instead, work from the brand:
 
 1. Read PRODUCT.md's Brand Personality words. What physical, spatial, or material experiences would embody those words if design were not involved? (A personality described as "specific, earned, unmistakable" evokes a hand-stamped letter, a numbered print, a watchmaker's loupe. A personality described as "restless, loud, unfiltered" evokes a concert poster, a spray-painted wall, a megaphone.)
 2. From those physical experiences, derive three visual directions that are genuinely different from each other AND from the current surface you're departing.
-3. Avoid the **reflex-reject lanes** in [brand.md](brand.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
+3. Avoid the **reflex-reject lanes** in [new-work.md](new-work.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
 4. Each direction must be expressible in one concrete sentence that names a real-world referent ("a museum exhibition label system for a contemporary art gallery" not "clean and minimal"). If your sentence contains only adjectives, it's not concrete enough.
 5. **While planning each direction, also name its 2–3 parameter knobs** (per the §7 budget table). The same principle as default mode: decide "what's tunable" during planning, not after writing the HTML. A departure-mode hero with 0 parameters is not "bold creative vision," it's a missed opportunity for the user to fine-tune the direction they pick.
 
diff --git a/.claude/skills/impeccable/reference/new-work.md b/.claude/skills/impeccable/reference/new-work.md
index 13c8f054b..28fc63d23 100644
--- a/.claude/skills/impeccable/reference/new-work.md
+++ b/.claude/skills/impeccable/reference/new-work.md
@@ -24,6 +24,10 @@ Plan a compact token system in your reasoning: palette, type, layout concept in
 
 Pick a color strategy before picking colors: Restrained (neutrals + one accent; the default when the visitor came to operate or read) / Committed (one saturated color carries 30-60% of the surface) / Full palette (3-4 named roles) / Drenched (the surface IS the color). Persuade and Experience surfaces have permission for the bolder strategies; take them when the brief allows. Dark vs. light is never a default: write one sentence of physical scene (who uses this, where, under what light, in what mood) and let it force the answer. The warm cream near-white body background is the saturated AI default; where the axis is free, pick a background that is a choice.
 
+- Name a real reference before picking a strategy; unnamed ambition becomes beige.
+- Palette IS voice: a calm brand and a restless brand should not share palette mechanics, and each new surface differentiates from the last.
+- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
+
 ## Type and imagery for new Persuade and Experience surfaces
 
 Choose faces like objects from the brand's world; these training-data defaults mean you stopped looking: Fraunces, Playfair Display, Cormorant, Lora, Crimson, Newsreader, Syne, Space Grotesk, Space Mono, IBM Plex, Inter-as-display, DM Sans, DM Serif, Outfit, Plus Jakarta Sans, Instrument Sans. (For Operate and Read surfaces the opposite holds: system stacks and workhorse UI faces are legitimate and often correct.)
@@ -34,4 +38,10 @@ Imagery-implying briefs (food, travel, place, product, fashion) must ship real,
 
 AI-generated interfaces cluster around a few looks regardless of subject: warm cream + high-contrast serif + terracotta accent; near-black + one neon accent (acid green, cyan) + glowing edges; broadsheet-editorial hairlines + italic display serif + small tracked mono labels. All are legitimate when the brief calls for them; the brief always wins. Where the brief leaves the aesthetic free, landing in one of them means your self-check failed. Same one tier deeper: if someone could guess your aesthetic from the category alone, or from category-plus-avoidance, rework until neither answer is obvious.
 
+**Name the aesthetic lane, then test it.** Before committing to moves, say which lane this is (a specimen page, minimal-cool tech, acid maximalism...). Then the inverse test: describe what you're about to build the way a competitor would describe theirs; if that sentence fits the modal page in the category, restart. Currently saturated lanes count as reflexes, not choices, when the brief doesn't require them; the flooded one right now is editorial-typographic (display serif, often italic, small mono labels, ruled separators, monochromatic restraint, no imagery).
+
+## Persuade and Experience moves
+
+Layout: asymmetric compositions and intentional grid breaks are on the table; fluid spacing with `clamp()` that breathes on larger viewports; for image-led briefs, full-bleed hero imagery with overlaid navigation is a canonical move, letting the photograph be the design. Permissions the Operate world doesn't get: ambitious first-load motion (one orchestrated page-load beats scattered micro-interactions; skipping entrance motion entirely is also a voice), single-purpose viewports (one dominant idea per fold, deliberate pacing), and art direction per section when the narrative demands it; consistency of voice beats consistency of treatment.
+
 Before finishing, verify against SKILL.md's craft floor and run the detector; a bold page that ships mechanical defects is not done.
diff --git a/.claude/skills/impeccable/reference/operate.md b/.claude/skills/impeccable/reference/operate.md
new file mode 100644
index 000000000..04ee9d7d2
--- /dev/null
+++ b/.claude/skills/impeccable/reference/operate.md
@@ -0,0 +1,60 @@
+# Operate mode depth (and Read notes)
+
+When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
+
+## The product slop test
+
+Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
+
+Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
+
+## Typography
+
+- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
+- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
+- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
+- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
+
+## Color
+
+Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
+
+- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
+- Accent color used for primary actions, current selection, and state indicators only, not decoration.
+- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
+
+## Layout
+
+- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
+
+## Components
+
+Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
+
+- Skeleton states for loading, not spinners in the middle of content.
+- Empty states that teach the interface, not "nothing here."
+- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
+
+## Motion
+
+- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
+- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
+- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
+
+## Product bans (on top of the shared absolute bans)
+
+- Decorative motion that doesn't convey state.
+- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
+- Display fonts in UI labels, buttons, data.
+- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
+- Heavy color or full-saturation accents on inactive states.
+- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
+
+## Product permissions
+
+Product can afford things brand surfaces can't.
+
+- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
+- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
+- Density. Tables with many rows, panels with many labels, dense information when users need it.
+- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
diff --git a/.claude/skills/impeccable/reference/product.md b/.claude/skills/impeccable/reference/product.md
index 47d6c1373..ccd31d2c1 100644
--- a/.claude/skills/impeccable/reference/product.md
+++ b/.claude/skills/impeccable/reference/product.md
@@ -1,60 +1,3 @@
-# Product family depth (Operate and Read surfaces)
+# Moved
 
-When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
-
-## The product slop test
-
-Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
-
-Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
-
-## Typography
-
-- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
-- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
-- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
-- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
-
-## Color
-
-Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
-
-- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
-- Accent color used for primary actions, current selection, and state indicators only, not decoration.
-- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
-
-## Layout
-
-- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
-
-## Components
-
-Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
-
-- Skeleton states for loading, not spinners in the middle of content.
-- Empty states that teach the interface, not "nothing here."
-- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
-
-## Motion
-
-- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
-- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
-- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
-
-## Product bans (on top of the shared absolute bans)
-
-- Decorative motion that doesn't convey state.
-- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
-- Display fonts in UI labels, buttons, data.
-- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
-- Heavy color or full-saturation accents on inactive states.
-- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
-
-## Product permissions
-
-Product can afford things brand surfaces can't.
-
-- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
-- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
-- Density. Tables with many rows, panels with many labels, dense information when users need it.
-- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
+Operate and Read depth lives in [operate.md](operate.md). The mode essentials are in SKILL.md. This stub remains because `PRODUCT.md` files with `register: product` and older links point here.
diff --git a/.claude/skills/impeccable/reference/typeset.md b/.claude/skills/impeccable/reference/typeset.md
index 819807f9e..c39fb6836 100644
--- a/.claude/skills/impeccable/reference/typeset.md
+++ b/.claude/skills/impeccable/reference/typeset.md
@@ -185,7 +185,7 @@ Use `ch` units for character-based measure (`max-width: 65ch`). Line-height scal
 
 #### Font Selection & Pairing
 
-The tactical selection procedure and the reflex-reject list live in [reference/brand.md](brand.md) under **Font selection procedure** and **Reflex-reject list** (loaded for brand-register tasks). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
+The tactical selection procedure and the reflex-reject list live in [new-work.md](new-work.md) (loaded for new identity work). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
 
 ##### Anti-reflexes worth defending against
 
diff --git a/.claude/skills/impeccable/scripts/context.mjs b/.claude/skills/impeccable/scripts/context.mjs
index 15829a157..c13990ee0 100644
--- a/.claude/skills/impeccable/scripts/context.mjs
+++ b/.claude/skills/impeccable/scripts/context.mjs
@@ -940,7 +940,7 @@ async function cli() {
     );
   }
   if (register) {
-    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md; \`reference/${register}.md\` has extended depth for substantial work.`);
+    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md.`);
   }
   const platform = extractPlatform(ctx.product);
   const nativeRefs =
diff --git a/.cursor/skills/impeccable/SKILL.md b/.cursor/skills/impeccable/SKILL.md
index b3596b952..44810d4d5 100644
--- a/.cursor/skills/impeccable/SKILL.md
+++ b/.cursor/skills/impeccable/SKILL.md
@@ -36,7 +36,7 @@ Build to this floor without announcing it. The design detector (the project hook
 
 ## Registers
 
-Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode. PRODUCT.md's `register` field names the family (`brand` covers Persuade and Experience; `product` covers Operate and Read), and `reference/brand.md` / `reference/product.md` carry extended depth for the two families.
+Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode; PRODUCT.md's `register` field survives only as a family hint (`brand` covers Persuade and Experience, `product` covers Operate and Read). Depth beyond the paragraphs below: [reference/new-work.md](reference/new-work.md) when inventing identity, [reference/operate.md](reference/operate.md) for substantial Operate and Read work.
 
 **Persuade** (landing pages, marketing, campaigns; design IS the product). The deliverable is an impression that stops the scroll, earns the click, converts. Spans every genre (tech, luxury, consumer); don't collapse them into one look. Briefs that imply imagery must ship real, verified imagery; a colored rectangle where a photo belongs reads as incomplete. New Persuade surfaces take their typeface procedure and reject list from [reference/new-work.md](reference/new-work.md).
 
diff --git a/.cursor/skills/impeccable/reference/brand.md b/.cursor/skills/impeccable/reference/brand.md
index 01af65d27..0f0184c0d 100644
--- a/.cursor/skills/impeccable/reference/brand.md
+++ b/.cursor/skills/impeccable/reference/brand.md
@@ -1,42 +1,3 @@
-# Brand family depth (Persuade and Experience surfaces)
+# Moved
 
-When design IS the product: brand sites, landing pages, campaign pages, portfolios, long-form content, about pages. The essentials live in SKILL.md (modes, craft floor) and, for new identity work, in [new-work.md](new-work.md); this file is extended depth for substantial brand work. Rules stated in those files are not repeated here.
-
-The register spans every genre. A tech brand, a luxury hotel, a restaurant, a band's album page, an agency portfolio. They share a stance (*communicate, not transact*) and diverge wildly in aesthetic. Don't collapse them into one look.
-
-## The aesthetic-lane test
-
-Before committing to moves, name the lane. A type-foundry specimen page is one lane; minimal-cool tech is another; acid-maximalism is another. Don't drift into editorial-magazine aesthetics on a brief that isn't editorial; a hiking brand with italic drop caps has the wrong register within the register.
-
-Then the inverse test: in one sentence, describe what you're about to build the way a competitor would describe theirs. If that sentence fits the modal landing page in the category, restart.
-
-### Reflex-reject aesthetic lanes
-
-Currently saturated aesthetic families that have flooded brand surfaces. If a brief lands in one of these lanes without a register reason that *requires* it (a literal magazine, a literal terminal), it's the second-order training reflex: the trap one tier deeper than a reflex font pick. Look further.
-
-- **Editorial-typographic.** Display serif (often italic) + small mono labels + ruled separators + monochromatic restraint. The fingerprint: three rule-separated columns, an italic serif headline, lowercase track-spaced metadata, no imagery.
-
-(Entries land and leave this list as families saturate and fade.)
-
-The reflex-reject lists apply to **new design choices**. When the existing brand has already committed to a font or a lane as part of its identity, identity-preservation wins.
-
-## Color
-
-- Name a real reference before picking a strategy; unnamed ambition becomes beige.
-- Palette IS voice. A calm brand and a restless brand should not share palette mechanics.
-- Don't converge across projects. Each brand surface differentiates from the last.
-- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
-
-## Layout
-
-- Asymmetric compositions are one option. Break the grid intentionally for emphasis.
-- Fluid spacing with `clamp()` that breathes on larger viewports.
-- For image-led briefs (hotels, restaurants, magazines, photography), full-bleed hero imagery with overlaid menu and centered headline is a canonical move; let the photograph be the design.
-
-## Brand permissions
-
-Brand can afford things product can't. Take them.
-
-- Ambitious first-load motion. Reveals and typographic choreography that earn their place; one orchestrated page-load beats scattered micro-interactions, and some brands skip entrance motion entirely, which is also a voice.
-- Single-purpose viewports. One dominant idea per fold, long scroll, deliberate pacing.
-- Art direction per section. Different sections can have different visual worlds if the narrative demands it. Consistency of voice beats consistency of treatment.
+The Persuade and Experience essentials are in SKILL.md; the depth for inventing new identity (typeface procedure, reject list and lanes, color discipline, layout moves, permissions) lives in [new-work.md](new-work.md). This stub remains because `PRODUCT.md` files with `register: brand` and older links point here.
diff --git a/.cursor/skills/impeccable/reference/live.md b/.cursor/skills/impeccable/reference/live.md
index 7867eaa03..3d6009641 100644
--- a/.cursor/skills/impeccable/reference/live.md
+++ b/.cursor/skills/impeccable/reference/live.md
@@ -109,7 +109,7 @@ node .cursor/skills/impeccable/scripts/live-insert.mjs --id EVENT_ID --count EVE
 - `--position` ← `event.insert.position` (`before` | `after`)
 - Anchor flags ← `event.insert.anchor` (same mapping as wrap: id, classes, tag, text)
 
-The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. Load `brand.md` or `product.md` (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
+The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. For Operate/Read surfaces load `operate.md`; Persuade/Experience surfaces use SKILL.md's mode guidance plus `new-work.md` when the variant invents identity (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
 
 For Svelte/SvelteKit targets, `live-insert.mjs` returns `previewMode: "svelte-component"` with `mode: "insert"`, `file` pointing at a temporary `node_modules/.impeccable-live/<id>/manifest.json`, `componentDir` pointing at the variant component files, and `sourceFile` pointing at the real `.svelte` route. Write each inserted variant as a real Svelte component (`v1.svelte`, `v2.svelte`, …) under `componentDir`. Insert variants must be non-empty net-new content with a single top-level root, no `data-impeccable-*` attributes, and CSS in each component's `<style>` block. Do **not** edit the route source during generation; the browser mounts the temporary component before/after the live anchor while the user cycles variants. On Accept, `live-accept.mjs` inserts the selected component markup into `sourceFile` immediately and deletes the temp session after the source write succeeds.
 
@@ -187,7 +187,7 @@ All three carry `fallback: "agent-driven"`. Follow **Handle fallback** below.
 
 ### 3. Load the action's reference
 
-If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded register reference (`brand.md` or `product.md`). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
+If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded mode depth (`operate.md` for Operate/Read; `new-work.md` when the variant invents identity). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
 
 Any other `event.action` (`bolder`, `quieter`, `distill`, `polish`, `typeset`, `colorize`, `layout`, `adapt`, `animate`, `delight`, `overdrive`): Read `reference/<action>.md` before planning. Each sub-command encodes a specific discipline; skipping its reference produces generic output. Those files may require specific params; layer them on top of the §7 budget, not instead of it.
 
@@ -252,7 +252,7 @@ Instead, work from the brand:
 
 1. Read PRODUCT.md's Brand Personality words. What physical, spatial, or material experiences would embody those words if design were not involved? (A personality described as "specific, earned, unmistakable" evokes a hand-stamped letter, a numbered print, a watchmaker's loupe. A personality described as "restless, loud, unfiltered" evokes a concert poster, a spray-painted wall, a megaphone.)
 2. From those physical experiences, derive three visual directions that are genuinely different from each other AND from the current surface you're departing.
-3. Avoid the **reflex-reject lanes** in [brand.md](brand.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
+3. Avoid the **reflex-reject lanes** in [new-work.md](new-work.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
 4. Each direction must be expressible in one concrete sentence that names a real-world referent ("a museum exhibition label system for a contemporary art gallery" not "clean and minimal"). If your sentence contains only adjectives, it's not concrete enough.
 5. **While planning each direction, also name its 2–3 parameter knobs** (per the §7 budget table). The same principle as default mode: decide "what's tunable" during planning, not after writing the HTML. A departure-mode hero with 0 parameters is not "bold creative vision," it's a missed opportunity for the user to fine-tune the direction they pick.
 
diff --git a/.cursor/skills/impeccable/reference/new-work.md b/.cursor/skills/impeccable/reference/new-work.md
index bd7decef9..1ab0e0470 100644
--- a/.cursor/skills/impeccable/reference/new-work.md
+++ b/.cursor/skills/impeccable/reference/new-work.md
@@ -24,6 +24,10 @@ Plan a compact token system in your reasoning: palette, type, layout concept in
 
 Pick a color strategy before picking colors: Restrained (neutrals + one accent; the default when the visitor came to operate or read) / Committed (one saturated color carries 30-60% of the surface) / Full palette (3-4 named roles) / Drenched (the surface IS the color). Persuade and Experience surfaces have permission for the bolder strategies; take them when the brief allows. Dark vs. light is never a default: write one sentence of physical scene (who uses this, where, under what light, in what mood) and let it force the answer. The warm cream near-white body background is the saturated AI default; where the axis is free, pick a background that is a choice.
 
+- Name a real reference before picking a strategy; unnamed ambition becomes beige.
+- Palette IS voice: a calm brand and a restless brand should not share palette mechanics, and each new surface differentiates from the last.
+- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
+
 ## Type and imagery for new Persuade and Experience surfaces
 
 Choose faces like objects from the brand's world; these training-data defaults mean you stopped looking: Fraunces, Playfair Display, Cormorant, Lora, Crimson, Newsreader, Syne, Space Grotesk, Space Mono, IBM Plex, Inter-as-display, DM Sans, DM Serif, Outfit, Plus Jakarta Sans, Instrument Sans. (For Operate and Read surfaces the opposite holds: system stacks and workhorse UI faces are legitimate and often correct.)
@@ -34,4 +38,10 @@ Imagery-implying briefs (food, travel, place, product, fashion) must ship real,
 
 AI-generated interfaces cluster around a few looks regardless of subject: warm cream + high-contrast serif + terracotta accent; near-black + one neon accent (acid green, cyan) + glowing edges; broadsheet-editorial hairlines + italic display serif + small tracked mono labels. All are legitimate when the brief calls for them; the brief always wins. Where the brief leaves the aesthetic free, landing in one of them means your self-check failed. Same one tier deeper: if someone could guess your aesthetic from the category alone, or from category-plus-avoidance, rework until neither answer is obvious.
 
+**Name the aesthetic lane, then test it.** Before committing to moves, say which lane this is (a specimen page, minimal-cool tech, acid maximalism...). Then the inverse test: describe what you're about to build the way a competitor would describe theirs; if that sentence fits the modal page in the category, restart. Currently saturated lanes count as reflexes, not choices, when the brief doesn't require them; the flooded one right now is editorial-typographic (display serif, often italic, small mono labels, ruled separators, monochromatic restraint, no imagery).
+
+## Persuade and Experience moves
+
+Layout: asymmetric compositions and intentional grid breaks are on the table; fluid spacing with `clamp()` that breathes on larger viewports; for image-led briefs, full-bleed hero imagery with overlaid navigation is a canonical move, letting the photograph be the design. Permissions the Operate world doesn't get: ambitious first-load motion (one orchestrated page-load beats scattered micro-interactions; skipping entrance motion entirely is also a voice), single-purpose viewports (one dominant idea per fold, deliberate pacing), and art direction per section when the narrative demands it; consistency of voice beats consistency of treatment.
+
 Before finishing, verify against SKILL.md's craft floor and run the detector; a bold page that ships mechanical defects is not done.
diff --git a/.cursor/skills/impeccable/reference/operate.md b/.cursor/skills/impeccable/reference/operate.md
new file mode 100644
index 000000000..04ee9d7d2
--- /dev/null
+++ b/.cursor/skills/impeccable/reference/operate.md
@@ -0,0 +1,60 @@
+# Operate mode depth (and Read notes)
+
+When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
+
+## The product slop test
+
+Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
+
+Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
+
+## Typography
+
+- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
+- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
+- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
+- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
+
+## Color
+
+Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
+
+- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
+- Accent color used for primary actions, current selection, and state indicators only, not decoration.
+- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
+
+## Layout
+
+- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
+
+## Components
+
+Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
+
+- Skeleton states for loading, not spinners in the middle of content.
+- Empty states that teach the interface, not "nothing here."
+- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
+
+## Motion
+
+- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
+- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
+- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
+
+## Product bans (on top of the shared absolute bans)
+
+- Decorative motion that doesn't convey state.
+- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
+- Display fonts in UI labels, buttons, data.
+- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
+- Heavy color or full-saturation accents on inactive states.
+- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
+
+## Product permissions
+
+Product can afford things brand surfaces can't.
+
+- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
+- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
+- Density. Tables with many rows, panels with many labels, dense information when users need it.
+- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
diff --git a/.cursor/skills/impeccable/reference/product.md b/.cursor/skills/impeccable/reference/product.md
index 47d6c1373..ccd31d2c1 100644
--- a/.cursor/skills/impeccable/reference/product.md
+++ b/.cursor/skills/impeccable/reference/product.md
@@ -1,60 +1,3 @@
-# Product family depth (Operate and Read surfaces)
+# Moved
 
-When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
-
-## The product slop test
-
-Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
-
-Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
-
-## Typography
-
-- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
-- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
-- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
-- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
-
-## Color
-
-Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
-
-- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
-- Accent color used for primary actions, current selection, and state indicators only, not decoration.
-- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
-
-## Layout
-
-- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
-
-## Components
-
-Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
-
-- Skeleton states for loading, not spinners in the middle of content.
-- Empty states that teach the interface, not "nothing here."
-- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
-
-## Motion
-
-- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
-- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
-- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
-
-## Product bans (on top of the shared absolute bans)
-
-- Decorative motion that doesn't convey state.
-- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
-- Display fonts in UI labels, buttons, data.
-- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
-- Heavy color or full-saturation accents on inactive states.
-- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
-
-## Product permissions
-
-Product can afford things brand surfaces can't.
-
-- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
-- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
-- Density. Tables with many rows, panels with many labels, dense information when users need it.
-- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
+Operate and Read depth lives in [operate.md](operate.md). The mode essentials are in SKILL.md. This stub remains because `PRODUCT.md` files with `register: product` and older links point here.
diff --git a/.cursor/skills/impeccable/reference/typeset.md b/.cursor/skills/impeccable/reference/typeset.md
index 2423a19df..2137456ef 100644
--- a/.cursor/skills/impeccable/reference/typeset.md
+++ b/.cursor/skills/impeccable/reference/typeset.md
@@ -185,7 +185,7 @@ Use `ch` units for character-based measure (`max-width: 65ch`). Line-height scal
 
 #### Font Selection & Pairing
 
-The tactical selection procedure and the reflex-reject list live in [reference/brand.md](brand.md) under **Font selection procedure** and **Reflex-reject list** (loaded for brand-register tasks). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
+The tactical selection procedure and the reflex-reject list live in [new-work.md](new-work.md) (loaded for new identity work). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
 
 ##### Anti-reflexes worth defending against
 
diff --git a/.cursor/skills/impeccable/scripts/context.mjs b/.cursor/skills/impeccable/scripts/context.mjs
index 15829a157..c13990ee0 100644
--- a/.cursor/skills/impeccable/scripts/context.mjs
+++ b/.cursor/skills/impeccable/scripts/context.mjs
@@ -940,7 +940,7 @@ async function cli() {
     );
   }
   if (register) {
-    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md; \`reference/${register}.md\` has extended depth for substantial work.`);
+    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md.`);
   }
   const platform = extractPlatform(ctx.product);
   const nativeRefs =
diff --git a/.gemini/skills/impeccable/SKILL.md b/.gemini/skills/impeccable/SKILL.md
index 8344f0430..dd7515386 100644
--- a/.gemini/skills/impeccable/SKILL.md
+++ b/.gemini/skills/impeccable/SKILL.md
@@ -37,7 +37,7 @@ Build to this floor without announcing it. The design detector (the project hook
 
 ## Registers
 
-Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode. PRODUCT.md's `register` field names the family (`brand` covers Persuade and Experience; `product` covers Operate and Read), and `reference/brand.md` / `reference/product.md` carry extended depth for the two families.
+Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode; PRODUCT.md's `register` field survives only as a family hint (`brand` covers Persuade and Experience, `product` covers Operate and Read). Depth beyond the paragraphs below: [reference/new-work.md](reference/new-work.md) when inventing identity, [reference/operate.md](reference/operate.md) for substantial Operate and Read work.
 
 **Persuade** (landing pages, marketing, campaigns; design IS the product). The deliverable is an impression that stops the scroll, earns the click, converts. Spans every genre (tech, luxury, consumer); don't collapse them into one look. Briefs that imply imagery must ship real, verified imagery; a colored rectangle where a photo belongs reads as incomplete. New Persuade surfaces take their typeface procedure and reject list from [reference/new-work.md](reference/new-work.md).
 
diff --git a/.gemini/skills/impeccable/reference/brand.md b/.gemini/skills/impeccable/reference/brand.md
index 01af65d27..0f0184c0d 100644
--- a/.gemini/skills/impeccable/reference/brand.md
+++ b/.gemini/skills/impeccable/reference/brand.md
@@ -1,42 +1,3 @@
-# Brand family depth (Persuade and Experience surfaces)
+# Moved
 
-When design IS the product: brand sites, landing pages, campaign pages, portfolios, long-form content, about pages. The essentials live in SKILL.md (modes, craft floor) and, for new identity work, in [new-work.md](new-work.md); this file is extended depth for substantial brand work. Rules stated in those files are not repeated here.
-
-The register spans every genre. A tech brand, a luxury hotel, a restaurant, a band's album page, an agency portfolio. They share a stance (*communicate, not transact*) and diverge wildly in aesthetic. Don't collapse them into one look.
-
-## The aesthetic-lane test
-
-Before committing to moves, name the lane. A type-foundry specimen page is one lane; minimal-cool tech is another; acid-maximalism is another. Don't drift into editorial-magazine aesthetics on a brief that isn't editorial; a hiking brand with italic drop caps has the wrong register within the register.
-
-Then the inverse test: in one sentence, describe what you're about to build the way a competitor would describe theirs. If that sentence fits the modal landing page in the category, restart.
-
-### Reflex-reject aesthetic lanes
-
-Currently saturated aesthetic families that have flooded brand surfaces. If a brief lands in one of these lanes without a register reason that *requires* it (a literal magazine, a literal terminal), it's the second-order training reflex: the trap one tier deeper than a reflex font pick. Look further.
-
-- **Editorial-typographic.** Display serif (often italic) + small mono labels + ruled separators + monochromatic restraint. The fingerprint: three rule-separated columns, an italic serif headline, lowercase track-spaced metadata, no imagery.
-
-(Entries land and leave this list as families saturate and fade.)
-
-The reflex-reject lists apply to **new design choices**. When the existing brand has already committed to a font or a lane as part of its identity, identity-preservation wins.
-
-## Color
-
-- Name a real reference before picking a strategy; unnamed ambition becomes beige.
-- Palette IS voice. A calm brand and a restless brand should not share palette mechanics.
-- Don't converge across projects. Each brand surface differentiates from the last.
-- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
-
-## Layout
-
-- Asymmetric compositions are one option. Break the grid intentionally for emphasis.
-- Fluid spacing with `clamp()` that breathes on larger viewports.
-- For image-led briefs (hotels, restaurants, magazines, photography), full-bleed hero imagery with overlaid menu and centered headline is a canonical move; let the photograph be the design.
-
-## Brand permissions
-
-Brand can afford things product can't. Take them.
-
-- Ambitious first-load motion. Reveals and typographic choreography that earn their place; one orchestrated page-load beats scattered micro-interactions, and some brands skip entrance motion entirely, which is also a voice.
-- Single-purpose viewports. One dominant idea per fold, long scroll, deliberate pacing.
-- Art direction per section. Different sections can have different visual worlds if the narrative demands it. Consistency of voice beats consistency of treatment.
+The Persuade and Experience essentials are in SKILL.md; the depth for inventing new identity (typeface procedure, reject list and lanes, color discipline, layout moves, permissions) lives in [new-work.md](new-work.md). This stub remains because `PRODUCT.md` files with `register: brand` and older links point here.
diff --git a/.gemini/skills/impeccable/reference/live.md b/.gemini/skills/impeccable/reference/live.md
index c405f2833..5dc73138f 100644
--- a/.gemini/skills/impeccable/reference/live.md
+++ b/.gemini/skills/impeccable/reference/live.md
@@ -109,7 +109,7 @@ node .gemini/skills/impeccable/scripts/live-insert.mjs --id EVENT_ID --count EVE
 - `--position` ← `event.insert.position` (`before` | `after`)
 - Anchor flags ← `event.insert.anchor` (same mapping as wrap: id, classes, tag, text)
 
-The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. Load `brand.md` or `product.md` (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
+The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. For Operate/Read surfaces load `operate.md`; Persuade/Experience surfaces use SKILL.md's mode guidance plus `new-work.md` when the variant invents identity (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
 
 For Svelte/SvelteKit targets, `live-insert.mjs` returns `previewMode: "svelte-component"` with `mode: "insert"`, `file` pointing at a temporary `node_modules/.impeccable-live/<id>/manifest.json`, `componentDir` pointing at the variant component files, and `sourceFile` pointing at the real `.svelte` route. Write each inserted variant as a real Svelte component (`v1.svelte`, `v2.svelte`, …) under `componentDir`. Insert variants must be non-empty net-new content with a single top-level root, no `data-impeccable-*` attributes, and CSS in each component's `<style>` block. Do **not** edit the route source during generation; the browser mounts the temporary component before/after the live anchor while the user cycles variants. On Accept, `live-accept.mjs` inserts the selected component markup into `sourceFile` immediately and deletes the temp session after the source write succeeds.
 
@@ -187,7 +187,7 @@ All three carry `fallback: "agent-driven"`. Follow **Handle fallback** below.
 
 ### 3. Load the action's reference
 
-If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded register reference (`brand.md` or `product.md`). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
+If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded mode depth (`operate.md` for Operate/Read; `new-work.md` when the variant invents identity). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
 
 Any other `event.action` (`bolder`, `quieter`, `distill`, `polish`, `typeset`, `colorize`, `layout`, `adapt`, `animate`, `delight`, `overdrive`): Read `reference/<action>.md` before planning. Each sub-command encodes a specific discipline; skipping its reference produces generic output. Those files may require specific params; layer them on top of the §7 budget, not instead of it.
 
@@ -252,7 +252,7 @@ Instead, work from the brand:
 
 1. Read PRODUCT.md's Brand Personality words. What physical, spatial, or material experiences would embody those words if design were not involved? (A personality described as "specific, earned, unmistakable" evokes a hand-stamped letter, a numbered print, a watchmaker's loupe. A personality described as "restless, loud, unfiltered" evokes a concert poster, a spray-painted wall, a megaphone.)
 2. From those physical experiences, derive three visual directions that are genuinely different from each other AND from the current surface you're departing.
-3. Avoid the **reflex-reject lanes** in [brand.md](brand.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
+3. Avoid the **reflex-reject lanes** in [new-work.md](new-work.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
 4. Each direction must be expressible in one concrete sentence that names a real-world referent ("a museum exhibition label system for a contemporary art gallery" not "clean and minimal"). If your sentence contains only adjectives, it's not concrete enough.
 5. **While planning each direction, also name its 2–3 parameter knobs** (per the §7 budget table). The same principle as default mode: decide "what's tunable" during planning, not after writing the HTML. A departure-mode hero with 0 parameters is not "bold creative vision," it's a missed opportunity for the user to fine-tune the direction they pick.
 
diff --git a/.gemini/skills/impeccable/reference/new-work.md b/.gemini/skills/impeccable/reference/new-work.md
index 669148061..da1d268ee 100644
--- a/.gemini/skills/impeccable/reference/new-work.md
+++ b/.gemini/skills/impeccable/reference/new-work.md
@@ -24,6 +24,10 @@ Plan a compact token system in your reasoning: palette, type, layout concept in
 
 Pick a color strategy before picking colors: Restrained (neutrals + one accent; the default when the visitor came to operate or read) / Committed (one saturated color carries 30-60% of the surface) / Full palette (3-4 named roles) / Drenched (the surface IS the color). Persuade and Experience surfaces have permission for the bolder strategies; take them when the brief allows. Dark vs. light is never a default: write one sentence of physical scene (who uses this, where, under what light, in what mood) and let it force the answer. The warm cream near-white body background is the saturated AI default; where the axis is free, pick a background that is a choice.
 
+- Name a real reference before picking a strategy; unnamed ambition becomes beige.
+- Palette IS voice: a calm brand and a restless brand should not share palette mechanics, and each new surface differentiates from the last.
+- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
+
 ## Type and imagery for new Persuade and Experience surfaces
 
 Choose faces like objects from the brand's world; these training-data defaults mean you stopped looking: Fraunces, Playfair Display, Cormorant, Lora, Crimson, Newsreader, Syne, Space Grotesk, Space Mono, IBM Plex, Inter-as-display, DM Sans, DM Serif, Outfit, Plus Jakarta Sans, Instrument Sans. (For Operate and Read surfaces the opposite holds: system stacks and workhorse UI faces are legitimate and often correct.)
@@ -34,4 +38,10 @@ Imagery-implying briefs (food, travel, place, product, fashion) must ship real,
 
 AI-generated interfaces cluster around a few looks regardless of subject: warm cream + high-contrast serif + terracotta accent; near-black + one neon accent (acid green, cyan) + glowing edges; broadsheet-editorial hairlines + italic display serif + small tracked mono labels. All are legitimate when the brief calls for them; the brief always wins. Where the brief leaves the aesthetic free, landing in one of them means your self-check failed. Same one tier deeper: if someone could guess your aesthetic from the category alone, or from category-plus-avoidance, rework until neither answer is obvious.
 
+**Name the aesthetic lane, then test it.** Before committing to moves, say which lane this is (a specimen page, minimal-cool tech, acid maximalism...). Then the inverse test: describe what you're about to build the way a competitor would describe theirs; if that sentence fits the modal page in the category, restart. Currently saturated lanes count as reflexes, not choices, when the brief doesn't require them; the flooded one right now is editorial-typographic (display serif, often italic, small mono labels, ruled separators, monochromatic restraint, no imagery).
+
+## Persuade and Experience moves
+
+Layout: asymmetric compositions and intentional grid breaks are on the table; fluid spacing with `clamp()` that breathes on larger viewports; for image-led briefs, full-bleed hero imagery with overlaid navigation is a canonical move, letting the photograph be the design. Permissions the Operate world doesn't get: ambitious first-load motion (one orchestrated page-load beats scattered micro-interactions; skipping entrance motion entirely is also a voice), single-purpose viewports (one dominant idea per fold, deliberate pacing), and art direction per section when the narrative demands it; consistency of voice beats consistency of treatment.
+
 Before finishing, verify against SKILL.md's craft floor and run the detector; a bold page that ships mechanical defects is not done.
diff --git a/.gemini/skills/impeccable/reference/operate.md b/.gemini/skills/impeccable/reference/operate.md
new file mode 100644
index 000000000..04ee9d7d2
--- /dev/null
+++ b/.gemini/skills/impeccable/reference/operate.md
@@ -0,0 +1,60 @@
+# Operate mode depth (and Read notes)
+
+When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
+
+## The product slop test
+
+Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
+
+Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
+
+## Typography
+
+- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
+- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
+- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
+- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
+
+## Color
+
+Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
+
+- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
+- Accent color used for primary actions, current selection, and state indicators only, not decoration.
+- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
+
+## Layout
+
+- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
+
+## Components
+
+Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
+
+- Skeleton states for loading, not spinners in the middle of content.
+- Empty states that teach the interface, not "nothing here."
+- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
+
+## Motion
+
+- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
+- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
+- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
+
+## Product bans (on top of the shared absolute bans)
+
+- Decorative motion that doesn't convey state.
+- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
+- Display fonts in UI labels, buttons, data.
+- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
+- Heavy color or full-saturation accents on inactive states.
+- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
+
+## Product permissions
+
+Product can afford things brand surfaces can't.
+
+- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
+- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
+- Density. Tables with many rows, panels with many labels, dense information when users need it.
+- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
diff --git a/.gemini/skills/impeccable/reference/product.md b/.gemini/skills/impeccable/reference/product.md
index 47d6c1373..ccd31d2c1 100644
--- a/.gemini/skills/impeccable/reference/product.md
+++ b/.gemini/skills/impeccable/reference/product.md
@@ -1,60 +1,3 @@
-# Product family depth (Operate and Read surfaces)
+# Moved
 
-When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
-
-## The product slop test
-
-Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
-
-Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
-
-## Typography
-
-- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
-- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
-- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
-- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
-
-## Color
-
-Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
-
-- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
-- Accent color used for primary actions, current selection, and state indicators only, not decoration.
-- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
-
-## Layout
-
-- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
-
-## Components
-
-Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
-
-- Skeleton states for loading, not spinners in the middle of content.
-- Empty states that teach the interface, not "nothing here."
-- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
-
-## Motion
-
-- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
-- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
-- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
-
-## Product bans (on top of the shared absolute bans)
-
-- Decorative motion that doesn't convey state.
-- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
-- Display fonts in UI labels, buttons, data.
-- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
-- Heavy color or full-saturation accents on inactive states.
-- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
-
-## Product permissions
-
-Product can afford things brand surfaces can't.
-
-- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
-- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
-- Density. Tables with many rows, panels with many labels, dense information when users need it.
-- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
+Operate and Read depth lives in [operate.md](operate.md). The mode essentials are in SKILL.md. This stub remains because `PRODUCT.md` files with `register: product` and older links point here.
diff --git a/.gemini/skills/impeccable/reference/typeset.md b/.gemini/skills/impeccable/reference/typeset.md
index 046d84aee..3a761e449 100644
--- a/.gemini/skills/impeccable/reference/typeset.md
+++ b/.gemini/skills/impeccable/reference/typeset.md
@@ -185,7 +185,7 @@ Use `ch` units for character-based measure (`max-width: 65ch`). Line-height scal
 
 #### Font Selection & Pairing
 
-The tactical selection procedure and the reflex-reject list live in [reference/brand.md](brand.md) under **Font selection procedure** and **Reflex-reject list** (loaded for brand-register tasks). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
+The tactical selection procedure and the reflex-reject list live in [new-work.md](new-work.md) (loaded for new identity work). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
 
 ##### Anti-reflexes worth defending against
 
diff --git a/.gemini/skills/impeccable/scripts/context.mjs b/.gemini/skills/impeccable/scripts/context.mjs
index 15829a157..c13990ee0 100644
--- a/.gemini/skills/impeccable/scripts/context.mjs
+++ b/.gemini/skills/impeccable/scripts/context.mjs
@@ -940,7 +940,7 @@ async function cli() {
     );
   }
   if (register) {
-    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md; \`reference/${register}.md\` has extended depth for substantial work.`);
+    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md.`);
   }
   const platform = extractPlatform(ctx.product);
   const nativeRefs =
diff --git a/.github/skills/impeccable/SKILL.md b/.github/skills/impeccable/SKILL.md
index 3e57e8a38..0f1e4c2f8 100644
--- a/.github/skills/impeccable/SKILL.md
+++ b/.github/skills/impeccable/SKILL.md
@@ -38,7 +38,7 @@ Build to this floor without announcing it. The design detector (the project hook
 
 ## Registers
 
-Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode. PRODUCT.md's `register` field names the family (`brand` covers Persuade and Experience; `product` covers Operate and Read), and `reference/brand.md` / `reference/product.md` carry extended depth for the two families.
+Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode; PRODUCT.md's `register` field survives only as a family hint (`brand` covers Persuade and Experience, `product` covers Operate and Read). Depth beyond the paragraphs below: [reference/new-work.md](reference/new-work.md) when inventing identity, [reference/operate.md](reference/operate.md) for substantial Operate and Read work.
 
 **Persuade** (landing pages, marketing, campaigns; design IS the product). The deliverable is an impression that stops the scroll, earns the click, converts. Spans every genre (tech, luxury, consumer); don't collapse them into one look. Briefs that imply imagery must ship real, verified imagery; a colored rectangle where a photo belongs reads as incomplete. New Persuade surfaces take their typeface procedure and reject list from [reference/new-work.md](reference/new-work.md).
 
diff --git a/.github/skills/impeccable/reference/brand.md b/.github/skills/impeccable/reference/brand.md
index 01af65d27..0f0184c0d 100644
--- a/.github/skills/impeccable/reference/brand.md
+++ b/.github/skills/impeccable/reference/brand.md
@@ -1,42 +1,3 @@
-# Brand family depth (Persuade and Experience surfaces)
+# Moved
 
-When design IS the product: brand sites, landing pages, campaign pages, portfolios, long-form content, about pages. The essentials live in SKILL.md (modes, craft floor) and, for new identity work, in [new-work.md](new-work.md); this file is extended depth for substantial brand work. Rules stated in those files are not repeated here.
-
-The register spans every genre. A tech brand, a luxury hotel, a restaurant, a band's album page, an agency portfolio. They share a stance (*communicate, not transact*) and diverge wildly in aesthetic. Don't collapse them into one look.
-
-## The aesthetic-lane test
-
-Before committing to moves, name the lane. A type-foundry specimen page is one lane; minimal-cool tech is another; acid-maximalism is another. Don't drift into editorial-magazine aesthetics on a brief that isn't editorial; a hiking brand with italic drop caps has the wrong register within the register.
-
-Then the inverse test: in one sentence, describe what you're about to build the way a competitor would describe theirs. If that sentence fits the modal landing page in the category, restart.
-
-### Reflex-reject aesthetic lanes
-
-Currently saturated aesthetic families that have flooded brand surfaces. If a brief lands in one of these lanes without a register reason that *requires* it (a literal magazine, a literal terminal), it's the second-order training reflex: the trap one tier deeper than a reflex font pick. Look further.
-
-- **Editorial-typographic.** Display serif (often italic) + small mono labels + ruled separators + monochromatic restraint. The fingerprint: three rule-separated columns, an italic serif headline, lowercase track-spaced metadata, no imagery.
-
-(Entries land and leave this list as families saturate and fade.)
-
-The reflex-reject lists apply to **new design choices**. When the existing brand has already committed to a font or a lane as part of its identity, identity-preservation wins.
-
-## Color
-
-- Name a real reference before picking a strategy; unnamed ambition becomes beige.
-- Palette IS voice. A calm brand and a restless brand should not share palette mechanics.
-- Don't converge across projects. Each brand surface differentiates from the last.
-- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
-
-## Layout
-
-- Asymmetric compositions are one option. Break the grid intentionally for emphasis.
-- Fluid spacing with `clamp()` that breathes on larger viewports.
-- For image-led briefs (hotels, restaurants, magazines, photography), full-bleed hero imagery with overlaid menu and centered headline is a canonical move; let the photograph be the design.
-
-## Brand permissions
-
-Brand can afford things product can't. Take them.
-
-- Ambitious first-load motion. Reveals and typographic choreography that earn their place; one orchestrated page-load beats scattered micro-interactions, and some brands skip entrance motion entirely, which is also a voice.
-- Single-purpose viewports. One dominant idea per fold, long scroll, deliberate pacing.
-- Art direction per section. Different sections can have different visual worlds if the narrative demands it. Consistency of voice beats consistency of treatment.
+The Persuade and Experience essentials are in SKILL.md; the depth for inventing new identity (typeface procedure, reject list and lanes, color discipline, layout moves, permissions) lives in [new-work.md](new-work.md). This stub remains because `PRODUCT.md` files with `register: brand` and older links point here.
diff --git a/.github/skills/impeccable/reference/live.md b/.github/skills/impeccable/reference/live.md
index 854ff85da..65ada3d79 100644
--- a/.github/skills/impeccable/reference/live.md
+++ b/.github/skills/impeccable/reference/live.md
@@ -109,7 +109,7 @@ node .github/skills/impeccable/scripts/live-insert.mjs --id EVENT_ID --count EVE
 - `--position` ← `event.insert.position` (`before` | `after`)
 - Anchor flags ← `event.insert.anchor` (same mapping as wrap: id, classes, tag, text)
 
-The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. Load `brand.md` or `product.md` (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
+The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. For Operate/Read surfaces load `operate.md`; Persuade/Experience surfaces use SKILL.md's mode guidance plus `new-work.md` when the variant invents identity (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
 
 For Svelte/SvelteKit targets, `live-insert.mjs` returns `previewMode: "svelte-component"` with `mode: "insert"`, `file` pointing at a temporary `node_modules/.impeccable-live/<id>/manifest.json`, `componentDir` pointing at the variant component files, and `sourceFile` pointing at the real `.svelte` route. Write each inserted variant as a real Svelte component (`v1.svelte`, `v2.svelte`, …) under `componentDir`. Insert variants must be non-empty net-new content with a single top-level root, no `data-impeccable-*` attributes, and CSS in each component's `<style>` block. Do **not** edit the route source during generation; the browser mounts the temporary component before/after the live anchor while the user cycles variants. On Accept, `live-accept.mjs` inserts the selected component markup into `sourceFile` immediately and deletes the temp session after the source write succeeds.
 
@@ -187,7 +187,7 @@ All three carry `fallback: "agent-driven"`. Follow **Handle fallback** below.
 
 ### 3. Load the action's reference
 
-If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded register reference (`brand.md` or `product.md`). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
+If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded mode depth (`operate.md` for Operate/Read; `new-work.md` when the variant invents identity). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
 
 Any other `event.action` (`bolder`, `quieter`, `distill`, `polish`, `typeset`, `colorize`, `layout`, `adapt`, `animate`, `delight`, `overdrive`): Read `reference/<action>.md` before planning. Each sub-command encodes a specific discipline; skipping its reference produces generic output. Those files may require specific params; layer them on top of the §7 budget, not instead of it.
 
@@ -252,7 +252,7 @@ Instead, work from the brand:
 
 1. Read PRODUCT.md's Brand Personality words. What physical, spatial, or material experiences would embody those words if design were not involved? (A personality described as "specific, earned, unmistakable" evokes a hand-stamped letter, a numbered print, a watchmaker's loupe. A personality described as "restless, loud, unfiltered" evokes a concert poster, a spray-painted wall, a megaphone.)
 2. From those physical experiences, derive three visual directions that are genuinely different from each other AND from the current surface you're departing.
-3. Avoid the **reflex-reject lanes** in [brand.md](brand.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
+3. Avoid the **reflex-reject lanes** in [new-work.md](new-work.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
 4. Each direction must be expressible in one concrete sentence that names a real-world referent ("a museum exhibition label system for a contemporary art gallery" not "clean and minimal"). If your sentence contains only adjectives, it's not concrete enough.
 5. **While planning each direction, also name its 2–3 parameter knobs** (per the §7 budget table). The same principle as default mode: decide "what's tunable" during planning, not after writing the HTML. A departure-mode hero with 0 parameters is not "bold creative vision," it's a missed opportunity for the user to fine-tune the direction they pick.
 
diff --git a/.github/skills/impeccable/reference/new-work.md b/.github/skills/impeccable/reference/new-work.md
index 352e93c18..19e6b3b4a 100644
--- a/.github/skills/impeccable/reference/new-work.md
+++ b/.github/skills/impeccable/reference/new-work.md
@@ -24,6 +24,10 @@ Plan a compact token system in your reasoning: palette, type, layout concept in
 
 Pick a color strategy before picking colors: Restrained (neutrals + one accent; the default when the visitor came to operate or read) / Committed (one saturated color carries 30-60% of the surface) / Full palette (3-4 named roles) / Drenched (the surface IS the color). Persuade and Experience surfaces have permission for the bolder strategies; take them when the brief allows. Dark vs. light is never a default: write one sentence of physical scene (who uses this, where, under what light, in what mood) and let it force the answer. The warm cream near-white body background is the saturated AI default; where the axis is free, pick a background that is a choice.
 
+- Name a real reference before picking a strategy; unnamed ambition becomes beige.
+- Palette IS voice: a calm brand and a restless brand should not share palette mechanics, and each new surface differentiates from the last.
+- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
+
 ## Type and imagery for new Persuade and Experience surfaces
 
 Choose faces like objects from the brand's world; these training-data defaults mean you stopped looking: Fraunces, Playfair Display, Cormorant, Lora, Crimson, Newsreader, Syne, Space Grotesk, Space Mono, IBM Plex, Inter-as-display, DM Sans, DM Serif, Outfit, Plus Jakarta Sans, Instrument Sans. (For Operate and Read surfaces the opposite holds: system stacks and workhorse UI faces are legitimate and often correct.)
@@ -34,4 +38,10 @@ Imagery-implying briefs (food, travel, place, product, fashion) must ship real,
 
 AI-generated interfaces cluster around a few looks regardless of subject: warm cream + high-contrast serif + terracotta accent; near-black + one neon accent (acid green, cyan) + glowing edges; broadsheet-editorial hairlines + italic display serif + small tracked mono labels. All are legitimate when the brief calls for them; the brief always wins. Where the brief leaves the aesthetic free, landing in one of them means your self-check failed. Same one tier deeper: if someone could guess your aesthetic from the category alone, or from category-plus-avoidance, rework until neither answer is obvious.
 
+**Name the aesthetic lane, then test it.** Before committing to moves, say which lane this is (a specimen page, minimal-cool tech, acid maximalism...). Then the inverse test: describe what you're about to build the way a competitor would describe theirs; if that sentence fits the modal page in the category, restart. Currently saturated lanes count as reflexes, not choices, when the brief doesn't require them; the flooded one right now is editorial-typographic (display serif, often italic, small mono labels, ruled separators, monochromatic restraint, no imagery).
+
+## Persuade and Experience moves
+
+Layout: asymmetric compositions and intentional grid breaks are on the table; fluid spacing with `clamp()` that breathes on larger viewports; for image-led briefs, full-bleed hero imagery with overlaid navigation is a canonical move, letting the photograph be the design. Permissions the Operate world doesn't get: ambitious first-load motion (one orchestrated page-load beats scattered micro-interactions; skipping entrance motion entirely is also a voice), single-purpose viewports (one dominant idea per fold, deliberate pacing), and art direction per section when the narrative demands it; consistency of voice beats consistency of treatment.
+
 Before finishing, verify against SKILL.md's craft floor and run the detector; a bold page that ships mechanical defects is not done.
diff --git a/.github/skills/impeccable/reference/operate.md b/.github/skills/impeccable/reference/operate.md
new file mode 100644
index 000000000..04ee9d7d2
--- /dev/null
+++ b/.github/skills/impeccable/reference/operate.md
@@ -0,0 +1,60 @@
+# Operate mode depth (and Read notes)
+
+When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
+
+## The product slop test
+
+Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
+
+Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
+
+## Typography
+
+- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
+- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
+- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
+- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
+
+## Color
+
+Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
+
+- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
+- Accent color used for primary actions, current selection, and state indicators only, not decoration.
+- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
+
+## Layout
+
+- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
+
+## Components
+
+Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
+
+- Skeleton states for loading, not spinners in the middle of content.
+- Empty states that teach the interface, not "nothing here."
+- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
+
+## Motion
+
+- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
+- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
+- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
+
+## Product bans (on top of the shared absolute bans)
+
+- Decorative motion that doesn't convey state.
+- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
+- Display fonts in UI labels, buttons, data.
+- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
+- Heavy color or full-saturation accents on inactive states.
+- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
+
+## Product permissions
+
+Product can afford things brand surfaces can't.
+
+- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
+- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
+- Density. Tables with many rows, panels with many labels, dense information when users need it.
+- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
diff --git a/.github/skills/impeccable/reference/product.md b/.github/skills/impeccable/reference/product.md
index 47d6c1373..ccd31d2c1 100644
--- a/.github/skills/impeccable/reference/product.md
+++ b/.github/skills/impeccable/reference/product.md
@@ -1,60 +1,3 @@
-# Product family depth (Operate and Read surfaces)
+# Moved
 
-When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
-
-## The product slop test
-
-Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
-
-Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
-
-## Typography
-
-- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
-- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
-- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
-- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
-
-## Color
-
-Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
-
-- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
-- Accent color used for primary actions, current selection, and state indicators only, not decoration.
-- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
-
-## Layout
-
-- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
-
-## Components
-
-Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
-
-- Skeleton states for loading, not spinners in the middle of content.
-- Empty states that teach the interface, not "nothing here."
-- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
-
-## Motion
-
-- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
-- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
-- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
-
-## Product bans (on top of the shared absolute bans)
-
-- Decorative motion that doesn't convey state.
-- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
-- Display fonts in UI labels, buttons, data.
-- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
-- Heavy color or full-saturation accents on inactive states.
-- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
-
-## Product permissions
-
-Product can afford things brand surfaces can't.
-
-- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
-- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
-- Density. Tables with many rows, panels with many labels, dense information when users need it.
-- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
+Operate and Read depth lives in [operate.md](operate.md). The mode essentials are in SKILL.md. This stub remains because `PRODUCT.md` files with `register: product` and older links point here.
diff --git a/.github/skills/impeccable/reference/typeset.md b/.github/skills/impeccable/reference/typeset.md
index df3ff4984..2b89a7452 100644
--- a/.github/skills/impeccable/reference/typeset.md
+++ b/.github/skills/impeccable/reference/typeset.md
@@ -185,7 +185,7 @@ Use `ch` units for character-based measure (`max-width: 65ch`). Line-height scal
 
 #### Font Selection & Pairing
 
-The tactical selection procedure and the reflex-reject list live in [reference/brand.md](brand.md) under **Font selection procedure** and **Reflex-reject list** (loaded for brand-register tasks). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
+The tactical selection procedure and the reflex-reject list live in [new-work.md](new-work.md) (loaded for new identity work). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
 
 ##### Anti-reflexes worth defending against
 
diff --git a/.github/skills/impeccable/scripts/context.mjs b/.github/skills/impeccable/scripts/context.mjs
index 15829a157..c13990ee0 100644
--- a/.github/skills/impeccable/scripts/context.mjs
+++ b/.github/skills/impeccable/scripts/context.mjs
@@ -940,7 +940,7 @@ async function cli() {
     );
   }
   if (register) {
-    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md; \`reference/${register}.md\` has extended depth for substantial work.`);
+    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md.`);
   }
   const platform = extractPlatform(ctx.product);
   const nativeRefs =
diff --git a/.kiro/skills/impeccable/SKILL.md b/.kiro/skills/impeccable/SKILL.md
index 010c29cf7..a84d3651a 100644
--- a/.kiro/skills/impeccable/SKILL.md
+++ b/.kiro/skills/impeccable/SKILL.md
@@ -36,7 +36,7 @@ Build to this floor without announcing it. The design detector (the project hook
 
 ## Registers
 
-Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode. PRODUCT.md's `register` field names the family (`brand` covers Persuade and Experience; `product` covers Operate and Read), and `reference/brand.md` / `reference/product.md` carry extended depth for the two families.
+Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode; PRODUCT.md's `register` field survives only as a family hint (`brand` covers Persuade and Experience, `product` covers Operate and Read). Depth beyond the paragraphs below: [reference/new-work.md](reference/new-work.md) when inventing identity, [reference/operate.md](reference/operate.md) for substantial Operate and Read work.
 
 **Persuade** (landing pages, marketing, campaigns; design IS the product). The deliverable is an impression that stops the scroll, earns the click, converts. Spans every genre (tech, luxury, consumer); don't collapse them into one look. Briefs that imply imagery must ship real, verified imagery; a colored rectangle where a photo belongs reads as incomplete. New Persuade surfaces take their typeface procedure and reject list from [reference/new-work.md](reference/new-work.md).
 
diff --git a/.kiro/skills/impeccable/reference/brand.md b/.kiro/skills/impeccable/reference/brand.md
index 01af65d27..0f0184c0d 100644
--- a/.kiro/skills/impeccable/reference/brand.md
+++ b/.kiro/skills/impeccable/reference/brand.md
@@ -1,42 +1,3 @@
-# Brand family depth (Persuade and Experience surfaces)
+# Moved
 
-When design IS the product: brand sites, landing pages, campaign pages, portfolios, long-form content, about pages. The essentials live in SKILL.md (modes, craft floor) and, for new identity work, in [new-work.md](new-work.md); this file is extended depth for substantial brand work. Rules stated in those files are not repeated here.
-
-The register spans every genre. A tech brand, a luxury hotel, a restaurant, a band's album page, an agency portfolio. They share a stance (*communicate, not transact*) and diverge wildly in aesthetic. Don't collapse them into one look.
-
-## The aesthetic-lane test
-
-Before committing to moves, name the lane. A type-foundry specimen page is one lane; minimal-cool tech is another; acid-maximalism is another. Don't drift into editorial-magazine aesthetics on a brief that isn't editorial; a hiking brand with italic drop caps has the wrong register within the register.
-
-Then the inverse test: in one sentence, describe what you're about to build the way a competitor would describe theirs. If that sentence fits the modal landing page in the category, restart.
-
-### Reflex-reject aesthetic lanes
-
-Currently saturated aesthetic families that have flooded brand surfaces. If a brief lands in one of these lanes without a register reason that *requires* it (a literal magazine, a literal terminal), it's the second-order training reflex: the trap one tier deeper than a reflex font pick. Look further.
-
-- **Editorial-typographic.** Display serif (often italic) + small mono labels + ruled separators + monochromatic restraint. The fingerprint: three rule-separated columns, an italic serif headline, lowercase track-spaced metadata, no imagery.
-
-(Entries land and leave this list as families saturate and fade.)
-
-The reflex-reject lists apply to **new design choices**. When the existing brand has already committed to a font or a lane as part of its identity, identity-preservation wins.
-
-## Color
-
-- Name a real reference before picking a strategy; unnamed ambition becomes beige.
-- Palette IS voice. A calm brand and a restless brand should not share palette mechanics.
-- Don't converge across projects. Each brand surface differentiates from the last.
-- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
-
-## Layout
-
-- Asymmetric compositions are one option. Break the grid intentionally for emphasis.
-- Fluid spacing with `clamp()` that breathes on larger viewports.
-- For image-led briefs (hotels, restaurants, magazines, photography), full-bleed hero imagery with overlaid menu and centered headline is a canonical move; let the photograph be the design.
-
-## Brand permissions
-
-Brand can afford things product can't. Take them.
-
-- Ambitious first-load motion. Reveals and typographic choreography that earn their place; one orchestrated page-load beats scattered micro-interactions, and some brands skip entrance motion entirely, which is also a voice.
-- Single-purpose viewports. One dominant idea per fold, long scroll, deliberate pacing.
-- Art direction per section. Different sections can have different visual worlds if the narrative demands it. Consistency of voice beats consistency of treatment.
+The Persuade and Experience essentials are in SKILL.md; the depth for inventing new identity (typeface procedure, reject list and lanes, color discipline, layout moves, permissions) lives in [new-work.md](new-work.md). This stub remains because `PRODUCT.md` files with `register: brand` and older links point here.
diff --git a/.kiro/skills/impeccable/reference/live.md b/.kiro/skills/impeccable/reference/live.md
index 00d1812c4..992f7a713 100644
--- a/.kiro/skills/impeccable/reference/live.md
+++ b/.kiro/skills/impeccable/reference/live.md
@@ -109,7 +109,7 @@ node .kiro/skills/impeccable/scripts/live-insert.mjs --id EVENT_ID --count EVENT
 - `--position` ← `event.insert.position` (`before` | `after`)
 - Anchor flags ← `event.insert.anchor` (same mapping as wrap: id, classes, tag, text)
 
-The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. Load `brand.md` or `product.md` (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
+The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. For Operate/Read surfaces load `operate.md`; Persuade/Experience surfaces use SKILL.md's mode guidance plus `new-work.md` when the variant invents identity (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
 
 For Svelte/SvelteKit targets, `live-insert.mjs` returns `previewMode: "svelte-component"` with `mode: "insert"`, `file` pointing at a temporary `node_modules/.impeccable-live/<id>/manifest.json`, `componentDir` pointing at the variant component files, and `sourceFile` pointing at the real `.svelte` route. Write each inserted variant as a real Svelte component (`v1.svelte`, `v2.svelte`, …) under `componentDir`. Insert variants must be non-empty net-new content with a single top-level root, no `data-impeccable-*` attributes, and CSS in each component's `<style>` block. Do **not** edit the route source during generation; the browser mounts the temporary component before/after the live anchor while the user cycles variants. On Accept, `live-accept.mjs` inserts the selected component markup into `sourceFile` immediately and deletes the temp session after the source write succeeds.
 
@@ -187,7 +187,7 @@ All three carry `fallback: "agent-driven"`. Follow **Handle fallback** below.
 
 ### 3. Load the action's reference
 
-If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded register reference (`brand.md` or `product.md`). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
+If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded mode depth (`operate.md` for Operate/Read; `new-work.md` when the variant invents identity). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
 
 Any other `event.action` (`bolder`, `quieter`, `distill`, `polish`, `typeset`, `colorize`, `layout`, `adapt`, `animate`, `delight`, `overdrive`): Read `reference/<action>.md` before planning. Each sub-command encodes a specific discipline; skipping its reference produces generic output. Those files may require specific params; layer them on top of the §7 budget, not instead of it.
 
@@ -252,7 +252,7 @@ Instead, work from the brand:
 
 1. Read PRODUCT.md's Brand Personality words. What physical, spatial, or material experiences would embody those words if design were not involved? (A personality described as "specific, earned, unmistakable" evokes a hand-stamped letter, a numbered print, a watchmaker's loupe. A personality described as "restless, loud, unfiltered" evokes a concert poster, a spray-painted wall, a megaphone.)
 2. From those physical experiences, derive three visual directions that are genuinely different from each other AND from the current surface you're departing.
-3. Avoid the **reflex-reject lanes** in [brand.md](brand.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
+3. Avoid the **reflex-reject lanes** in [new-work.md](new-work.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
 4. Each direction must be expressible in one concrete sentence that names a real-world referent ("a museum exhibition label system for a contemporary art gallery" not "clean and minimal"). If your sentence contains only adjectives, it's not concrete enough.
 5. **While planning each direction, also name its 2–3 parameter knobs** (per the §7 budget table). The same principle as default mode: decide "what's tunable" during planning, not after writing the HTML. A departure-mode hero with 0 parameters is not "bold creative vision," it's a missed opportunity for the user to fine-tune the direction they pick.
 
diff --git a/.kiro/skills/impeccable/reference/new-work.md b/.kiro/skills/impeccable/reference/new-work.md
index 4f45638f3..cd692e486 100644
--- a/.kiro/skills/impeccable/reference/new-work.md
+++ b/.kiro/skills/impeccable/reference/new-work.md
@@ -24,6 +24,10 @@ Plan a compact token system in your reasoning: palette, type, layout concept in
 
 Pick a color strategy before picking colors: Restrained (neutrals + one accent; the default when the visitor came to operate or read) / Committed (one saturated color carries 30-60% of the surface) / Full palette (3-4 named roles) / Drenched (the surface IS the color). Persuade and Experience surfaces have permission for the bolder strategies; take them when the brief allows. Dark vs. light is never a default: write one sentence of physical scene (who uses this, where, under what light, in what mood) and let it force the answer. The warm cream near-white body background is the saturated AI default; where the axis is free, pick a background that is a choice.
 
+- Name a real reference before picking a strategy; unnamed ambition becomes beige.
+- Palette IS voice: a calm brand and a restless brand should not share palette mechanics, and each new surface differentiates from the last.
+- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
+
 ## Type and imagery for new Persuade and Experience surfaces
 
 Choose faces like objects from the brand's world; these training-data defaults mean you stopped looking: Fraunces, Playfair Display, Cormorant, Lora, Crimson, Newsreader, Syne, Space Grotesk, Space Mono, IBM Plex, Inter-as-display, DM Sans, DM Serif, Outfit, Plus Jakarta Sans, Instrument Sans. (For Operate and Read surfaces the opposite holds: system stacks and workhorse UI faces are legitimate and often correct.)
@@ -34,4 +38,10 @@ Imagery-implying briefs (food, travel, place, product, fashion) must ship real,
 
 AI-generated interfaces cluster around a few looks regardless of subject: warm cream + high-contrast serif + terracotta accent; near-black + one neon accent (acid green, cyan) + glowing edges; broadsheet-editorial hairlines + italic display serif + small tracked mono labels. All are legitimate when the brief calls for them; the brief always wins. Where the brief leaves the aesthetic free, landing in one of them means your self-check failed. Same one tier deeper: if someone could guess your aesthetic from the category alone, or from category-plus-avoidance, rework until neither answer is obvious.
 
+**Name the aesthetic lane, then test it.** Before committing to moves, say which lane this is (a specimen page, minimal-cool tech, acid maximalism...). Then the inverse test: describe what you're about to build the way a competitor would describe theirs; if that sentence fits the modal page in the category, restart. Currently saturated lanes count as reflexes, not choices, when the brief doesn't require them; the flooded one right now is editorial-typographic (display serif, often italic, small mono labels, ruled separators, monochromatic restraint, no imagery).
+
+## Persuade and Experience moves
+
+Layout: asymmetric compositions and intentional grid breaks are on the table; fluid spacing with `clamp()` that breathes on larger viewports; for image-led briefs, full-bleed hero imagery with overlaid navigation is a canonical move, letting the photograph be the design. Permissions the Operate world doesn't get: ambitious first-load motion (one orchestrated page-load beats scattered micro-interactions; skipping entrance motion entirely is also a voice), single-purpose viewports (one dominant idea per fold, deliberate pacing), and art direction per section when the narrative demands it; consistency of voice beats consistency of treatment.
+
 Before finishing, verify against SKILL.md's craft floor and run the detector; a bold page that ships mechanical defects is not done.
diff --git a/.kiro/skills/impeccable/reference/operate.md b/.kiro/skills/impeccable/reference/operate.md
new file mode 100644
index 000000000..04ee9d7d2
--- /dev/null
+++ b/.kiro/skills/impeccable/reference/operate.md
@@ -0,0 +1,60 @@
+# Operate mode depth (and Read notes)
+
+When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
+
+## The product slop test
+
+Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
+
+Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
+
+## Typography
+
+- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
+- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
+- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
+- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
+
+## Color
+
+Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
+
+- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
+- Accent color used for primary actions, current selection, and state indicators only, not decoration.
+- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
+
+## Layout
+
+- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
+
+## Components
+
+Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
+
+- Skeleton states for loading, not spinners in the middle of content.
+- Empty states that teach the interface, not "nothing here."
+- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
+
+## Motion
+
+- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
+- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
+- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
+
+## Product bans (on top of the shared absolute bans)
+
+- Decorative motion that doesn't convey state.
+- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
+- Display fonts in UI labels, buttons, data.
+- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
+- Heavy color or full-saturation accents on inactive states.
+- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
+
+## Product permissions
+
+Product can afford things brand surfaces can't.
+
+- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
+- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
+- Density. Tables with many rows, panels with many labels, dense information when users need it.
+- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
diff --git a/.kiro/skills/impeccable/reference/product.md b/.kiro/skills/impeccable/reference/product.md
index 47d6c1373..ccd31d2c1 100644
--- a/.kiro/skills/impeccable/reference/product.md
+++ b/.kiro/skills/impeccable/reference/product.md
@@ -1,60 +1,3 @@
-# Product family depth (Operate and Read surfaces)
+# Moved
 
-When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
-
-## The product slop test
-
-Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
-
-Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
-
-## Typography
-
-- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
-- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
-- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
-- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
-
-## Color
-
-Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
-
-- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
-- Accent color used for primary actions, current selection, and state indicators only, not decoration.
-- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
-
-## Layout
-
-- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
-
-## Components
-
-Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
-
-- Skeleton states for loading, not spinners in the middle of content.
-- Empty states that teach the interface, not "nothing here."
-- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
-
-## Motion
-
-- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
-- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
-- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
-
-## Product bans (on top of the shared absolute bans)
-
-- Decorative motion that doesn't convey state.
-- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
-- Display fonts in UI labels, buttons, data.
-- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
-- Heavy color or full-saturation accents on inactive states.
-- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
-
-## Product permissions
-
-Product can afford things brand surfaces can't.
-
-- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
-- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
-- Density. Tables with many rows, panels with many labels, dense information when users need it.
-- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
+Operate and Read depth lives in [operate.md](operate.md). The mode essentials are in SKILL.md. This stub remains because `PRODUCT.md` files with `register: product` and older links point here.
diff --git a/.kiro/skills/impeccable/reference/typeset.md b/.kiro/skills/impeccable/reference/typeset.md
index 01fe68bc8..30d075fab 100644
--- a/.kiro/skills/impeccable/reference/typeset.md
+++ b/.kiro/skills/impeccable/reference/typeset.md
@@ -185,7 +185,7 @@ Use `ch` units for character-based measure (`max-width: 65ch`). Line-height scal
 
 #### Font Selection & Pairing
 
-The tactical selection procedure and the reflex-reject list live in [reference/brand.md](brand.md) under **Font selection procedure** and **Reflex-reject list** (loaded for brand-register tasks). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
+The tactical selection procedure and the reflex-reject list live in [new-work.md](new-work.md) (loaded for new identity work). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
 
 ##### Anti-reflexes worth defending against
 
diff --git a/.kiro/skills/impeccable/scripts/context.mjs b/.kiro/skills/impeccable/scripts/context.mjs
index 15829a157..c13990ee0 100644
--- a/.kiro/skills/impeccable/scripts/context.mjs
+++ b/.kiro/skills/impeccable/scripts/context.mjs
@@ -940,7 +940,7 @@ async function cli() {
     );
   }
   if (register) {
-    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md; \`reference/${register}.md\` has extended depth for substantial work.`);
+    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md.`);
   }
   const platform = extractPlatform(ctx.product);
   const nativeRefs =
diff --git a/.opencode/skills/impeccable/SKILL.md b/.opencode/skills/impeccable/SKILL.md
index a4548ed8e..eebc50104 100644
--- a/.opencode/skills/impeccable/SKILL.md
+++ b/.opencode/skills/impeccable/SKILL.md
@@ -41,7 +41,7 @@ Build to this floor without announcing it. The design detector (the project hook
 
 ## Registers
 
-Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode. PRODUCT.md's `register` field names the family (`brand` covers Persuade and Experience; `product` covers Operate and Read), and `reference/brand.md` / `reference/product.md` carry extended depth for the two families.
+Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode; PRODUCT.md's `register` field survives only as a family hint (`brand` covers Persuade and Experience, `product` covers Operate and Read). Depth beyond the paragraphs below: [reference/new-work.md](reference/new-work.md) when inventing identity, [reference/operate.md](reference/operate.md) for substantial Operate and Read work.
 
 **Persuade** (landing pages, marketing, campaigns; design IS the product). The deliverable is an impression that stops the scroll, earns the click, converts. Spans every genre (tech, luxury, consumer); don't collapse them into one look. Briefs that imply imagery must ship real, verified imagery; a colored rectangle where a photo belongs reads as incomplete. New Persuade surfaces take their typeface procedure and reject list from [reference/new-work.md](reference/new-work.md).
 
diff --git a/.opencode/skills/impeccable/reference/brand.md b/.opencode/skills/impeccable/reference/brand.md
index 01af65d27..0f0184c0d 100644
--- a/.opencode/skills/impeccable/reference/brand.md
+++ b/.opencode/skills/impeccable/reference/brand.md
@@ -1,42 +1,3 @@
-# Brand family depth (Persuade and Experience surfaces)
+# Moved
 
-When design IS the product: brand sites, landing pages, campaign pages, portfolios, long-form content, about pages. The essentials live in SKILL.md (modes, craft floor) and, for new identity work, in [new-work.md](new-work.md); this file is extended depth for substantial brand work. Rules stated in those files are not repeated here.
-
-The register spans every genre. A tech brand, a luxury hotel, a restaurant, a band's album page, an agency portfolio. They share a stance (*communicate, not transact*) and diverge wildly in aesthetic. Don't collapse them into one look.
-
-## The aesthetic-lane test
-
-Before committing to moves, name the lane. A type-foundry specimen page is one lane; minimal-cool tech is another; acid-maximalism is another. Don't drift into editorial-magazine aesthetics on a brief that isn't editorial; a hiking brand with italic drop caps has the wrong register within the register.
-
-Then the inverse test: in one sentence, describe what you're about to build the way a competitor would describe theirs. If that sentence fits the modal landing page in the category, restart.
-
-### Reflex-reject aesthetic lanes
-
-Currently saturated aesthetic families that have flooded brand surfaces. If a brief lands in one of these lanes without a register reason that *requires* it (a literal magazine, a literal terminal), it's the second-order training reflex: the trap one tier deeper than a reflex font pick. Look further.
-
-- **Editorial-typographic.** Display serif (often italic) + small mono labels + ruled separators + monochromatic restraint. The fingerprint: three rule-separated columns, an italic serif headline, lowercase track-spaced metadata, no imagery.
-
-(Entries land and leave this list as families saturate and fade.)
-
-The reflex-reject lists apply to **new design choices**. When the existing brand has already committed to a font or a lane as part of its identity, identity-preservation wins.
-
-## Color
-
-- Name a real reference before picking a strategy; unnamed ambition becomes beige.
-- Palette IS voice. A calm brand and a restless brand should not share palette mechanics.
-- Don't converge across projects. Each brand surface differentiates from the last.
-- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
-
-## Layout
-
-- Asymmetric compositions are one option. Break the grid intentionally for emphasis.
-- Fluid spacing with `clamp()` that breathes on larger viewports.
-- For image-led briefs (hotels, restaurants, magazines, photography), full-bleed hero imagery with overlaid menu and centered headline is a canonical move; let the photograph be the design.
-
-## Brand permissions
-
-Brand can afford things product can't. Take them.
-
-- Ambitious first-load motion. Reveals and typographic choreography that earn their place; one orchestrated page-load beats scattered micro-interactions, and some brands skip entrance motion entirely, which is also a voice.
-- Single-purpose viewports. One dominant idea per fold, long scroll, deliberate pacing.
-- Art direction per section. Different sections can have different visual worlds if the narrative demands it. Consistency of voice beats consistency of treatment.
+The Persuade and Experience essentials are in SKILL.md; the depth for inventing new identity (typeface procedure, reject list and lanes, color discipline, layout moves, permissions) lives in [new-work.md](new-work.md). This stub remains because `PRODUCT.md` files with `register: brand` and older links point here.
diff --git a/.opencode/skills/impeccable/reference/live.md b/.opencode/skills/impeccable/reference/live.md
index bf49a7c40..e10c27451 100644
--- a/.opencode/skills/impeccable/reference/live.md
+++ b/.opencode/skills/impeccable/reference/live.md
@@ -109,7 +109,7 @@ node .opencode/skills/impeccable/scripts/live-insert.mjs --id EVENT_ID --count E
 - `--position` ← `event.insert.position` (`before` | `after`)
 - Anchor flags ← `event.insert.anchor` (same mapping as wrap: id, classes, tag, text)
 
-The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. Load `brand.md` or `product.md` (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
+The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. For Operate/Read surfaces load `operate.md`; Persuade/Experience surfaces use SKILL.md's mode guidance plus `new-work.md` when the variant invents identity (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
 
 For Svelte/SvelteKit targets, `live-insert.mjs` returns `previewMode: "svelte-component"` with `mode: "insert"`, `file` pointing at a temporary `node_modules/.impeccable-live/<id>/manifest.json`, `componentDir` pointing at the variant component files, and `sourceFile` pointing at the real `.svelte` route. Write each inserted variant as a real Svelte component (`v1.svelte`, `v2.svelte`, …) under `componentDir`. Insert variants must be non-empty net-new content with a single top-level root, no `data-impeccable-*` attributes, and CSS in each component's `<style>` block. Do **not** edit the route source during generation; the browser mounts the temporary component before/after the live anchor while the user cycles variants. On Accept, `live-accept.mjs` inserts the selected component markup into `sourceFile` immediately and deletes the temp session after the source write succeeds.
 
@@ -187,7 +187,7 @@ All three carry `fallback: "agent-driven"`. Follow **Handle fallback** below.
 
 ### 3. Load the action's reference
 
-If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded register reference (`brand.md` or `product.md`). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
+If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded mode depth (`operate.md` for Operate/Read; `new-work.md` when the variant invents identity). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
 
 Any other `event.action` (`bolder`, `quieter`, `distill`, `polish`, `typeset`, `colorize`, `layout`, `adapt`, `animate`, `delight`, `overdrive`): Read `reference/<action>.md` before planning. Each sub-command encodes a specific discipline; skipping its reference produces generic output. Those files may require specific params; layer them on top of the §7 budget, not instead of it.
 
@@ -252,7 +252,7 @@ Instead, work from the brand:
 
 1. Read PRODUCT.md's Brand Personality words. What physical, spatial, or material experiences would embody those words if design were not involved? (A personality described as "specific, earned, unmistakable" evokes a hand-stamped letter, a numbered print, a watchmaker's loupe. A personality described as "restless, loud, unfiltered" evokes a concert poster, a spray-painted wall, a megaphone.)
 2. From those physical experiences, derive three visual directions that are genuinely different from each other AND from the current surface you're departing.
-3. Avoid the **reflex-reject lanes** in [brand.md](brand.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
+3. Avoid the **reflex-reject lanes** in [new-work.md](new-work.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
 4. Each direction must be expressible in one concrete sentence that names a real-world referent ("a museum exhibition label system for a contemporary art gallery" not "clean and minimal"). If your sentence contains only adjectives, it's not concrete enough.
 5. **While planning each direction, also name its 2–3 parameter knobs** (per the §7 budget table). The same principle as default mode: decide "what's tunable" during planning, not after writing the HTML. A departure-mode hero with 0 parameters is not "bold creative vision," it's a missed opportunity for the user to fine-tune the direction they pick.
 
diff --git a/.opencode/skills/impeccable/reference/new-work.md b/.opencode/skills/impeccable/reference/new-work.md
index 0c1f2bfb0..332aeb1c1 100644
--- a/.opencode/skills/impeccable/reference/new-work.md
+++ b/.opencode/skills/impeccable/reference/new-work.md
@@ -24,6 +24,10 @@ Plan a compact token system in your reasoning: palette, type, layout concept in
 
 Pick a color strategy before picking colors: Restrained (neutrals + one accent; the default when the visitor came to operate or read) / Committed (one saturated color carries 30-60% of the surface) / Full palette (3-4 named roles) / Drenched (the surface IS the color). Persuade and Experience surfaces have permission for the bolder strategies; take them when the brief allows. Dark vs. light is never a default: write one sentence of physical scene (who uses this, where, under what light, in what mood) and let it force the answer. The warm cream near-white body background is the saturated AI default; where the axis is free, pick a background that is a choice.
 
+- Name a real reference before picking a strategy; unnamed ambition becomes beige.
+- Palette IS voice: a calm brand and a restless brand should not share palette mechanics, and each new surface differentiates from the last.
+- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
+
 ## Type and imagery for new Persuade and Experience surfaces
 
 Choose faces like objects from the brand's world; these training-data defaults mean you stopped looking: Fraunces, Playfair Display, Cormorant, Lora, Crimson, Newsreader, Syne, Space Grotesk, Space Mono, IBM Plex, Inter-as-display, DM Sans, DM Serif, Outfit, Plus Jakarta Sans, Instrument Sans. (For Operate and Read surfaces the opposite holds: system stacks and workhorse UI faces are legitimate and often correct.)
@@ -34,4 +38,10 @@ Imagery-implying briefs (food, travel, place, product, fashion) must ship real,
 
 AI-generated interfaces cluster around a few looks regardless of subject: warm cream + high-contrast serif + terracotta accent; near-black + one neon accent (acid green, cyan) + glowing edges; broadsheet-editorial hairlines + italic display serif + small tracked mono labels. All are legitimate when the brief calls for them; the brief always wins. Where the brief leaves the aesthetic free, landing in one of them means your self-check failed. Same one tier deeper: if someone could guess your aesthetic from the category alone, or from category-plus-avoidance, rework until neither answer is obvious.
 
+**Name the aesthetic lane, then test it.** Before committing to moves, say which lane this is (a specimen page, minimal-cool tech, acid maximalism...). Then the inverse test: describe what you're about to build the way a competitor would describe theirs; if that sentence fits the modal page in the category, restart. Currently saturated lanes count as reflexes, not choices, when the brief doesn't require them; the flooded one right now is editorial-typographic (display serif, often italic, small mono labels, ruled separators, monochromatic restraint, no imagery).
+
+## Persuade and Experience moves
+
+Layout: asymmetric compositions and intentional grid breaks are on the table; fluid spacing with `clamp()` that breathes on larger viewports; for image-led briefs, full-bleed hero imagery with overlaid navigation is a canonical move, letting the photograph be the design. Permissions the Operate world doesn't get: ambitious first-load motion (one orchestrated page-load beats scattered micro-interactions; skipping entrance motion entirely is also a voice), single-purpose viewports (one dominant idea per fold, deliberate pacing), and art direction per section when the narrative demands it; consistency of voice beats consistency of treatment.
+
 Before finishing, verify against SKILL.md's craft floor and run the detector; a bold page that ships mechanical defects is not done.
diff --git a/.opencode/skills/impeccable/reference/operate.md b/.opencode/skills/impeccable/reference/operate.md
new file mode 100644
index 000000000..04ee9d7d2
--- /dev/null
+++ b/.opencode/skills/impeccable/reference/operate.md
@@ -0,0 +1,60 @@
+# Operate mode depth (and Read notes)
+
+When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
+
+## The product slop test
+
+Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
+
+Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
+
+## Typography
+
+- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
+- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
+- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
+- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
+
+## Color
+
+Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
+
+- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
+- Accent color used for primary actions, current selection, and state indicators only, not decoration.
+- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
+
+## Layout
+
+- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
+
+## Components
+
+Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
+
+- Skeleton states for loading, not spinners in the middle of content.
+- Empty states that teach the interface, not "nothing here."
+- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
+
+## Motion
+
+- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
+- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
+- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
+
+## Product bans (on top of the shared absolute bans)
+
+- Decorative motion that doesn't convey state.
+- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
+- Display fonts in UI labels, buttons, data.
+- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
+- Heavy color or full-saturation accents on inactive states.
+- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
+
+## Product permissions
+
+Product can afford things brand surfaces can't.
+
+- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
+- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
+- Density. Tables with many rows, panels with many labels, dense information when users need it.
+- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
diff --git a/.opencode/skills/impeccable/reference/product.md b/.opencode/skills/impeccable/reference/product.md
index 47d6c1373..ccd31d2c1 100644
--- a/.opencode/skills/impeccable/reference/product.md
+++ b/.opencode/skills/impeccable/reference/product.md
@@ -1,60 +1,3 @@
-# Product family depth (Operate and Read surfaces)
+# Moved
 
-When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
-
-## The product slop test
-
-Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
-
-Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
-
-## Typography
-
-- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
-- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
-- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
-- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
-
-## Color
-
-Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
-
-- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
-- Accent color used for primary actions, current selection, and state indicators only, not decoration.
-- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
-
-## Layout
-
-- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
-
-## Components
-
-Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
-
-- Skeleton states for loading, not spinners in the middle of content.
-- Empty states that teach the interface, not "nothing here."
-- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
-
-## Motion
-
-- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
-- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
-- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
-
-## Product bans (on top of the shared absolute bans)
-
-- Decorative motion that doesn't convey state.
-- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
-- Display fonts in UI labels, buttons, data.
-- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
-- Heavy color or full-saturation accents on inactive states.
-- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
-
-## Product permissions
-
-Product can afford things brand surfaces can't.
-
-- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
-- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
-- Density. Tables with many rows, panels with many labels, dense information when users need it.
-- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
+Operate and Read depth lives in [operate.md](operate.md). The mode essentials are in SKILL.md. This stub remains because `PRODUCT.md` files with `register: product` and older links point here.
diff --git a/.opencode/skills/impeccable/reference/typeset.md b/.opencode/skills/impeccable/reference/typeset.md
index e892f8ba5..877f67801 100644
--- a/.opencode/skills/impeccable/reference/typeset.md
+++ b/.opencode/skills/impeccable/reference/typeset.md
@@ -185,7 +185,7 @@ Use `ch` units for character-based measure (`max-width: 65ch`). Line-height scal
 
 #### Font Selection & Pairing
 
-The tactical selection procedure and the reflex-reject list live in [reference/brand.md](brand.md) under **Font selection procedure** and **Reflex-reject list** (loaded for brand-register tasks). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
+The tactical selection procedure and the reflex-reject list live in [new-work.md](new-work.md) (loaded for new identity work). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
 
 ##### Anti-reflexes worth defending against
 
diff --git a/.opencode/skills/impeccable/scripts/context.mjs b/.opencode/skills/impeccable/scripts/context.mjs
index 15829a157..c13990ee0 100644
--- a/.opencode/skills/impeccable/scripts/context.mjs
+++ b/.opencode/skills/impeccable/scripts/context.mjs
@@ -940,7 +940,7 @@ async function cli() {
     );
   }
   if (register) {
-    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md; \`reference/${register}.md\` has extended depth for substantial work.`);
+    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md.`);
   }
   const platform = extractPlatform(ctx.product);
   const nativeRefs =
diff --git a/.pi/skills/impeccable/SKILL.md b/.pi/skills/impeccable/SKILL.md
index ac43d5ddb..f72154dfc 100644
--- a/.pi/skills/impeccable/SKILL.md
+++ b/.pi/skills/impeccable/SKILL.md
@@ -39,7 +39,7 @@ Build to this floor without announcing it. The design detector (the project hook
 
 ## Registers
 
-Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode. PRODUCT.md's `register` field names the family (`brand` covers Persuade and Experience; `product` covers Operate and Read), and `reference/brand.md` / `reference/product.md` carry extended depth for the two families.
+Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode; PRODUCT.md's `register` field survives only as a family hint (`brand` covers Persuade and Experience, `product` covers Operate and Read). Depth beyond the paragraphs below: [reference/new-work.md](reference/new-work.md) when inventing identity, [reference/operate.md](reference/operate.md) for substantial Operate and Read work.
 
 **Persuade** (landing pages, marketing, campaigns; design IS the product). The deliverable is an impression that stops the scroll, earns the click, converts. Spans every genre (tech, luxury, consumer); don't collapse them into one look. Briefs that imply imagery must ship real, verified imagery; a colored rectangle where a photo belongs reads as incomplete. New Persuade surfaces take their typeface procedure and reject list from [reference/new-work.md](reference/new-work.md).
 
diff --git a/.pi/skills/impeccable/reference/brand.md b/.pi/skills/impeccable/reference/brand.md
index 01af65d27..0f0184c0d 100644
--- a/.pi/skills/impeccable/reference/brand.md
+++ b/.pi/skills/impeccable/reference/brand.md
@@ -1,42 +1,3 @@
-# Brand family depth (Persuade and Experience surfaces)
+# Moved
 
-When design IS the product: brand sites, landing pages, campaign pages, portfolios, long-form content, about pages. The essentials live in SKILL.md (modes, craft floor) and, for new identity work, in [new-work.md](new-work.md); this file is extended depth for substantial brand work. Rules stated in those files are not repeated here.
-
-The register spans every genre. A tech brand, a luxury hotel, a restaurant, a band's album page, an agency portfolio. They share a stance (*communicate, not transact*) and diverge wildly in aesthetic. Don't collapse them into one look.
-
-## The aesthetic-lane test
-
-Before committing to moves, name the lane. A type-foundry specimen page is one lane; minimal-cool tech is another; acid-maximalism is another. Don't drift into editorial-magazine aesthetics on a brief that isn't editorial; a hiking brand with italic drop caps has the wrong register within the register.
-
-Then the inverse test: in one sentence, describe what you're about to build the way a competitor would describe theirs. If that sentence fits the modal landing page in the category, restart.
-
-### Reflex-reject aesthetic lanes
-
-Currently saturated aesthetic families that have flooded brand surfaces. If a brief lands in one of these lanes without a register reason that *requires* it (a literal magazine, a literal terminal), it's the second-order training reflex: the trap one tier deeper than a reflex font pick. Look further.
-
-- **Editorial-typographic.** Display serif (often italic) + small mono labels + ruled separators + monochromatic restraint. The fingerprint: three rule-separated columns, an italic serif headline, lowercase track-spaced metadata, no imagery.
-
-(Entries land and leave this list as families saturate and fade.)
-
-The reflex-reject lists apply to **new design choices**. When the existing brand has already committed to a font or a lane as part of its identity, identity-preservation wins.
-
-## Color
-
-- Name a real reference before picking a strategy; unnamed ambition becomes beige.
-- Palette IS voice. A calm brand and a restless brand should not share palette mechanics.
-- Don't converge across projects. Each brand surface differentiates from the last.
-- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
-
-## Layout
-
-- Asymmetric compositions are one option. Break the grid intentionally for emphasis.
-- Fluid spacing with `clamp()` that breathes on larger viewports.
-- For image-led briefs (hotels, restaurants, magazines, photography), full-bleed hero imagery with overlaid menu and centered headline is a canonical move; let the photograph be the design.
-
-## Brand permissions
-
-Brand can afford things product can't. Take them.
-
-- Ambitious first-load motion. Reveals and typographic choreography that earn their place; one orchestrated page-load beats scattered micro-interactions, and some brands skip entrance motion entirely, which is also a voice.
-- Single-purpose viewports. One dominant idea per fold, long scroll, deliberate pacing.
-- Art direction per section. Different sections can have different visual worlds if the narrative demands it. Consistency of voice beats consistency of treatment.
+The Persuade and Experience essentials are in SKILL.md; the depth for inventing new identity (typeface procedure, reject list and lanes, color discipline, layout moves, permissions) lives in [new-work.md](new-work.md). This stub remains because `PRODUCT.md` files with `register: brand` and older links point here.
diff --git a/.pi/skills/impeccable/reference/live.md b/.pi/skills/impeccable/reference/live.md
index e8e3e1921..1e00744e0 100644
--- a/.pi/skills/impeccable/reference/live.md
+++ b/.pi/skills/impeccable/reference/live.md
@@ -109,7 +109,7 @@ node .pi/skills/impeccable/scripts/live-insert.mjs --id EVENT_ID --count EVENT_C
 - `--position` ← `event.insert.position` (`before` | `after`)
 - Anchor flags ← `event.insert.anchor` (same mapping as wrap: id, classes, tag, text)
 
-The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. Load `brand.md` or `product.md` (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
+The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. For Operate/Read surfaces load `operate.md`; Persuade/Experience surfaces use SKILL.md's mode guidance plus `new-work.md` when the variant invents identity (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
 
 For Svelte/SvelteKit targets, `live-insert.mjs` returns `previewMode: "svelte-component"` with `mode: "insert"`, `file` pointing at a temporary `node_modules/.impeccable-live/<id>/manifest.json`, `componentDir` pointing at the variant component files, and `sourceFile` pointing at the real `.svelte` route. Write each inserted variant as a real Svelte component (`v1.svelte`, `v2.svelte`, …) under `componentDir`. Insert variants must be non-empty net-new content with a single top-level root, no `data-impeccable-*` attributes, and CSS in each component's `<style>` block. Do **not** edit the route source during generation; the browser mounts the temporary component before/after the live anchor while the user cycles variants. On Accept, `live-accept.mjs` inserts the selected component markup into `sourceFile` immediately and deletes the temp session after the source write succeeds.
 
@@ -187,7 +187,7 @@ All three carry `fallback: "agent-driven"`. Follow **Handle fallback** below.
 
 ### 3. Load the action's reference
 
-If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded register reference (`brand.md` or `product.md`). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
+If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded mode depth (`operate.md` for Operate/Read; `new-work.md` when the variant invents identity). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
 
 Any other `event.action` (`bolder`, `quieter`, `distill`, `polish`, `typeset`, `colorize`, `layout`, `adapt`, `animate`, `delight`, `overdrive`): Read `reference/<action>.md` before planning. Each sub-command encodes a specific discipline; skipping its reference produces generic output. Those files may require specific params; layer them on top of the §7 budget, not instead of it.
 
@@ -252,7 +252,7 @@ Instead, work from the brand:
 
 1. Read PRODUCT.md's Brand Personality words. What physical, spatial, or material experiences would embody those words if design were not involved? (A personality described as "specific, earned, unmistakable" evokes a hand-stamped letter, a numbered print, a watchmaker's loupe. A personality described as "restless, loud, unfiltered" evokes a concert poster, a spray-painted wall, a megaphone.)
 2. From those physical experiences, derive three visual directions that are genuinely different from each other AND from the current surface you're departing.
-3. Avoid the **reflex-reject lanes** in [brand.md](brand.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
+3. Avoid the **reflex-reject lanes** in [new-work.md](new-work.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
 4. Each direction must be expressible in one concrete sentence that names a real-world referent ("a museum exhibition label system for a contemporary art gallery" not "clean and minimal"). If your sentence contains only adjectives, it's not concrete enough.
 5. **While planning each direction, also name its 2–3 parameter knobs** (per the §7 budget table). The same principle as default mode: decide "what's tunable" during planning, not after writing the HTML. A departure-mode hero with 0 parameters is not "bold creative vision," it's a missed opportunity for the user to fine-tune the direction they pick.
 
diff --git a/.pi/skills/impeccable/reference/new-work.md b/.pi/skills/impeccable/reference/new-work.md
index 765b149c5..0babbacfe 100644
--- a/.pi/skills/impeccable/reference/new-work.md
+++ b/.pi/skills/impeccable/reference/new-work.md
@@ -24,6 +24,10 @@ Plan a compact token system in your reasoning: palette, type, layout concept in
 
 Pick a color strategy before picking colors: Restrained (neutrals + one accent; the default when the visitor came to operate or read) / Committed (one saturated color carries 30-60% of the surface) / Full palette (3-4 named roles) / Drenched (the surface IS the color). Persuade and Experience surfaces have permission for the bolder strategies; take them when the brief allows. Dark vs. light is never a default: write one sentence of physical scene (who uses this, where, under what light, in what mood) and let it force the answer. The warm cream near-white body background is the saturated AI default; where the axis is free, pick a background that is a choice.
 
+- Name a real reference before picking a strategy; unnamed ambition becomes beige.
+- Palette IS voice: a calm brand and a restless brand should not share palette mechanics, and each new surface differentiates from the last.
+- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
+
 ## Type and imagery for new Persuade and Experience surfaces
 
 Choose faces like objects from the brand's world; these training-data defaults mean you stopped looking: Fraunces, Playfair Display, Cormorant, Lora, Crimson, Newsreader, Syne, Space Grotesk, Space Mono, IBM Plex, Inter-as-display, DM Sans, DM Serif, Outfit, Plus Jakarta Sans, Instrument Sans. (For Operate and Read surfaces the opposite holds: system stacks and workhorse UI faces are legitimate and often correct.)
@@ -34,4 +38,10 @@ Imagery-implying briefs (food, travel, place, product, fashion) must ship real,
 
 AI-generated interfaces cluster around a few looks regardless of subject: warm cream + high-contrast serif + terracotta accent; near-black + one neon accent (acid green, cyan) + glowing edges; broadsheet-editorial hairlines + italic display serif + small tracked mono labels. All are legitimate when the brief calls for them; the brief always wins. Where the brief leaves the aesthetic free, landing in one of them means your self-check failed. Same one tier deeper: if someone could guess your aesthetic from the category alone, or from category-plus-avoidance, rework until neither answer is obvious.
 
+**Name the aesthetic lane, then test it.** Before committing to moves, say which lane this is (a specimen page, minimal-cool tech, acid maximalism...). Then the inverse test: describe what you're about to build the way a competitor would describe theirs; if that sentence fits the modal page in the category, restart. Currently saturated lanes count as reflexes, not choices, when the brief doesn't require them; the flooded one right now is editorial-typographic (display serif, often italic, small mono labels, ruled separators, monochromatic restraint, no imagery).
+
+## Persuade and Experience moves
+
+Layout: asymmetric compositions and intentional grid breaks are on the table; fluid spacing with `clamp()` that breathes on larger viewports; for image-led briefs, full-bleed hero imagery with overlaid navigation is a canonical move, letting the photograph be the design. Permissions the Operate world doesn't get: ambitious first-load motion (one orchestrated page-load beats scattered micro-interactions; skipping entrance motion entirely is also a voice), single-purpose viewports (one dominant idea per fold, deliberate pacing), and art direction per section when the narrative demands it; consistency of voice beats consistency of treatment.
+
 Before finishing, verify against SKILL.md's craft floor and run the detector; a bold page that ships mechanical defects is not done.
diff --git a/.pi/skills/impeccable/reference/operate.md b/.pi/skills/impeccable/reference/operate.md
new file mode 100644
index 000000000..04ee9d7d2
--- /dev/null
+++ b/.pi/skills/impeccable/reference/operate.md
@@ -0,0 +1,60 @@
+# Operate mode depth (and Read notes)
+
+When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
+
+## The product slop test
+
+Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
+
+Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
+
+## Typography
+
+- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
+- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
+- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
+- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
+
+## Color
+
+Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
+
+- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
+- Accent color used for primary actions, current selection, and state indicators only, not decoration.
+- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
+
+## Layout
+
+- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
+
+## Components
+
+Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
+
+- Skeleton states for loading, not spinners in the middle of content.
+- Empty states that teach the interface, not "nothing here."
+- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
+
+## Motion
+
+- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
+- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
+- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
+
+## Product bans (on top of the shared absolute bans)
+
+- Decorative motion that doesn't convey state.
+- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
+- Display fonts in UI labels, buttons, data.
+- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
+- Heavy color or full-saturation accents on inactive states.
+- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
+
+## Product permissions
+
+Product can afford things brand surfaces can't.
+
+- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
+- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
+- Density. Tables with many rows, panels with many labels, dense information when users need it.
+- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
diff --git a/.pi/skills/impeccable/reference/product.md b/.pi/skills/impeccable/reference/product.md
index 47d6c1373..ccd31d2c1 100644
--- a/.pi/skills/impeccable/reference/product.md
+++ b/.pi/skills/impeccable/reference/product.md
@@ -1,60 +1,3 @@
-# Product family depth (Operate and Read surfaces)
+# Moved
 
-When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
-
-## The product slop test
-
-Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
-
-Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
-
-## Typography
-
-- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
-- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
-- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
-- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
-
-## Color
-
-Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
-
-- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
-- Accent color used for primary actions, current selection, and state indicators only, not decoration.
-- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
-
-## Layout
-
-- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
-
-## Components
-
-Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
-
-- Skeleton states for loading, not spinners in the middle of content.
-- Empty states that teach the interface, not "nothing here."
-- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
-
-## Motion
-
-- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
-- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
-- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
-
-## Product bans (on top of the shared absolute bans)
-
-- Decorative motion that doesn't convey state.
-- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
-- Display fonts in UI labels, buttons, data.
-- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
-- Heavy color or full-saturation accents on inactive states.
-- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
-
-## Product permissions
-
-Product can afford things brand surfaces can't.
-
-- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
-- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
-- Density. Tables with many rows, panels with many labels, dense information when users need it.
-- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
+Operate and Read depth lives in [operate.md](operate.md). The mode essentials are in SKILL.md. This stub remains because `PRODUCT.md` files with `register: product` and older links point here.
diff --git a/.pi/skills/impeccable/reference/typeset.md b/.pi/skills/impeccable/reference/typeset.md
index e3eed82a2..f1513f83e 100644
--- a/.pi/skills/impeccable/reference/typeset.md
+++ b/.pi/skills/impeccable/reference/typeset.md
@@ -185,7 +185,7 @@ Use `ch` units for character-based measure (`max-width: 65ch`). Line-height scal
 
 #### Font Selection & Pairing
 
-The tactical selection procedure and the reflex-reject list live in [reference/brand.md](brand.md) under **Font selection procedure** and **Reflex-reject list** (loaded for brand-register tasks). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
+The tactical selection procedure and the reflex-reject list live in [new-work.md](new-work.md) (loaded for new identity work). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
 
 ##### Anti-reflexes worth defending against
 
diff --git a/.pi/skills/impeccable/scripts/context.mjs b/.pi/skills/impeccable/scripts/context.mjs
index 15829a157..c13990ee0 100644
--- a/.pi/skills/impeccable/scripts/context.mjs
+++ b/.pi/skills/impeccable/scripts/context.mjs
@@ -940,7 +940,7 @@ async function cli() {
     );
   }
   if (register) {
-    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md; \`reference/${register}.md\` has extended depth for substantial work.`);
+    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md.`);
   }
   const platform = extractPlatform(ctx.product);
   const nativeRefs =
diff --git a/.qoder/skills/impeccable/SKILL.md b/.qoder/skills/impeccable/SKILL.md
index a589b9dc2..7c3827686 100644
--- a/.qoder/skills/impeccable/SKILL.md
+++ b/.qoder/skills/impeccable/SKILL.md
@@ -41,7 +41,7 @@ Build to this floor without announcing it. The design detector (the project hook
 
 ## Registers
 
-Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode. PRODUCT.md's `register` field names the family (`brand` covers Persuade and Experience; `product` covers Operate and Read), and `reference/brand.md` / `reference/product.md` carry extended depth for the two families.
+Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode; PRODUCT.md's `register` field survives only as a family hint (`brand` covers Persuade and Experience, `product` covers Operate and Read). Depth beyond the paragraphs below: [reference/new-work.md](reference/new-work.md) when inventing identity, [reference/operate.md](reference/operate.md) for substantial Operate and Read work.
 
 **Persuade** (landing pages, marketing, campaigns; design IS the product). The deliverable is an impression that stops the scroll, earns the click, converts. Spans every genre (tech, luxury, consumer); don't collapse them into one look. Briefs that imply imagery must ship real, verified imagery; a colored rectangle where a photo belongs reads as incomplete. New Persuade surfaces take their typeface procedure and reject list from [reference/new-work.md](reference/new-work.md).
 
diff --git a/.qoder/skills/impeccable/reference/brand.md b/.qoder/skills/impeccable/reference/brand.md
index 01af65d27..0f0184c0d 100644
--- a/.qoder/skills/impeccable/reference/brand.md
+++ b/.qoder/skills/impeccable/reference/brand.md
@@ -1,42 +1,3 @@
-# Brand family depth (Persuade and Experience surfaces)
+# Moved
 
-When design IS the product: brand sites, landing pages, campaign pages, portfolios, long-form content, about pages. The essentials live in SKILL.md (modes, craft floor) and, for new identity work, in [new-work.md](new-work.md); this file is extended depth for substantial brand work. Rules stated in those files are not repeated here.
-
-The register spans every genre. A tech brand, a luxury hotel, a restaurant, a band's album page, an agency portfolio. They share a stance (*communicate, not transact*) and diverge wildly in aesthetic. Don't collapse them into one look.
-
-## The aesthetic-lane test
-
-Before committing to moves, name the lane. A type-foundry specimen page is one lane; minimal-cool tech is another; acid-maximalism is another. Don't drift into editorial-magazine aesthetics on a brief that isn't editorial; a hiking brand with italic drop caps has the wrong register within the register.
-
-Then the inverse test: in one sentence, describe what you're about to build the way a competitor would describe theirs. If that sentence fits the modal landing page in the category, restart.
-
-### Reflex-reject aesthetic lanes
-
-Currently saturated aesthetic families that have flooded brand surfaces. If a brief lands in one of these lanes without a register reason that *requires* it (a literal magazine, a literal terminal), it's the second-order training reflex: the trap one tier deeper than a reflex font pick. Look further.
-
-- **Editorial-typographic.** Display serif (often italic) + small mono labels + ruled separators + monochromatic restraint. The fingerprint: three rule-separated columns, an italic serif headline, lowercase track-spaced metadata, no imagery.
-
-(Entries land and leave this list as families saturate and fade.)
-
-The reflex-reject lists apply to **new design choices**. When the existing brand has already committed to a font or a lane as part of its identity, identity-preservation wins.
-
-## Color
-
-- Name a real reference before picking a strategy; unnamed ambition becomes beige.
-- Palette IS voice. A calm brand and a restless brand should not share palette mechanics.
-- Don't converge across projects. Each brand surface differentiates from the last.
-- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
-
-## Layout
-
-- Asymmetric compositions are one option. Break the grid intentionally for emphasis.
-- Fluid spacing with `clamp()` that breathes on larger viewports.
-- For image-led briefs (hotels, restaurants, magazines, photography), full-bleed hero imagery with overlaid menu and centered headline is a canonical move; let the photograph be the design.
-
-## Brand permissions
-
-Brand can afford things product can't. Take them.
-
-- Ambitious first-load motion. Reveals and typographic choreography that earn their place; one orchestrated page-load beats scattered micro-interactions, and some brands skip entrance motion entirely, which is also a voice.
-- Single-purpose viewports. One dominant idea per fold, long scroll, deliberate pacing.
-- Art direction per section. Different sections can have different visual worlds if the narrative demands it. Consistency of voice beats consistency of treatment.
+The Persuade and Experience essentials are in SKILL.md; the depth for inventing new identity (typeface procedure, reject list and lanes, color discipline, layout moves, permissions) lives in [new-work.md](new-work.md). This stub remains because `PRODUCT.md` files with `register: brand` and older links point here.
diff --git a/.qoder/skills/impeccable/reference/live.md b/.qoder/skills/impeccable/reference/live.md
index 2b819b64c..eb63070ea 100644
--- a/.qoder/skills/impeccable/reference/live.md
+++ b/.qoder/skills/impeccable/reference/live.md
@@ -109,7 +109,7 @@ node .qoder/skills/impeccable/scripts/live-insert.mjs --id EVENT_ID --count EVEN
 - `--position` ← `event.insert.position` (`before` | `after`)
 - Anchor flags ← `event.insert.anchor` (same mapping as wrap: id, classes, tag, text)
 
-The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. Load `brand.md` or `product.md` (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
+The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. For Operate/Read surfaces load `operate.md`; Persuade/Experience surfaces use SKILL.md's mode guidance plus `new-work.md` when the variant invents identity (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
 
 For Svelte/SvelteKit targets, `live-insert.mjs` returns `previewMode: "svelte-component"` with `mode: "insert"`, `file` pointing at a temporary `node_modules/.impeccable-live/<id>/manifest.json`, `componentDir` pointing at the variant component files, and `sourceFile` pointing at the real `.svelte` route. Write each inserted variant as a real Svelte component (`v1.svelte`, `v2.svelte`, …) under `componentDir`. Insert variants must be non-empty net-new content with a single top-level root, no `data-impeccable-*` attributes, and CSS in each component's `<style>` block. Do **not** edit the route source during generation; the browser mounts the temporary component before/after the live anchor while the user cycles variants. On Accept, `live-accept.mjs` inserts the selected component markup into `sourceFile` immediately and deletes the temp session after the source write succeeds.
 
@@ -187,7 +187,7 @@ All three carry `fallback: "agent-driven"`. Follow **Handle fallback** below.
 
 ### 3. Load the action's reference
 
-If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded register reference (`brand.md` or `product.md`). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
+If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded mode depth (`operate.md` for Operate/Read; `new-work.md` when the variant invents identity). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
 
 Any other `event.action` (`bolder`, `quieter`, `distill`, `polish`, `typeset`, `colorize`, `layout`, `adapt`, `animate`, `delight`, `overdrive`): Read `reference/<action>.md` before planning. Each sub-command encodes a specific discipline; skipping its reference produces generic output. Those files may require specific params; layer them on top of the §7 budget, not instead of it.
 
@@ -252,7 +252,7 @@ Instead, work from the brand:
 
 1. Read PRODUCT.md's Brand Personality words. What physical, spatial, or material experiences would embody those words if design were not involved? (A personality described as "specific, earned, unmistakable" evokes a hand-stamped letter, a numbered print, a watchmaker's loupe. A personality described as "restless, loud, unfiltered" evokes a concert poster, a spray-painted wall, a megaphone.)
 2. From those physical experiences, derive three visual directions that are genuinely different from each other AND from the current surface you're departing.
-3. Avoid the **reflex-reject lanes** in [brand.md](brand.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
+3. Avoid the **reflex-reject lanes** in [new-work.md](new-work.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
 4. Each direction must be expressible in one concrete sentence that names a real-world referent ("a museum exhibition label system for a contemporary art gallery" not "clean and minimal"). If your sentence contains only adjectives, it's not concrete enough.
 5. **While planning each direction, also name its 2–3 parameter knobs** (per the §7 budget table). The same principle as default mode: decide "what's tunable" during planning, not after writing the HTML. A departure-mode hero with 0 parameters is not "bold creative vision," it's a missed opportunity for the user to fine-tune the direction they pick.
 
diff --git a/.qoder/skills/impeccable/reference/new-work.md b/.qoder/skills/impeccable/reference/new-work.md
index 07868de22..5cc642f06 100644
--- a/.qoder/skills/impeccable/reference/new-work.md
+++ b/.qoder/skills/impeccable/reference/new-work.md
@@ -24,6 +24,10 @@ Plan a compact token system in your reasoning: palette, type, layout concept in
 
 Pick a color strategy before picking colors: Restrained (neutrals + one accent; the default when the visitor came to operate or read) / Committed (one saturated color carries 30-60% of the surface) / Full palette (3-4 named roles) / Drenched (the surface IS the color). Persuade and Experience surfaces have permission for the bolder strategies; take them when the brief allows. Dark vs. light is never a default: write one sentence of physical scene (who uses this, where, under what light, in what mood) and let it force the answer. The warm cream near-white body background is the saturated AI default; where the axis is free, pick a background that is a choice.
 
+- Name a real reference before picking a strategy; unnamed ambition becomes beige.
+- Palette IS voice: a calm brand and a restless brand should not share palette mechanics, and each new surface differentiates from the last.
+- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
+
 ## Type and imagery for new Persuade and Experience surfaces
 
 Choose faces like objects from the brand's world; these training-data defaults mean you stopped looking: Fraunces, Playfair Display, Cormorant, Lora, Crimson, Newsreader, Syne, Space Grotesk, Space Mono, IBM Plex, Inter-as-display, DM Sans, DM Serif, Outfit, Plus Jakarta Sans, Instrument Sans. (For Operate and Read surfaces the opposite holds: system stacks and workhorse UI faces are legitimate and often correct.)
@@ -34,4 +38,10 @@ Imagery-implying briefs (food, travel, place, product, fashion) must ship real,
 
 AI-generated interfaces cluster around a few looks regardless of subject: warm cream + high-contrast serif + terracotta accent; near-black + one neon accent (acid green, cyan) + glowing edges; broadsheet-editorial hairlines + italic display serif + small tracked mono labels. All are legitimate when the brief calls for them; the brief always wins. Where the brief leaves the aesthetic free, landing in one of them means your self-check failed. Same one tier deeper: if someone could guess your aesthetic from the category alone, or from category-plus-avoidance, rework until neither answer is obvious.
 
+**Name the aesthetic lane, then test it.** Before committing to moves, say which lane this is (a specimen page, minimal-cool tech, acid maximalism...). Then the inverse test: describe what you're about to build the way a competitor would describe theirs; if that sentence fits the modal page in the category, restart. Currently saturated lanes count as reflexes, not choices, when the brief doesn't require them; the flooded one right now is editorial-typographic (display serif, often italic, small mono labels, ruled separators, monochromatic restraint, no imagery).
+
+## Persuade and Experience moves
+
+Layout: asymmetric compositions and intentional grid breaks are on the table; fluid spacing with `clamp()` that breathes on larger viewports; for image-led briefs, full-bleed hero imagery with overlaid navigation is a canonical move, letting the photograph be the design. Permissions the Operate world doesn't get: ambitious first-load motion (one orchestrated page-load beats scattered micro-interactions; skipping entrance motion entirely is also a voice), single-purpose viewports (one dominant idea per fold, deliberate pacing), and art direction per section when the narrative demands it; consistency of voice beats consistency of treatment.
+
 Before finishing, verify against SKILL.md's craft floor and run the detector; a bold page that ships mechanical defects is not done.
diff --git a/.qoder/skills/impeccable/reference/operate.md b/.qoder/skills/impeccable/reference/operate.md
new file mode 100644
index 000000000..04ee9d7d2
--- /dev/null
+++ b/.qoder/skills/impeccable/reference/operate.md
@@ -0,0 +1,60 @@
+# Operate mode depth (and Read notes)
+
+When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
+
+## The product slop test
+
+Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
+
+Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
+
+## Typography
+
+- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
+- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
+- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
+- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
+
+## Color
+
+Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
+
+- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
+- Accent color used for primary actions, current selection, and state indicators only, not decoration.
+- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
+
+## Layout
+
+- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
+
+## Components
+
+Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
+
+- Skeleton states for loading, not spinners in the middle of content.
+- Empty states that teach the interface, not "nothing here."
+- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
+
+## Motion
+
+- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
+- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
+- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
+
+## Product bans (on top of the shared absolute bans)
+
+- Decorative motion that doesn't convey state.
+- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
+- Display fonts in UI labels, buttons, data.
+- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
+- Heavy color or full-saturation accents on inactive states.
+- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
+
+## Product permissions
+
+Product can afford things brand surfaces can't.
+
+- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
+- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
+- Density. Tables with many rows, panels with many labels, dense information when users need it.
+- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
diff --git a/.qoder/skills/impeccable/reference/product.md b/.qoder/skills/impeccable/reference/product.md
index 47d6c1373..ccd31d2c1 100644
--- a/.qoder/skills/impeccable/reference/product.md
+++ b/.qoder/skills/impeccable/reference/product.md
@@ -1,60 +1,3 @@
-# Product family depth (Operate and Read surfaces)
+# Moved
 
-When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
-
-## The product slop test
-
-Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
-
-Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
-
-## Typography
-
-- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
-- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
-- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
-- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
-
-## Color
-
-Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
-
-- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
-- Accent color used for primary actions, current selection, and state indicators only, not decoration.
-- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
-
-## Layout
-
-- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
-
-## Components
-
-Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
-
-- Skeleton states for loading, not spinners in the middle of content.
-- Empty states that teach the interface, not "nothing here."
-- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
-
-## Motion
-
-- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
-- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
-- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
-
-## Product bans (on top of the shared absolute bans)
-
-- Decorative motion that doesn't convey state.
-- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
-- Display fonts in UI labels, buttons, data.
-- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
-- Heavy color or full-saturation accents on inactive states.
-- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
-
-## Product permissions
-
-Product can afford things brand surfaces can't.
-
-- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
-- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
-- Density. Tables with many rows, panels with many labels, dense information when users need it.
-- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
+Operate and Read depth lives in [operate.md](operate.md). The mode essentials are in SKILL.md. This stub remains because `PRODUCT.md` files with `register: product` and older links point here.
diff --git a/.qoder/skills/impeccable/reference/typeset.md b/.qoder/skills/impeccable/reference/typeset.md
index 4fdb5a9fd..8e9fc4e1f 100644
--- a/.qoder/skills/impeccable/reference/typeset.md
+++ b/.qoder/skills/impeccable/reference/typeset.md
@@ -185,7 +185,7 @@ Use `ch` units for character-based measure (`max-width: 65ch`). Line-height scal
 
 #### Font Selection & Pairing
 
-The tactical selection procedure and the reflex-reject list live in [reference/brand.md](brand.md) under **Font selection procedure** and **Reflex-reject list** (loaded for brand-register tasks). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
+The tactical selection procedure and the reflex-reject list live in [new-work.md](new-work.md) (loaded for new identity work). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
 
 ##### Anti-reflexes worth defending against
 
diff --git a/.qoder/skills/impeccable/scripts/context.mjs b/.qoder/skills/impeccable/scripts/context.mjs
index 15829a157..c13990ee0 100644
--- a/.qoder/skills/impeccable/scripts/context.mjs
+++ b/.qoder/skills/impeccable/scripts/context.mjs
@@ -940,7 +940,7 @@ async function cli() {
     );
   }
   if (register) {
-    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md; \`reference/${register}.md\` has extended depth for substantial work.`);
+    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md.`);
   }
   const platform = extractPlatform(ctx.product);
   const nativeRefs =
diff --git a/.rovodev/skills/impeccable/SKILL.md b/.rovodev/skills/impeccable/SKILL.md
index 6bdedf39e..6c4b7e9c7 100644
--- a/.rovodev/skills/impeccable/SKILL.md
+++ b/.rovodev/skills/impeccable/SKILL.md
@@ -41,7 +41,7 @@ Build to this floor without announcing it. The design detector (the project hook
 
 ## Registers
 
-Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode. PRODUCT.md's `register` field names the family (`brand` covers Persuade and Experience; `product` covers Operate and Read), and `reference/brand.md` / `reference/product.md` carry extended depth for the two families.
+Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode; PRODUCT.md's `register` field survives only as a family hint (`brand` covers Persuade and Experience, `product` covers Operate and Read). Depth beyond the paragraphs below: [reference/new-work.md](reference/new-work.md) when inventing identity, [reference/operate.md](reference/operate.md) for substantial Operate and Read work.
 
 **Persuade** (landing pages, marketing, campaigns; design IS the product). The deliverable is an impression that stops the scroll, earns the click, converts. Spans every genre (tech, luxury, consumer); don't collapse them into one look. Briefs that imply imagery must ship real, verified imagery; a colored rectangle where a photo belongs reads as incomplete. New Persuade surfaces take their typeface procedure and reject list from [reference/new-work.md](reference/new-work.md).
 
diff --git a/.rovodev/skills/impeccable/reference/brand.md b/.rovodev/skills/impeccable/reference/brand.md
index 01af65d27..0f0184c0d 100644
--- a/.rovodev/skills/impeccable/reference/brand.md
+++ b/.rovodev/skills/impeccable/reference/brand.md
@@ -1,42 +1,3 @@
-# Brand family depth (Persuade and Experience surfaces)
+# Moved
 
-When design IS the product: brand sites, landing pages, campaign pages, portfolios, long-form content, about pages. The essentials live in SKILL.md (modes, craft floor) and, for new identity work, in [new-work.md](new-work.md); this file is extended depth for substantial brand work. Rules stated in those files are not repeated here.
-
-The register spans every genre. A tech brand, a luxury hotel, a restaurant, a band's album page, an agency portfolio. They share a stance (*communicate, not transact*) and diverge wildly in aesthetic. Don't collapse them into one look.
-
-## The aesthetic-lane test
-
-Before committing to moves, name the lane. A type-foundry specimen page is one lane; minimal-cool tech is another; acid-maximalism is another. Don't drift into editorial-magazine aesthetics on a brief that isn't editorial; a hiking brand with italic drop caps has the wrong register within the register.
-
-Then the inverse test: in one sentence, describe what you're about to build the way a competitor would describe theirs. If that sentence fits the modal landing page in the category, restart.
-
-### Reflex-reject aesthetic lanes
-
-Currently saturated aesthetic families that have flooded brand surfaces. If a brief lands in one of these lanes without a register reason that *requires* it (a literal magazine, a literal terminal), it's the second-order training reflex: the trap one tier deeper than a reflex font pick. Look further.
-
-- **Editorial-typographic.** Display serif (often italic) + small mono labels + ruled separators + monochromatic restraint. The fingerprint: three rule-separated columns, an italic serif headline, lowercase track-spaced metadata, no imagery.
-
-(Entries land and leave this list as families saturate and fade.)
-
-The reflex-reject lists apply to **new design choices**. When the existing brand has already committed to a font or a lane as part of its identity, identity-preservation wins.
-
-## Color
-
-- Name a real reference before picking a strategy; unnamed ambition becomes beige.
-- Palette IS voice. A calm brand and a restless brand should not share palette mechanics.
-- Don't converge across projects. Each brand surface differentiates from the last.
-- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
-
-## Layout
-
-- Asymmetric compositions are one option. Break the grid intentionally for emphasis.
-- Fluid spacing with `clamp()` that breathes on larger viewports.
-- For image-led briefs (hotels, restaurants, magazines, photography), full-bleed hero imagery with overlaid menu and centered headline is a canonical move; let the photograph be the design.
-
-## Brand permissions
-
-Brand can afford things product can't. Take them.
-
-- Ambitious first-load motion. Reveals and typographic choreography that earn their place; one orchestrated page-load beats scattered micro-interactions, and some brands skip entrance motion entirely, which is also a voice.
-- Single-purpose viewports. One dominant idea per fold, long scroll, deliberate pacing.
-- Art direction per section. Different sections can have different visual worlds if the narrative demands it. Consistency of voice beats consistency of treatment.
+The Persuade and Experience essentials are in SKILL.md; the depth for inventing new identity (typeface procedure, reject list and lanes, color discipline, layout moves, permissions) lives in [new-work.md](new-work.md). This stub remains because `PRODUCT.md` files with `register: brand` and older links point here.
diff --git a/.rovodev/skills/impeccable/reference/live.md b/.rovodev/skills/impeccable/reference/live.md
index d3d4f5caa..36303cc8d 100644
--- a/.rovodev/skills/impeccable/reference/live.md
+++ b/.rovodev/skills/impeccable/reference/live.md
@@ -109,7 +109,7 @@ node .rovodev/skills/impeccable/scripts/live-insert.mjs --id EVENT_ID --count EV
 - `--position` ← `event.insert.position` (`before` | `after`)
 - Anchor flags ← `event.insert.anchor` (same mapping as wrap: id, classes, tag, text)
 
-The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. Load `brand.md` or `product.md` (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
+The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. For Operate/Read surfaces load `operate.md`; Persuade/Experience surfaces use SKILL.md's mode guidance plus `new-work.md` when the variant invents identity (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
 
 For Svelte/SvelteKit targets, `live-insert.mjs` returns `previewMode: "svelte-component"` with `mode: "insert"`, `file` pointing at a temporary `node_modules/.impeccable-live/<id>/manifest.json`, `componentDir` pointing at the variant component files, and `sourceFile` pointing at the real `.svelte` route. Write each inserted variant as a real Svelte component (`v1.svelte`, `v2.svelte`, …) under `componentDir`. Insert variants must be non-empty net-new content with a single top-level root, no `data-impeccable-*` attributes, and CSS in each component's `<style>` block. Do **not** edit the route source during generation; the browser mounts the temporary component before/after the live anchor while the user cycles variants. On Accept, `live-accept.mjs` inserts the selected component markup into `sourceFile` immediately and deletes the temp session after the source write succeeds.
 
@@ -187,7 +187,7 @@ All three carry `fallback: "agent-driven"`. Follow **Handle fallback** below.
 
 ### 3. Load the action's reference
 
-If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded register reference (`brand.md` or `product.md`). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
+If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded mode depth (`operate.md` for Operate/Read; `new-work.md` when the variant invents identity). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
 
 Any other `event.action` (`bolder`, `quieter`, `distill`, `polish`, `typeset`, `colorize`, `layout`, `adapt`, `animate`, `delight`, `overdrive`): Read `reference/<action>.md` before planning. Each sub-command encodes a specific discipline; skipping its reference produces generic output. Those files may require specific params; layer them on top of the §7 budget, not instead of it.
 
@@ -252,7 +252,7 @@ Instead, work from the brand:
 
 1. Read PRODUCT.md's Brand Personality words. What physical, spatial, or material experiences would embody those words if design were not involved? (A personality described as "specific, earned, unmistakable" evokes a hand-stamped letter, a numbered print, a watchmaker's loupe. A personality described as "restless, loud, unfiltered" evokes a concert poster, a spray-painted wall, a megaphone.)
 2. From those physical experiences, derive three visual directions that are genuinely different from each other AND from the current surface you're departing.
-3. Avoid the **reflex-reject lanes** in [brand.md](brand.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
+3. Avoid the **reflex-reject lanes** in [new-work.md](new-work.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
 4. Each direction must be expressible in one concrete sentence that names a real-world referent ("a museum exhibition label system for a contemporary art gallery" not "clean and minimal"). If your sentence contains only adjectives, it's not concrete enough.
 5. **While planning each direction, also name its 2–3 parameter knobs** (per the §7 budget table). The same principle as default mode: decide "what's tunable" during planning, not after writing the HTML. A departure-mode hero with 0 parameters is not "bold creative vision," it's a missed opportunity for the user to fine-tune the direction they pick.
 
diff --git a/.rovodev/skills/impeccable/reference/new-work.md b/.rovodev/skills/impeccable/reference/new-work.md
index 3a30a5c13..cc134cf3c 100644
--- a/.rovodev/skills/impeccable/reference/new-work.md
+++ b/.rovodev/skills/impeccable/reference/new-work.md
@@ -24,6 +24,10 @@ Plan a compact token system in your reasoning: palette, type, layout concept in
 
 Pick a color strategy before picking colors: Restrained (neutrals + one accent; the default when the visitor came to operate or read) / Committed (one saturated color carries 30-60% of the surface) / Full palette (3-4 named roles) / Drenched (the surface IS the color). Persuade and Experience surfaces have permission for the bolder strategies; take them when the brief allows. Dark vs. light is never a default: write one sentence of physical scene (who uses this, where, under what light, in what mood) and let it force the answer. The warm cream near-white body background is the saturated AI default; where the axis is free, pick a background that is a choice.
 
+- Name a real reference before picking a strategy; unnamed ambition becomes beige.
+- Palette IS voice: a calm brand and a restless brand should not share palette mechanics, and each new surface differentiates from the last.
+- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
+
 ## Type and imagery for new Persuade and Experience surfaces
 
 Choose faces like objects from the brand's world; these training-data defaults mean you stopped looking: Fraunces, Playfair Display, Cormorant, Lora, Crimson, Newsreader, Syne, Space Grotesk, Space Mono, IBM Plex, Inter-as-display, DM Sans, DM Serif, Outfit, Plus Jakarta Sans, Instrument Sans. (For Operate and Read surfaces the opposite holds: system stacks and workhorse UI faces are legitimate and often correct.)
@@ -34,4 +38,10 @@ Imagery-implying briefs (food, travel, place, product, fashion) must ship real,
 
 AI-generated interfaces cluster around a few looks regardless of subject: warm cream + high-contrast serif + terracotta accent; near-black + one neon accent (acid green, cyan) + glowing edges; broadsheet-editorial hairlines + italic display serif + small tracked mono labels. All are legitimate when the brief calls for them; the brief always wins. Where the brief leaves the aesthetic free, landing in one of them means your self-check failed. Same one tier deeper: if someone could guess your aesthetic from the category alone, or from category-plus-avoidance, rework until neither answer is obvious.
 
+**Name the aesthetic lane, then test it.** Before committing to moves, say which lane this is (a specimen page, minimal-cool tech, acid maximalism...). Then the inverse test: describe what you're about to build the way a competitor would describe theirs; if that sentence fits the modal page in the category, restart. Currently saturated lanes count as reflexes, not choices, when the brief doesn't require them; the flooded one right now is editorial-typographic (display serif, often italic, small mono labels, ruled separators, monochromatic restraint, no imagery).
+
+## Persuade and Experience moves
+
+Layout: asymmetric compositions and intentional grid breaks are on the table; fluid spacing with `clamp()` that breathes on larger viewports; for image-led briefs, full-bleed hero imagery with overlaid navigation is a canonical move, letting the photograph be the design. Permissions the Operate world doesn't get: ambitious first-load motion (one orchestrated page-load beats scattered micro-interactions; skipping entrance motion entirely is also a voice), single-purpose viewports (one dominant idea per fold, deliberate pacing), and art direction per section when the narrative demands it; consistency of voice beats consistency of treatment.
+
 Before finishing, verify against SKILL.md's craft floor and run the detector; a bold page that ships mechanical defects is not done.
diff --git a/.rovodev/skills/impeccable/reference/operate.md b/.rovodev/skills/impeccable/reference/operate.md
new file mode 100644
index 000000000..04ee9d7d2
--- /dev/null
+++ b/.rovodev/skills/impeccable/reference/operate.md
@@ -0,0 +1,60 @@
+# Operate mode depth (and Read notes)
+
+When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
+
+## The product slop test
+
+Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
+
+Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
+
+## Typography
+
+- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
+- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
+- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
+- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
+
+## Color
+
+Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
+
+- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
+- Accent color used for primary actions, current selection, and state indicators only, not decoration.
+- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
+
+## Layout
+
+- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
+
+## Components
+
+Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
+
+- Skeleton states for loading, not spinners in the middle of content.
+- Empty states that teach the interface, not "nothing here."
+- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
+
+## Motion
+
+- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
+- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
+- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
+
+## Product bans (on top of the shared absolute bans)
+
+- Decorative motion that doesn't convey state.
+- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
+- Display fonts in UI labels, buttons, data.
+- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
+- Heavy color or full-saturation accents on inactive states.
+- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
+
+## Product permissions
+
+Product can afford things brand surfaces can't.
+
+- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
+- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
+- Density. Tables with many rows, panels with many labels, dense information when users need it.
+- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
diff --git a/.rovodev/skills/impeccable/reference/product.md b/.rovodev/skills/impeccable/reference/product.md
index 47d6c1373..ccd31d2c1 100644
--- a/.rovodev/skills/impeccable/reference/product.md
+++ b/.rovodev/skills/impeccable/reference/product.md
@@ -1,60 +1,3 @@
-# Product family depth (Operate and Read surfaces)
+# Moved
 
-When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
-
-## The product slop test
-
-Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
-
-Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
-
-## Typography
-
-- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
-- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
-- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
-- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
-
-## Color
-
-Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
-
-- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
-- Accent color used for primary actions, current selection, and state indicators only, not decoration.
-- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
-
-## Layout
-
-- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
-
-## Components
-
-Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
-
-- Skeleton states for loading, not spinners in the middle of content.
-- Empty states that teach the interface, not "nothing here."
-- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
-
-## Motion
-
-- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
-- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
-- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
-
-## Product bans (on top of the shared absolute bans)
-
-- Decorative motion that doesn't convey state.
-- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
-- Display fonts in UI labels, buttons, data.
-- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
-- Heavy color or full-saturation accents on inactive states.
-- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
-
-## Product permissions
-
-Product can afford things brand surfaces can't.
-
-- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
-- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
-- Density. Tables with many rows, panels with many labels, dense information when users need it.
-- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
+Operate and Read depth lives in [operate.md](operate.md). The mode essentials are in SKILL.md. This stub remains because `PRODUCT.md` files with `register: product` and older links point here.
diff --git a/.rovodev/skills/impeccable/reference/typeset.md b/.rovodev/skills/impeccable/reference/typeset.md
index eb6440c11..3d3c00a3f 100644
--- a/.rovodev/skills/impeccable/reference/typeset.md
+++ b/.rovodev/skills/impeccable/reference/typeset.md
@@ -185,7 +185,7 @@ Use `ch` units for character-based measure (`max-width: 65ch`). Line-height scal
 
 #### Font Selection & Pairing
 
-The tactical selection procedure and the reflex-reject list live in [reference/brand.md](brand.md) under **Font selection procedure** and **Reflex-reject list** (loaded for brand-register tasks). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
+The tactical selection procedure and the reflex-reject list live in [new-work.md](new-work.md) (loaded for new identity work). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
 
 ##### Anti-reflexes worth defending against
 
diff --git a/.rovodev/skills/impeccable/scripts/context.mjs b/.rovodev/skills/impeccable/scripts/context.mjs
index 15829a157..c13990ee0 100644
--- a/.rovodev/skills/impeccable/scripts/context.mjs
+++ b/.rovodev/skills/impeccable/scripts/context.mjs
@@ -940,7 +940,7 @@ async function cli() {
     );
   }
   if (register) {
-    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md; \`reference/${register}.md\` has extended depth for substantial work.`);
+    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md.`);
   }
   const platform = extractPlatform(ctx.product);
   const nativeRefs =
diff --git a/.trae-cn/skills/impeccable/SKILL.md b/.trae-cn/skills/impeccable/SKILL.md
index fdb7548c7..9505883d6 100644
--- a/.trae-cn/skills/impeccable/SKILL.md
+++ b/.trae-cn/skills/impeccable/SKILL.md
@@ -38,7 +38,7 @@ Build to this floor without announcing it. The design detector (the project hook
 
 ## Registers
 
-Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode. PRODUCT.md's `register` field names the family (`brand` covers Persuade and Experience; `product` covers Operate and Read), and `reference/brand.md` / `reference/product.md` carry extended depth for the two families.
+Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode; PRODUCT.md's `register` field survives only as a family hint (`brand` covers Persuade and Experience, `product` covers Operate and Read). Depth beyond the paragraphs below: [reference/new-work.md](reference/new-work.md) when inventing identity, [reference/operate.md](reference/operate.md) for substantial Operate and Read work.
 
 **Persuade** (landing pages, marketing, campaigns; design IS the product). The deliverable is an impression that stops the scroll, earns the click, converts. Spans every genre (tech, luxury, consumer); don't collapse them into one look. Briefs that imply imagery must ship real, verified imagery; a colored rectangle where a photo belongs reads as incomplete. New Persuade surfaces take their typeface procedure and reject list from [reference/new-work.md](reference/new-work.md).
 
diff --git a/.trae-cn/skills/impeccable/reference/brand.md b/.trae-cn/skills/impeccable/reference/brand.md
index 01af65d27..0f0184c0d 100644
--- a/.trae-cn/skills/impeccable/reference/brand.md
+++ b/.trae-cn/skills/impeccable/reference/brand.md
@@ -1,42 +1,3 @@
-# Brand family depth (Persuade and Experience surfaces)
+# Moved
 
-When design IS the product: brand sites, landing pages, campaign pages, portfolios, long-form content, about pages. The essentials live in SKILL.md (modes, craft floor) and, for new identity work, in [new-work.md](new-work.md); this file is extended depth for substantial brand work. Rules stated in those files are not repeated here.
-
-The register spans every genre. A tech brand, a luxury hotel, a restaurant, a band's album page, an agency portfolio. They share a stance (*communicate, not transact*) and diverge wildly in aesthetic. Don't collapse them into one look.
-
-## The aesthetic-lane test
-
-Before committing to moves, name the lane. A type-foundry specimen page is one lane; minimal-cool tech is another; acid-maximalism is another. Don't drift into editorial-magazine aesthetics on a brief that isn't editorial; a hiking brand with italic drop caps has the wrong register within the register.
-
-Then the inverse test: in one sentence, describe what you're about to build the way a competitor would describe theirs. If that sentence fits the modal landing page in the category, restart.
-
-### Reflex-reject aesthetic lanes
-
-Currently saturated aesthetic families that have flooded brand surfaces. If a brief lands in one of these lanes without a register reason that *requires* it (a literal magazine, a literal terminal), it's the second-order training reflex: the trap one tier deeper than a reflex font pick. Look further.
-
-- **Editorial-typographic.** Display serif (often italic) + small mono labels + ruled separators + monochromatic restraint. The fingerprint: three rule-separated columns, an italic serif headline, lowercase track-spaced metadata, no imagery.
-
-(Entries land and leave this list as families saturate and fade.)
-
-The reflex-reject lists apply to **new design choices**. When the existing brand has already committed to a font or a lane as part of its identity, identity-preservation wins.
-
-## Color
-
-- Name a real reference before picking a strategy; unnamed ambition becomes beige.
-- Palette IS voice. A calm brand and a restless brand should not share palette mechanics.
-- Don't converge across projects. Each brand surface differentiates from the last.
-- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
-
-## Layout
-
-- Asymmetric compositions are one option. Break the grid intentionally for emphasis.
-- Fluid spacing with `clamp()` that breathes on larger viewports.
-- For image-led briefs (hotels, restaurants, magazines, photography), full-bleed hero imagery with overlaid menu and centered headline is a canonical move; let the photograph be the design.
-
-## Brand permissions
-
-Brand can afford things product can't. Take them.
-
-- Ambitious first-load motion. Reveals and typographic choreography that earn their place; one orchestrated page-load beats scattered micro-interactions, and some brands skip entrance motion entirely, which is also a voice.
-- Single-purpose viewports. One dominant idea per fold, long scroll, deliberate pacing.
-- Art direction per section. Different sections can have different visual worlds if the narrative demands it. Consistency of voice beats consistency of treatment.
+The Persuade and Experience essentials are in SKILL.md; the depth for inventing new identity (typeface procedure, reject list and lanes, color discipline, layout moves, permissions) lives in [new-work.md](new-work.md). This stub remains because `PRODUCT.md` files with `register: brand` and older links point here.
diff --git a/.trae-cn/skills/impeccable/reference/live.md b/.trae-cn/skills/impeccable/reference/live.md
index ba78670e6..1c15b7ff0 100644
--- a/.trae-cn/skills/impeccable/reference/live.md
+++ b/.trae-cn/skills/impeccable/reference/live.md
@@ -109,7 +109,7 @@ node .trae-cn/skills/impeccable/scripts/live-insert.mjs --id EVENT_ID --count EV
 - `--position` ← `event.insert.position` (`before` | `after`)
 - Anchor flags ← `event.insert.anchor` (same mapping as wrap: id, classes, tag, text)
 
-The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. Load `brand.md` or `product.md` (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
+The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. For Operate/Read surfaces load `operate.md`; Persuade/Experience surfaces use SKILL.md's mode guidance plus `new-work.md` when the variant invents identity (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
 
 For Svelte/SvelteKit targets, `live-insert.mjs` returns `previewMode: "svelte-component"` with `mode: "insert"`, `file` pointing at a temporary `node_modules/.impeccable-live/<id>/manifest.json`, `componentDir` pointing at the variant component files, and `sourceFile` pointing at the real `.svelte` route. Write each inserted variant as a real Svelte component (`v1.svelte`, `v2.svelte`, …) under `componentDir`. Insert variants must be non-empty net-new content with a single top-level root, no `data-impeccable-*` attributes, and CSS in each component's `<style>` block. Do **not** edit the route source during generation; the browser mounts the temporary component before/after the live anchor while the user cycles variants. On Accept, `live-accept.mjs` inserts the selected component markup into `sourceFile` immediately and deletes the temp session after the source write succeeds.
 
@@ -187,7 +187,7 @@ All three carry `fallback: "agent-driven"`. Follow **Handle fallback** below.
 
 ### 3. Load the action's reference
 
-If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded register reference (`brand.md` or `product.md`). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
+If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded mode depth (`operate.md` for Operate/Read; `new-work.md` when the variant invents identity). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
 
 Any other `event.action` (`bolder`, `quieter`, `distill`, `polish`, `typeset`, `colorize`, `layout`, `adapt`, `animate`, `delight`, `overdrive`): Read `reference/<action>.md` before planning. Each sub-command encodes a specific discipline; skipping its reference produces generic output. Those files may require specific params; layer them on top of the §7 budget, not instead of it.
 
@@ -252,7 +252,7 @@ Instead, work from the brand:
 
 1. Read PRODUCT.md's Brand Personality words. What physical, spatial, or material experiences would embody those words if design were not involved? (A personality described as "specific, earned, unmistakable" evokes a hand-stamped letter, a numbered print, a watchmaker's loupe. A personality described as "restless, loud, unfiltered" evokes a concert poster, a spray-painted wall, a megaphone.)
 2. From those physical experiences, derive three visual directions that are genuinely different from each other AND from the current surface you're departing.
-3. Avoid the **reflex-reject lanes** in [brand.md](brand.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
+3. Avoid the **reflex-reject lanes** in [new-work.md](new-work.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
 4. Each direction must be expressible in one concrete sentence that names a real-world referent ("a museum exhibition label system for a contemporary art gallery" not "clean and minimal"). If your sentence contains only adjectives, it's not concrete enough.
 5. **While planning each direction, also name its 2–3 parameter knobs** (per the §7 budget table). The same principle as default mode: decide "what's tunable" during planning, not after writing the HTML. A departure-mode hero with 0 parameters is not "bold creative vision," it's a missed opportunity for the user to fine-tune the direction they pick.
 
diff --git a/.trae-cn/skills/impeccable/reference/new-work.md b/.trae-cn/skills/impeccable/reference/new-work.md
index 2a4d0078e..3c2b0bdd0 100644
--- a/.trae-cn/skills/impeccable/reference/new-work.md
+++ b/.trae-cn/skills/impeccable/reference/new-work.md
@@ -24,6 +24,10 @@ Plan a compact token system in your reasoning: palette, type, layout concept in
 
 Pick a color strategy before picking colors: Restrained (neutrals + one accent; the default when the visitor came to operate or read) / Committed (one saturated color carries 30-60% of the surface) / Full palette (3-4 named roles) / Drenched (the surface IS the color). Persuade and Experience surfaces have permission for the bolder strategies; take them when the brief allows. Dark vs. light is never a default: write one sentence of physical scene (who uses this, where, under what light, in what mood) and let it force the answer. The warm cream near-white body background is the saturated AI default; where the axis is free, pick a background that is a choice.
 
+- Name a real reference before picking a strategy; unnamed ambition becomes beige.
+- Palette IS voice: a calm brand and a restless brand should not share palette mechanics, and each new surface differentiates from the last.
+- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
+
 ## Type and imagery for new Persuade and Experience surfaces
 
 Choose faces like objects from the brand's world; these training-data defaults mean you stopped looking: Fraunces, Playfair Display, Cormorant, Lora, Crimson, Newsreader, Syne, Space Grotesk, Space Mono, IBM Plex, Inter-as-display, DM Sans, DM Serif, Outfit, Plus Jakarta Sans, Instrument Sans. (For Operate and Read surfaces the opposite holds: system stacks and workhorse UI faces are legitimate and often correct.)
@@ -34,4 +38,10 @@ Imagery-implying briefs (food, travel, place, product, fashion) must ship real,
 
 AI-generated interfaces cluster around a few looks regardless of subject: warm cream + high-contrast serif + terracotta accent; near-black + one neon accent (acid green, cyan) + glowing edges; broadsheet-editorial hairlines + italic display serif + small tracked mono labels. All are legitimate when the brief calls for them; the brief always wins. Where the brief leaves the aesthetic free, landing in one of them means your self-check failed. Same one tier deeper: if someone could guess your aesthetic from the category alone, or from category-plus-avoidance, rework until neither answer is obvious.
 
+**Name the aesthetic lane, then test it.** Before committing to moves, say which lane this is (a specimen page, minimal-cool tech, acid maximalism...). Then the inverse test: describe what you're about to build the way a competitor would describe theirs; if that sentence fits the modal page in the category, restart. Currently saturated lanes count as reflexes, not choices, when the brief doesn't require them; the flooded one right now is editorial-typographic (display serif, often italic, small mono labels, ruled separators, monochromatic restraint, no imagery).
+
+## Persuade and Experience moves
+
+Layout: asymmetric compositions and intentional grid breaks are on the table; fluid spacing with `clamp()` that breathes on larger viewports; for image-led briefs, full-bleed hero imagery with overlaid navigation is a canonical move, letting the photograph be the design. Permissions the Operate world doesn't get: ambitious first-load motion (one orchestrated page-load beats scattered micro-interactions; skipping entrance motion entirely is also a voice), single-purpose viewports (one dominant idea per fold, deliberate pacing), and art direction per section when the narrative demands it; consistency of voice beats consistency of treatment.
+
 Before finishing, verify against SKILL.md's craft floor and run the detector; a bold page that ships mechanical defects is not done.
diff --git a/.trae-cn/skills/impeccable/reference/operate.md b/.trae-cn/skills/impeccable/reference/operate.md
new file mode 100644
index 000000000..04ee9d7d2
--- /dev/null
+++ b/.trae-cn/skills/impeccable/reference/operate.md
@@ -0,0 +1,60 @@
+# Operate mode depth (and Read notes)
+
+When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
+
+## The product slop test
+
+Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
+
+Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
+
+## Typography
+
+- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
+- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
+- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
+- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
+
+## Color
+
+Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
+
+- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
+- Accent color used for primary actions, current selection, and state indicators only, not decoration.
+- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
+
+## Layout
+
+- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
+
+## Components
+
+Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
+
+- Skeleton states for loading, not spinners in the middle of content.
+- Empty states that teach the interface, not "nothing here."
+- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
+
+## Motion
+
+- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
+- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
+- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
+
+## Product bans (on top of the shared absolute bans)
+
+- Decorative motion that doesn't convey state.
+- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
+- Display fonts in UI labels, buttons, data.
+- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
+- Heavy color or full-saturation accents on inactive states.
+- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
+
+## Product permissions
+
+Product can afford things brand surfaces can't.
+
+- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
+- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
+- Density. Tables with many rows, panels with many labels, dense information when users need it.
+- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
diff --git a/.trae-cn/skills/impeccable/reference/product.md b/.trae-cn/skills/impeccable/reference/product.md
index 47d6c1373..ccd31d2c1 100644
--- a/.trae-cn/skills/impeccable/reference/product.md
+++ b/.trae-cn/skills/impeccable/reference/product.md
@@ -1,60 +1,3 @@
-# Product family depth (Operate and Read surfaces)
+# Moved
 
-When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
-
-## The product slop test
-
-Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
-
-Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
-
-## Typography
-
-- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
-- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
-- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
-- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
-
-## Color
-
-Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
-
-- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
-- Accent color used for primary actions, current selection, and state indicators only, not decoration.
-- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
-
-## Layout
-
-- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
-
-## Components
-
-Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
-
-- Skeleton states for loading, not spinners in the middle of content.
-- Empty states that teach the interface, not "nothing here."
-- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
-
-## Motion
-
-- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
-- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
-- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
-
-## Product bans (on top of the shared absolute bans)
-
-- Decorative motion that doesn't convey state.
-- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
-- Display fonts in UI labels, buttons, data.
-- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
-- Heavy color or full-saturation accents on inactive states.
-- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
-
-## Product permissions
-
-Product can afford things brand surfaces can't.
-
-- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
-- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
-- Density. Tables with many rows, panels with many labels, dense information when users need it.
-- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
+Operate and Read depth lives in [operate.md](operate.md). The mode essentials are in SKILL.md. This stub remains because `PRODUCT.md` files with `register: product` and older links point here.
diff --git a/.trae-cn/skills/impeccable/reference/typeset.md b/.trae-cn/skills/impeccable/reference/typeset.md
index 3576a2630..c84123698 100644
--- a/.trae-cn/skills/impeccable/reference/typeset.md
+++ b/.trae-cn/skills/impeccable/reference/typeset.md
@@ -185,7 +185,7 @@ Use `ch` units for character-based measure (`max-width: 65ch`). Line-height scal
 
 #### Font Selection & Pairing
 
-The tactical selection procedure and the reflex-reject list live in [reference/brand.md](brand.md) under **Font selection procedure** and **Reflex-reject list** (loaded for brand-register tasks). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
+The tactical selection procedure and the reflex-reject list live in [new-work.md](new-work.md) (loaded for new identity work). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
 
 ##### Anti-reflexes worth defending against
 
diff --git a/.trae-cn/skills/impeccable/scripts/context.mjs b/.trae-cn/skills/impeccable/scripts/context.mjs
index 15829a157..c13990ee0 100644
--- a/.trae-cn/skills/impeccable/scripts/context.mjs
+++ b/.trae-cn/skills/impeccable/scripts/context.mjs
@@ -940,7 +940,7 @@ async function cli() {
     );
   }
   if (register) {
-    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md; \`reference/${register}.md\` has extended depth for substantial work.`);
+    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md.`);
   }
   const platform = extractPlatform(ctx.product);
   const nativeRefs =
diff --git a/.trae/skills/impeccable/SKILL.md b/.trae/skills/impeccable/SKILL.md
index 06d1e9e9d..31f94e9b4 100644
--- a/.trae/skills/impeccable/SKILL.md
+++ b/.trae/skills/impeccable/SKILL.md
@@ -38,7 +38,7 @@ Build to this floor without announcing it. The design detector (the project hook
 
 ## Registers
 
-Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode. PRODUCT.md's `register` field names the family (`brand` covers Persuade and Experience; `product` covers Operate and Read), and `reference/brand.md` / `reference/product.md` carry extended depth for the two families.
+Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode; PRODUCT.md's `register` field survives only as a family hint (`brand` covers Persuade and Experience, `product` covers Operate and Read). Depth beyond the paragraphs below: [reference/new-work.md](reference/new-work.md) when inventing identity, [reference/operate.md](reference/operate.md) for substantial Operate and Read work.
 
 **Persuade** (landing pages, marketing, campaigns; design IS the product). The deliverable is an impression that stops the scroll, earns the click, converts. Spans every genre (tech, luxury, consumer); don't collapse them into one look. Briefs that imply imagery must ship real, verified imagery; a colored rectangle where a photo belongs reads as incomplete. New Persuade surfaces take their typeface procedure and reject list from [reference/new-work.md](reference/new-work.md).
 
diff --git a/.trae/skills/impeccable/reference/brand.md b/.trae/skills/impeccable/reference/brand.md
index 01af65d27..0f0184c0d 100644
--- a/.trae/skills/impeccable/reference/brand.md
+++ b/.trae/skills/impeccable/reference/brand.md
@@ -1,42 +1,3 @@
-# Brand family depth (Persuade and Experience surfaces)
+# Moved
 
-When design IS the product: brand sites, landing pages, campaign pages, portfolios, long-form content, about pages. The essentials live in SKILL.md (modes, craft floor) and, for new identity work, in [new-work.md](new-work.md); this file is extended depth for substantial brand work. Rules stated in those files are not repeated here.
-
-The register spans every genre. A tech brand, a luxury hotel, a restaurant, a band's album page, an agency portfolio. They share a stance (*communicate, not transact*) and diverge wildly in aesthetic. Don't collapse them into one look.
-
-## The aesthetic-lane test
-
-Before committing to moves, name the lane. A type-foundry specimen page is one lane; minimal-cool tech is another; acid-maximalism is another. Don't drift into editorial-magazine aesthetics on a brief that isn't editorial; a hiking brand with italic drop caps has the wrong register within the register.
-
-Then the inverse test: in one sentence, describe what you're about to build the way a competitor would describe theirs. If that sentence fits the modal landing page in the category, restart.
-
-### Reflex-reject aesthetic lanes
-
-Currently saturated aesthetic families that have flooded brand surfaces. If a brief lands in one of these lanes without a register reason that *requires* it (a literal magazine, a literal terminal), it's the second-order training reflex: the trap one tier deeper than a reflex font pick. Look further.
-
-- **Editorial-typographic.** Display serif (often italic) + small mono labels + ruled separators + monochromatic restraint. The fingerprint: three rule-separated columns, an italic serif headline, lowercase track-spaced metadata, no imagery.
-
-(Entries land and leave this list as families saturate and fade.)
-
-The reflex-reject lists apply to **new design choices**. When the existing brand has already committed to a font or a lane as part of its identity, identity-preservation wins.
-
-## Color
-
-- Name a real reference before picking a strategy; unnamed ambition becomes beige.
-- Palette IS voice. A calm brand and a restless brand should not share palette mechanics.
-- Don't converge across projects. Each brand surface differentiates from the last.
-- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
-
-## Layout
-
-- Asymmetric compositions are one option. Break the grid intentionally for emphasis.
-- Fluid spacing with `clamp()` that breathes on larger viewports.
-- For image-led briefs (hotels, restaurants, magazines, photography), full-bleed hero imagery with overlaid menu and centered headline is a canonical move; let the photograph be the design.
-
-## Brand permissions
-
-Brand can afford things product can't. Take them.
-
-- Ambitious first-load motion. Reveals and typographic choreography that earn their place; one orchestrated page-load beats scattered micro-interactions, and some brands skip entrance motion entirely, which is also a voice.
-- Single-purpose viewports. One dominant idea per fold, long scroll, deliberate pacing.
-- Art direction per section. Different sections can have different visual worlds if the narrative demands it. Consistency of voice beats consistency of treatment.
+The Persuade and Experience essentials are in SKILL.md; the depth for inventing new identity (typeface procedure, reject list and lanes, color discipline, layout moves, permissions) lives in [new-work.md](new-work.md). This stub remains because `PRODUCT.md` files with `register: brand` and older links point here.
diff --git a/.trae/skills/impeccable/reference/live.md b/.trae/skills/impeccable/reference/live.md
index c8279f19c..4e68e77c4 100644
--- a/.trae/skills/impeccable/reference/live.md
+++ b/.trae/skills/impeccable/reference/live.md
@@ -109,7 +109,7 @@ node .trae/skills/impeccable/scripts/live-insert.mjs --id EVENT_ID --count EVENT
 - `--position` ← `event.insert.position` (`before` | `after`)
 - Anchor flags ← `event.insert.anchor` (same mapping as wrap: id, classes, tag, text)
 
-The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. Load `brand.md` or `product.md` (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
+The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. For Operate/Read surfaces load `operate.md`; Persuade/Experience surfaces use SKILL.md's mode guidance plus `new-work.md` when the variant invents identity (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
 
 For Svelte/SvelteKit targets, `live-insert.mjs` returns `previewMode: "svelte-component"` with `mode: "insert"`, `file` pointing at a temporary `node_modules/.impeccable-live/<id>/manifest.json`, `componentDir` pointing at the variant component files, and `sourceFile` pointing at the real `.svelte` route. Write each inserted variant as a real Svelte component (`v1.svelte`, `v2.svelte`, …) under `componentDir`. Insert variants must be non-empty net-new content with a single top-level root, no `data-impeccable-*` attributes, and CSS in each component's `<style>` block. Do **not** edit the route source during generation; the browser mounts the temporary component before/after the live anchor while the user cycles variants. On Accept, `live-accept.mjs` inserts the selected component markup into `sourceFile` immediately and deletes the temp session after the source write succeeds.
 
@@ -187,7 +187,7 @@ All three carry `fallback: "agent-driven"`. Follow **Handle fallback** below.
 
 ### 3. Load the action's reference
 
-If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded register reference (`brand.md` or `product.md`). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
+If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded mode depth (`operate.md` for Operate/Read; `new-work.md` when the variant invents identity). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
 
 Any other `event.action` (`bolder`, `quieter`, `distill`, `polish`, `typeset`, `colorize`, `layout`, `adapt`, `animate`, `delight`, `overdrive`): Read `reference/<action>.md` before planning. Each sub-command encodes a specific discipline; skipping its reference produces generic output. Those files may require specific params; layer them on top of the §7 budget, not instead of it.
 
@@ -252,7 +252,7 @@ Instead, work from the brand:
 
 1. Read PRODUCT.md's Brand Personality words. What physical, spatial, or material experiences would embody those words if design were not involved? (A personality described as "specific, earned, unmistakable" evokes a hand-stamped letter, a numbered print, a watchmaker's loupe. A personality described as "restless, loud, unfiltered" evokes a concert poster, a spray-painted wall, a megaphone.)
 2. From those physical experiences, derive three visual directions that are genuinely different from each other AND from the current surface you're departing.
-3. Avoid the **reflex-reject lanes** in [brand.md](brand.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
+3. Avoid the **reflex-reject lanes** in [new-work.md](new-work.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
 4. Each direction must be expressible in one concrete sentence that names a real-world referent ("a museum exhibition label system for a contemporary art gallery" not "clean and minimal"). If your sentence contains only adjectives, it's not concrete enough.
 5. **While planning each direction, also name its 2–3 parameter knobs** (per the §7 budget table). The same principle as default mode: decide "what's tunable" during planning, not after writing the HTML. A departure-mode hero with 0 parameters is not "bold creative vision," it's a missed opportunity for the user to fine-tune the direction they pick.
 
diff --git a/.trae/skills/impeccable/reference/new-work.md b/.trae/skills/impeccable/reference/new-work.md
index 201d14898..564714a15 100644
--- a/.trae/skills/impeccable/reference/new-work.md
+++ b/.trae/skills/impeccable/reference/new-work.md
@@ -24,6 +24,10 @@ Plan a compact token system in your reasoning: palette, type, layout concept in
 
 Pick a color strategy before picking colors: Restrained (neutrals + one accent; the default when the visitor came to operate or read) / Committed (one saturated color carries 30-60% of the surface) / Full palette (3-4 named roles) / Drenched (the surface IS the color). Persuade and Experience surfaces have permission for the bolder strategies; take them when the brief allows. Dark vs. light is never a default: write one sentence of physical scene (who uses this, where, under what light, in what mood) and let it force the answer. The warm cream near-white body background is the saturated AI default; where the axis is free, pick a background that is a choice.
 
+- Name a real reference before picking a strategy; unnamed ambition becomes beige.
+- Palette IS voice: a calm brand and a restless brand should not share palette mechanics, and each new surface differentiates from the last.
+- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
+
 ## Type and imagery for new Persuade and Experience surfaces
 
 Choose faces like objects from the brand's world; these training-data defaults mean you stopped looking: Fraunces, Playfair Display, Cormorant, Lora, Crimson, Newsreader, Syne, Space Grotesk, Space Mono, IBM Plex, Inter-as-display, DM Sans, DM Serif, Outfit, Plus Jakarta Sans, Instrument Sans. (For Operate and Read surfaces the opposite holds: system stacks and workhorse UI faces are legitimate and often correct.)
@@ -34,4 +38,10 @@ Imagery-implying briefs (food, travel, place, product, fashion) must ship real,
 
 AI-generated interfaces cluster around a few looks regardless of subject: warm cream + high-contrast serif + terracotta accent; near-black + one neon accent (acid green, cyan) + glowing edges; broadsheet-editorial hairlines + italic display serif + small tracked mono labels. All are legitimate when the brief calls for them; the brief always wins. Where the brief leaves the aesthetic free, landing in one of them means your self-check failed. Same one tier deeper: if someone could guess your aesthetic from the category alone, or from category-plus-avoidance, rework until neither answer is obvious.
 
+**Name the aesthetic lane, then test it.** Before committing to moves, say which lane this is (a specimen page, minimal-cool tech, acid maximalism...). Then the inverse test: describe what you're about to build the way a competitor would describe theirs; if that sentence fits the modal page in the category, restart. Currently saturated lanes count as reflexes, not choices, when the brief doesn't require them; the flooded one right now is editorial-typographic (display serif, often italic, small mono labels, ruled separators, monochromatic restraint, no imagery).
+
+## Persuade and Experience moves
+
+Layout: asymmetric compositions and intentional grid breaks are on the table; fluid spacing with `clamp()` that breathes on larger viewports; for image-led briefs, full-bleed hero imagery with overlaid navigation is a canonical move, letting the photograph be the design. Permissions the Operate world doesn't get: ambitious first-load motion (one orchestrated page-load beats scattered micro-interactions; skipping entrance motion entirely is also a voice), single-purpose viewports (one dominant idea per fold, deliberate pacing), and art direction per section when the narrative demands it; consistency of voice beats consistency of treatment.
+
 Before finishing, verify against SKILL.md's craft floor and run the detector; a bold page that ships mechanical defects is not done.
diff --git a/.trae/skills/impeccable/reference/operate.md b/.trae/skills/impeccable/reference/operate.md
new file mode 100644
index 000000000..04ee9d7d2
--- /dev/null
+++ b/.trae/skills/impeccable/reference/operate.md
@@ -0,0 +1,60 @@
+# Operate mode depth (and Read notes)
+
+When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
+
+## The product slop test
+
+Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
+
+Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
+
+## Typography
+
+- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
+- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
+- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
+- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
+
+## Color
+
+Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
+
+- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
+- Accent color used for primary actions, current selection, and state indicators only, not decoration.
+- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
+
+## Layout
+
+- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
+
+## Components
+
+Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
+
+- Skeleton states for loading, not spinners in the middle of content.
+- Empty states that teach the interface, not "nothing here."
+- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
+
+## Motion
+
+- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
+- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
+- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
+
+## Product bans (on top of the shared absolute bans)
+
+- Decorative motion that doesn't convey state.
+- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
+- Display fonts in UI labels, buttons, data.
+- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
+- Heavy color or full-saturation accents on inactive states.
+- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
+
+## Product permissions
+
+Product can afford things brand surfaces can't.
+
+- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
+- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
+- Density. Tables with many rows, panels with many labels, dense information when users need it.
+- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
diff --git a/.trae/skills/impeccable/reference/product.md b/.trae/skills/impeccable/reference/product.md
index 47d6c1373..ccd31d2c1 100644
--- a/.trae/skills/impeccable/reference/product.md
+++ b/.trae/skills/impeccable/reference/product.md
@@ -1,60 +1,3 @@
-# Product family depth (Operate and Read surfaces)
+# Moved
 
-When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
-
-## The product slop test
-
-Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
-
-Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
-
-## Typography
-
-- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
-- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
-- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
-- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
-
-## Color
-
-Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
-
-- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
-- Accent color used for primary actions, current selection, and state indicators only, not decoration.
-- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
-
-## Layout
-
-- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
-
-## Components
-
-Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
-
-- Skeleton states for loading, not spinners in the middle of content.
-- Empty states that teach the interface, not "nothing here."
-- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
-
-## Motion
-
-- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
-- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
-- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
-
-## Product bans (on top of the shared absolute bans)
-
-- Decorative motion that doesn't convey state.
-- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
-- Display fonts in UI labels, buttons, data.
-- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
-- Heavy color or full-saturation accents on inactive states.
-- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
-
-## Product permissions
-
-Product can afford things brand surfaces can't.
-
-- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
-- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
-- Density. Tables with many rows, panels with many labels, dense information when users need it.
-- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
+Operate and Read depth lives in [operate.md](operate.md). The mode essentials are in SKILL.md. This stub remains because `PRODUCT.md` files with `register: product` and older links point here.
diff --git a/.trae/skills/impeccable/reference/typeset.md b/.trae/skills/impeccable/reference/typeset.md
index 8a273b6bb..b4fa29bbb 100644
--- a/.trae/skills/impeccable/reference/typeset.md
+++ b/.trae/skills/impeccable/reference/typeset.md
@@ -185,7 +185,7 @@ Use `ch` units for character-based measure (`max-width: 65ch`). Line-height scal
 
 #### Font Selection & Pairing
 
-The tactical selection procedure and the reflex-reject list live in [reference/brand.md](brand.md) under **Font selection procedure** and **Reflex-reject list** (loaded for brand-register tasks). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
+The tactical selection procedure and the reflex-reject list live in [new-work.md](new-work.md) (loaded for new identity work). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
 
 ##### Anti-reflexes worth defending against
 
diff --git a/.trae/skills/impeccable/scripts/context.mjs b/.trae/skills/impeccable/scripts/context.mjs
index 15829a157..c13990ee0 100644
--- a/.trae/skills/impeccable/scripts/context.mjs
+++ b/.trae/skills/impeccable/scripts/context.mjs
@@ -940,7 +940,7 @@ async function cli() {
     );
   }
   if (register) {
-    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md; \`reference/${register}.md\` has extended depth for substantial work.`);
+    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md.`);
   }
   const platform = extractPlatform(ctx.product);
   const nativeRefs =
diff --git a/plugin/skills/impeccable/SKILL.md b/plugin/skills/impeccable/SKILL.md
index 8645c49ff..c84d959dd 100644
--- a/plugin/skills/impeccable/SKILL.md
+++ b/plugin/skills/impeccable/SKILL.md
@@ -41,7 +41,7 @@ Build to this floor without announcing it. The design detector (the project hook
 
 ## Registers
 
-Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode. PRODUCT.md's `register` field names the family (`brand` covers Persuade and Experience; `product` covers Operate and Read), and `reference/brand.md` / `reference/product.md` carry extended depth for the two families.
+Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode; PRODUCT.md's `register` field survives only as a family hint (`brand` covers Persuade and Experience, `product` covers Operate and Read). Depth beyond the paragraphs below: [reference/new-work.md](reference/new-work.md) when inventing identity, [reference/operate.md](reference/operate.md) for substantial Operate and Read work.
 
 **Persuade** (landing pages, marketing, campaigns; design IS the product). The deliverable is an impression that stops the scroll, earns the click, converts. Spans every genre (tech, luxury, consumer); don't collapse them into one look. Briefs that imply imagery must ship real, verified imagery; a colored rectangle where a photo belongs reads as incomplete. New Persuade surfaces take their typeface procedure and reject list from [reference/new-work.md](reference/new-work.md).
 
diff --git a/plugin/skills/impeccable/reference/brand.md b/plugin/skills/impeccable/reference/brand.md
index 01af65d27..0f0184c0d 100644
--- a/plugin/skills/impeccable/reference/brand.md
+++ b/plugin/skills/impeccable/reference/brand.md
@@ -1,42 +1,3 @@
-# Brand family depth (Persuade and Experience surfaces)
+# Moved
 
-When design IS the product: brand sites, landing pages, campaign pages, portfolios, long-form content, about pages. The essentials live in SKILL.md (modes, craft floor) and, for new identity work, in [new-work.md](new-work.md); this file is extended depth for substantial brand work. Rules stated in those files are not repeated here.
-
-The register spans every genre. A tech brand, a luxury hotel, a restaurant, a band's album page, an agency portfolio. They share a stance (*communicate, not transact*) and diverge wildly in aesthetic. Don't collapse them into one look.
-
-## The aesthetic-lane test
-
-Before committing to moves, name the lane. A type-foundry specimen page is one lane; minimal-cool tech is another; acid-maximalism is another. Don't drift into editorial-magazine aesthetics on a brief that isn't editorial; a hiking brand with italic drop caps has the wrong register within the register.
-
-Then the inverse test: in one sentence, describe what you're about to build the way a competitor would describe theirs. If that sentence fits the modal landing page in the category, restart.
-
-### Reflex-reject aesthetic lanes
-
-Currently saturated aesthetic families that have flooded brand surfaces. If a brief lands in one of these lanes without a register reason that *requires* it (a literal magazine, a literal terminal), it's the second-order training reflex: the trap one tier deeper than a reflex font pick. Look further.
-
-- **Editorial-typographic.** Display serif (often italic) + small mono labels + ruled separators + monochromatic restraint. The fingerprint: three rule-separated columns, an italic serif headline, lowercase track-spaced metadata, no imagery.
-
-(Entries land and leave this list as families saturate and fade.)
-
-The reflex-reject lists apply to **new design choices**. When the existing brand has already committed to a font or a lane as part of its identity, identity-preservation wins.
-
-## Color
-
-- Name a real reference before picking a strategy; unnamed ambition becomes beige.
-- Palette IS voice. A calm brand and a restless brand should not share palette mechanics.
-- Don't converge across projects. Each brand surface differentiates from the last.
-- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
-
-## Layout
-
-- Asymmetric compositions are one option. Break the grid intentionally for emphasis.
-- Fluid spacing with `clamp()` that breathes on larger viewports.
-- For image-led briefs (hotels, restaurants, magazines, photography), full-bleed hero imagery with overlaid menu and centered headline is a canonical move; let the photograph be the design.
-
-## Brand permissions
-
-Brand can afford things product can't. Take them.
-
-- Ambitious first-load motion. Reveals and typographic choreography that earn their place; one orchestrated page-load beats scattered micro-interactions, and some brands skip entrance motion entirely, which is also a voice.
-- Single-purpose viewports. One dominant idea per fold, long scroll, deliberate pacing.
-- Art direction per section. Different sections can have different visual worlds if the narrative demands it. Consistency of voice beats consistency of treatment.
+The Persuade and Experience essentials are in SKILL.md; the depth for inventing new identity (typeface procedure, reject list and lanes, color discipline, layout moves, permissions) lives in [new-work.md](new-work.md). This stub remains because `PRODUCT.md` files with `register: brand` and older links point here.
diff --git a/plugin/skills/impeccable/reference/live.md b/plugin/skills/impeccable/reference/live.md
index 8c2cccd0a..b20cee04a 100644
--- a/plugin/skills/impeccable/reference/live.md
+++ b/plugin/skills/impeccable/reference/live.md
@@ -109,7 +109,7 @@ node .claude/skills/impeccable/scripts/live-insert.mjs --id EVENT_ID --count EVE
 - `--position` ← `event.insert.position` (`before` | `after`)
 - Anchor flags ← `event.insert.anchor` (same mapping as wrap: id, classes, tag, text)
 
-The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. Load `brand.md` or `product.md` (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
+The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. For Operate/Read surfaces load `operate.md`; Persuade/Experience surfaces use SKILL.md's mode guidance plus `new-work.md` when the variant invents identity (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
 
 For Svelte/SvelteKit targets, `live-insert.mjs` returns `previewMode: "svelte-component"` with `mode: "insert"`, `file` pointing at a temporary `node_modules/.impeccable-live/<id>/manifest.json`, `componentDir` pointing at the variant component files, and `sourceFile` pointing at the real `.svelte` route. Write each inserted variant as a real Svelte component (`v1.svelte`, `v2.svelte`, …) under `componentDir`. Insert variants must be non-empty net-new content with a single top-level root, no `data-impeccable-*` attributes, and CSS in each component's `<style>` block. Do **not** edit the route source during generation; the browser mounts the temporary component before/after the live anchor while the user cycles variants. On Accept, `live-accept.mjs` inserts the selected component markup into `sourceFile` immediately and deletes the temp session after the source write succeeds.
 
@@ -187,7 +187,7 @@ All three carry `fallback: "agent-driven"`. Follow **Handle fallback** below.
 
 ### 3. Load the action's reference
 
-If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded register reference (`brand.md` or `product.md`). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
+If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded mode depth (`operate.md` for Operate/Read; `new-work.md` when the variant invents identity). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
 
 Any other `event.action` (`bolder`, `quieter`, `distill`, `polish`, `typeset`, `colorize`, `layout`, `adapt`, `animate`, `delight`, `overdrive`): Read `reference/<action>.md` before planning. Each sub-command encodes a specific discipline; skipping its reference produces generic output. Those files may require specific params; layer them on top of the §7 budget, not instead of it.
 
@@ -252,7 +252,7 @@ Instead, work from the brand:
 
 1. Read PRODUCT.md's Brand Personality words. What physical, spatial, or material experiences would embody those words if design were not involved? (A personality described as "specific, earned, unmistakable" evokes a hand-stamped letter, a numbered print, a watchmaker's loupe. A personality described as "restless, loud, unfiltered" evokes a concert poster, a spray-painted wall, a megaphone.)
 2. From those physical experiences, derive three visual directions that are genuinely different from each other AND from the current surface you're departing.
-3. Avoid the **reflex-reject lanes** in [brand.md](brand.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
+3. Avoid the **reflex-reject lanes** in [new-work.md](new-work.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
 4. Each direction must be expressible in one concrete sentence that names a real-world referent ("a museum exhibition label system for a contemporary art gallery" not "clean and minimal"). If your sentence contains only adjectives, it's not concrete enough.
 5. **While planning each direction, also name its 2–3 parameter knobs** (per the §7 budget table). The same principle as default mode: decide "what's tunable" during planning, not after writing the HTML. A departure-mode hero with 0 parameters is not "bold creative vision," it's a missed opportunity for the user to fine-tune the direction they pick.
 
diff --git a/plugin/skills/impeccable/reference/new-work.md b/plugin/skills/impeccable/reference/new-work.md
index 13c8f054b..28fc63d23 100644
--- a/plugin/skills/impeccable/reference/new-work.md
+++ b/plugin/skills/impeccable/reference/new-work.md
@@ -24,6 +24,10 @@ Plan a compact token system in your reasoning: palette, type, layout concept in
 
 Pick a color strategy before picking colors: Restrained (neutrals + one accent; the default when the visitor came to operate or read) / Committed (one saturated color carries 30-60% of the surface) / Full palette (3-4 named roles) / Drenched (the surface IS the color). Persuade and Experience surfaces have permission for the bolder strategies; take them when the brief allows. Dark vs. light is never a default: write one sentence of physical scene (who uses this, where, under what light, in what mood) and let it force the answer. The warm cream near-white body background is the saturated AI default; where the axis is free, pick a background that is a choice.
 
+- Name a real reference before picking a strategy; unnamed ambition becomes beige.
+- Palette IS voice: a calm brand and a restless brand should not share palette mechanics, and each new surface differentiates from the last.
+- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette.
+
 ## Type and imagery for new Persuade and Experience surfaces
 
 Choose faces like objects from the brand's world; these training-data defaults mean you stopped looking: Fraunces, Playfair Display, Cormorant, Lora, Crimson, Newsreader, Syne, Space Grotesk, Space Mono, IBM Plex, Inter-as-display, DM Sans, DM Serif, Outfit, Plus Jakarta Sans, Instrument Sans. (For Operate and Read surfaces the opposite holds: system stacks and workhorse UI faces are legitimate and often correct.)
@@ -34,4 +38,10 @@ Imagery-implying briefs (food, travel, place, product, fashion) must ship real,
 
 AI-generated interfaces cluster around a few looks regardless of subject: warm cream + high-contrast serif + terracotta accent; near-black + one neon accent (acid green, cyan) + glowing edges; broadsheet-editorial hairlines + italic display serif + small tracked mono labels. All are legitimate when the brief calls for them; the brief always wins. Where the brief leaves the aesthetic free, landing in one of them means your self-check failed. Same one tier deeper: if someone could guess your aesthetic from the category alone, or from category-plus-avoidance, rework until neither answer is obvious.
 
+**Name the aesthetic lane, then test it.** Before committing to moves, say which lane this is (a specimen page, minimal-cool tech, acid maximalism...). Then the inverse test: describe what you're about to build the way a competitor would describe theirs; if that sentence fits the modal page in the category, restart. Currently saturated lanes count as reflexes, not choices, when the brief doesn't require them; the flooded one right now is editorial-typographic (display serif, often italic, small mono labels, ruled separators, monochromatic restraint, no imagery).
+
+## Persuade and Experience moves
+
+Layout: asymmetric compositions and intentional grid breaks are on the table; fluid spacing with `clamp()` that breathes on larger viewports; for image-led briefs, full-bleed hero imagery with overlaid navigation is a canonical move, letting the photograph be the design. Permissions the Operate world doesn't get: ambitious first-load motion (one orchestrated page-load beats scattered micro-interactions; skipping entrance motion entirely is also a voice), single-purpose viewports (one dominant idea per fold, deliberate pacing), and art direction per section when the narrative demands it; consistency of voice beats consistency of treatment.
+
 Before finishing, verify against SKILL.md's craft floor and run the detector; a bold page that ships mechanical defects is not done.
diff --git a/plugin/skills/impeccable/reference/operate.md b/plugin/skills/impeccable/reference/operate.md
new file mode 100644
index 000000000..04ee9d7d2
--- /dev/null
+++ b/plugin/skills/impeccable/reference/operate.md
@@ -0,0 +1,60 @@
+# Operate mode depth (and Read notes)
+
+When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
+
+## The product slop test
+
+Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
+
+Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
+
+## Typography
+
+- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
+- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
+- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
+- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
+
+## Color
+
+Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
+
+- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
+- Accent color used for primary actions, current selection, and state indicators only, not decoration.
+- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
+
+## Layout
+
+- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
+
+## Components
+
+Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
+
+- Skeleton states for loading, not spinners in the middle of content.
+- Empty states that teach the interface, not "nothing here."
+- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
+
+## Motion
+
+- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
+- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
+- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
+
+## Product bans (on top of the shared absolute bans)
+
+- Decorative motion that doesn't convey state.
+- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
+- Display fonts in UI labels, buttons, data.
+- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
+- Heavy color or full-saturation accents on inactive states.
+- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
+
+## Product permissions
+
+Product can afford things brand surfaces can't.
+
+- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
+- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
+- Density. Tables with many rows, panels with many labels, dense information when users need it.
+- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
diff --git a/plugin/skills/impeccable/reference/product.md b/plugin/skills/impeccable/reference/product.md
index 47d6c1373..ccd31d2c1 100644
--- a/plugin/skills/impeccable/reference/product.md
+++ b/plugin/skills/impeccable/reference/product.md
@@ -1,60 +1,3 @@
-# Product family depth (Operate and Read surfaces)
+# Moved
 
-When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
-
-## The product slop test
-
-Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
-
-Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
-
-## Typography
-
-- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data.
-- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better.
-- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise.
-- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine.
-
-## Color
-
-Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor.
-
-- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these.
-- Accent color used for primary actions, current selection, and state indicators only, not decoration.
-- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface).
-
-## Layout
-
-- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography.
-
-## Components
-
-Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these.
-
-- Skeleton states for loading, not spinners in the middle of content.
-- Empty states that teach the interface, not "nothing here."
-- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style.
-
-## Motion
-
-- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography.
-- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else.
-- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load.
-
-## Product bans (on top of the shared absolute bans)
-
-- Decorative motion that doesn't convey state.
-- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong.
-- Display fonts in UI labels, buttons, data.
-- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals).
-- Heavy color or full-saturation accents on inactive states.
-- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
-
-## Product permissions
-
-Product can afford things brand surfaces can't.
-
-- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
-- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
-- Density. Tables with many rows, panels with many labels, dense information when users need it.
-- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
+Operate and Read depth lives in [operate.md](operate.md). The mode essentials are in SKILL.md. This stub remains because `PRODUCT.md` files with `register: product` and older links point here.
diff --git a/plugin/skills/impeccable/reference/typeset.md b/plugin/skills/impeccable/reference/typeset.md
index 819807f9e..c39fb6836 100644
--- a/plugin/skills/impeccable/reference/typeset.md
+++ b/plugin/skills/impeccable/reference/typeset.md
@@ -185,7 +185,7 @@ Use `ch` units for character-based measure (`max-width: 65ch`). Line-height scal
 
 #### Font Selection & Pairing
 
-The tactical selection procedure and the reflex-reject list live in [reference/brand.md](brand.md) under **Font selection procedure** and **Reflex-reject list** (loaded for brand-register tasks). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
+The tactical selection procedure and the reflex-reject list live in [new-work.md](new-work.md) (loaded for new identity work). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
 
 ##### Anti-reflexes worth defending against
 
diff --git a/plugin/skills/impeccable/scripts/context.mjs b/plugin/skills/impeccable/scripts/context.mjs
index 15829a157..c13990ee0 100644
--- a/plugin/skills/impeccable/scripts/context.mjs
+++ b/plugin/skills/impeccable/scripts/context.mjs
@@ -940,7 +940,7 @@ async function cli() {
     );
   }
   if (register) {
-    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md; \`reference/${register}.md\` has extended depth for substantial work.`);
+    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md.`);
   }
   const platform = extractPlatform(ctx.product);
   const nativeRefs =
diff --git a/skill/SKILL.src.md b/skill/SKILL.src.md
index f668c3e3d..4ff77e86a 100644
--- a/skill/SKILL.src.md
+++ b/skill/SKILL.src.md
@@ -52,7 +52,7 @@ Calibration for this provider:
 
 ## Registers
 
-Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode. PRODUCT.md's `register` field names the family (`brand` covers Persuade and Experience; `product` covers Operate and Read), and `reference/brand.md` / `reference/product.md` carry extended depth for the two families. <!-- rule:skill-visitor-mode -->
+Name the visitor's mode before designing; the page's grammar follows from it, and most ruined pages are one mode wearing another mode's grammar. The brief and the surface decide the mode; PRODUCT.md's `register` field survives only as a family hint (`brand` covers Persuade and Experience, `product` covers Operate and Read). Depth beyond the paragraphs below: [reference/new-work.md](reference/new-work.md) when inventing identity, [reference/operate.md](reference/operate.md) for substantial Operate and Read work. <!-- rule:skill-visitor-mode -->
 
 **Persuade** (landing pages, marketing, campaigns; design IS the product). The deliverable is an impression that stops the scroll, earns the click, converts. Spans every genre (tech, luxury, consumer); don't collapse them into one look. Briefs that imply imagery must ship real, verified imagery; a colored rectangle where a photo belongs reads as incomplete. New Persuade surfaces take their typeface procedure and reject list from [reference/new-work.md](reference/new-work.md). <!-- rule:brand-register-core -->
 
diff --git a/skill/reference/brand.md b/skill/reference/brand.md
index 929b82e5d..0f0184c0d 100644
--- a/skill/reference/brand.md
+++ b/skill/reference/brand.md
@@ -1,42 +1,3 @@
-# Brand family depth (Persuade and Experience surfaces)
+# Moved
 
-When design IS the product: brand sites, landing pages, campaign pages, portfolios, long-form content, about pages. The essentials live in SKILL.md (modes, craft floor) and, for new identity work, in [new-work.md](new-work.md); this file is extended depth for substantial brand work. Rules stated in those files are not repeated here.
-
-The register spans every genre. A tech brand, a luxury hotel, a restaurant, a band's album page, an agency portfolio. They share a stance (*communicate, not transact*) and diverge wildly in aesthetic. Don't collapse them into one look.
-
-## The aesthetic-lane test
-
-Before committing to moves, name the lane. A type-foundry specimen page is one lane; minimal-cool tech is another; acid-maximalism is another. Don't drift into editorial-magazine aesthetics on a brief that isn't editorial; a hiking brand with italic drop caps has the wrong register within the register. <!-- rule:brand-typo-pairing-voice -->
-
-Then the inverse test: in one sentence, describe what you're about to build the way a competitor would describe theirs. If that sentence fits the modal landing page in the category, restart.
-
-### Reflex-reject aesthetic lanes
-
-Currently saturated aesthetic families that have flooded brand surfaces. If a brief lands in one of these lanes without a register reason that *requires* it (a literal magazine, a literal terminal), it's the second-order training reflex: the trap one tier deeper than a reflex font pick. Look further. <!-- rule:brand-typo-reflex-reject-lanes -->
-
-- **Editorial-typographic.** Display serif (often italic) + small mono labels + ruled separators + monochromatic restraint. The fingerprint: three rule-separated columns, an italic serif headline, lowercase track-spaced metadata, no imagery.
-
-(Entries land and leave this list as families saturate and fade.)
-
-The reflex-reject lists apply to **new design choices**. When the existing brand has already committed to a font or a lane as part of its identity, identity-preservation wins.
-
-## Color
-
-- Name a real reference before picking a strategy; unnamed ambition becomes beige. <!-- rule:brand-color-named-reference -->
-- Palette IS voice. A calm brand and a restless brand should not share palette mechanics. <!-- rule:brand-color-palette-is-voice -->
-- Don't converge across projects. Each brand surface differentiates from the last. <!-- rule:brand-color-no-converge -->
-- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette. <!-- rule:brand-color-no-cultural-symbol -->
-
-## Layout
-
-- Asymmetric compositions are one option. Break the grid intentionally for emphasis. <!-- rule:brand-layout-asymmetric -->
-- Fluid spacing with `clamp()` that breathes on larger viewports. <!-- rule:brand-layout-fluid-spacing -->
-- For image-led briefs (hotels, restaurants, magazines, photography), full-bleed hero imagery with overlaid menu and centered headline is a canonical move; let the photograph be the design. <!-- rule:brand-layout-image-led-hero -->
-
-## Brand permissions
-
-Brand can afford things product can't. Take them.
-
-- Ambitious first-load motion. Reveals and typographic choreography that earn their place; one orchestrated page-load beats scattered micro-interactions, and some brands skip entrance motion entirely, which is also a voice. <!-- rule:brand-permission-first-load-motion -->
-- Single-purpose viewports. One dominant idea per fold, long scroll, deliberate pacing. <!-- rule:brand-permission-single-purpose-viewports -->
-- Art direction per section. Different sections can have different visual worlds if the narrative demands it. Consistency of voice beats consistency of treatment. <!-- rule:brand-permission-art-direction -->
+The Persuade and Experience essentials are in SKILL.md; the depth for inventing new identity (typeface procedure, reject list and lanes, color discipline, layout moves, permissions) lives in [new-work.md](new-work.md). This stub remains because `PRODUCT.md` files with `register: brand` and older links point here.
diff --git a/skill/reference/live.md b/skill/reference/live.md
index c084d6d21..715bb59f4 100644
--- a/skill/reference/live.md
+++ b/skill/reference/live.md
@@ -113,7 +113,7 @@ node {{scripts_path}}/live-insert.mjs --id EVENT_ID --count EVENT_COUNT --positi
 - `--position` ← `event.insert.position` (`before` | `after`)
 - Anchor flags ← `event.insert.anchor` (same mapping as wrap: id, classes, tag, text)
 
-The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. Load `brand.md` or `product.md` (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
+The scaffold has **no** `data-impeccable-variant="original"`. Variants are net-new HTML+CSS inserted at `insertLine`. For Operate/Read surfaces load `operate.md`; Persuade/Experience surfaces use SKILL.md's mode guidance plus `new-work.md` when the variant invents identity (freeform only, no action sub-command). Write all variants in one edit, then `--reply done`.
 
 For Svelte/SvelteKit targets, `live-insert.mjs` returns `previewMode: "svelte-component"` with `mode: "insert"`, `file` pointing at a temporary `node_modules/.impeccable-live/<id>/manifest.json`, `componentDir` pointing at the variant component files, and `sourceFile` pointing at the real `.svelte` route. Write each inserted variant as a real Svelte component (`v1.svelte`, `v2.svelte`, …) under `componentDir`. Insert variants must be non-empty net-new content with a single top-level root, no `data-impeccable-*` attributes, and CSS in each component's `<style>` block. Do **not** edit the route source during generation; the browser mounts the temporary component before/after the live anchor while the user cycles variants. On Accept, `live-accept.mjs` inserts the selected component markup into `sourceFile` immediately and deletes the temp session after the source write succeeds.
 
@@ -191,7 +191,7 @@ All three carry `fallback: "agent-driven"`. Follow **Handle fallback** below.
 
 ### 3. Load the action's reference
 
-If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded register reference (`brand.md` or `product.md`). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
+If `event.action` is `impeccable` (the default freeform action), use SKILL.md's shared laws plus the loaded mode depth (`operate.md` for Operate/Read; `new-work.md` when the variant invents identity). Do not load a sub-command reference. **Freeform is not a pass to skip parameters:** you still follow the composition budget and the freeform bias in **§7 Parameters** below. Sub-command files list MUST-have signature knobs; freeform has no such file, so sizing knobs from surface weight and primary axes is entirely on you.
 
 Any other `event.action` (`bolder`, `quieter`, `distill`, `polish`, `typeset`, `colorize`, `layout`, `adapt`, `animate`, `delight`, `overdrive`): Read `reference/<action>.md` before planning. Each sub-command encodes a specific discipline; skipping its reference produces generic output. Those files may require specific params; layer them on top of the §7 budget, not instead of it.
 
@@ -256,7 +256,7 @@ Instead, work from the brand:
 
 1. Read PRODUCT.md's Brand Personality words. What physical, spatial, or material experiences would embody those words if design were not involved? (A personality described as "specific, earned, unmistakable" evokes a hand-stamped letter, a numbered print, a watchmaker's loupe. A personality described as "restless, loud, unfiltered" evokes a concert poster, a spray-painted wall, a megaphone.)
 2. From those physical experiences, derive three visual directions that are genuinely different from each other AND from the current surface you're departing.
-3. Avoid the **reflex-reject lanes** in [brand.md](brand.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
+3. Avoid the **reflex-reject lanes** in [new-work.md](new-work.md). Don't trade one monoculture for another. If you find yourself reaching for "Swiss-grid" or "Terminal" or "Industrial-signage" by reflex, you are pattern-matching a catalog in your training data, not reading the brand. Start over from the personality words.
 4. Each direction must be expressible in one concrete sentence that names a real-world referent ("a museum exhibition label system for a contemporary art gallery" not "clean and minimal"). If your sentence contains only adjectives, it's not concrete enough.
 5. **While planning each direction, also name its 2–3 parameter knobs** (per the §7 budget table). The same principle as default mode: decide "what's tunable" during planning, not after writing the HTML. A departure-mode hero with 0 parameters is not "bold creative vision," it's a missed opportunity for the user to fine-tune the direction they pick.
 
diff --git a/skill/reference/new-work.md b/skill/reference/new-work.md
index 1e165fdb7..89c948b54 100644
--- a/skill/reference/new-work.md
+++ b/skill/reference/new-work.md
@@ -24,6 +24,10 @@ Plan a compact token system in your reasoning: palette, type, layout concept in
 
 Pick a color strategy before picking colors: Restrained (neutrals + one accent; the default when the visitor came to operate or read) / Committed (one saturated color carries 30-60% of the surface) / Full palette (3-4 named roles) / Drenched (the surface IS the color). Persuade and Experience surfaces have permission for the bolder strategies; take them when the brief allows. Dark vs. light is never a default: write one sentence of physical scene (who uses this, where, under what light, in what mood) and let it force the answer. The warm cream near-white body background is the saturated AI default; where the axis is free, pick a background that is a choice.
 
+- Name a real reference before picking a strategy; unnamed ambition becomes beige. <!-- rule:brand-color-named-reference -->
+- Palette IS voice: a calm brand and a restless brand should not share palette mechanics, and each new surface differentiates from the last. <!-- rule:brand-color-palette-is-voice -->
+- When a cultural-symbol palette is the obvious pull, reach past it. Let the cultural reading come from typography, imagery, and copy, not the palette. <!-- rule:brand-color-no-cultural-symbol -->
+
 ## Type and imagery for new Persuade and Experience surfaces
 
 Choose faces like objects from the brand's world; these training-data defaults mean you stopped looking: Fraunces, Playfair Display, Cormorant, Lora, Crimson, Newsreader, Syne, Space Grotesk, Space Mono, IBM Plex, Inter-as-display, DM Sans, DM Serif, Outfit, Plus Jakarta Sans, Instrument Sans. (For Operate and Read surfaces the opposite holds: system stacks and workhorse UI faces are legitimate and often correct.)
@@ -34,4 +38,10 @@ Imagery-implying briefs (food, travel, place, product, fashion) must ship real,
 
 AI-generated interfaces cluster around a few looks regardless of subject: warm cream + high-contrast serif + terracotta accent; near-black + one neon accent (acid green, cyan) + glowing edges; broadsheet-editorial hairlines + italic display serif + small tracked mono labels. All are legitimate when the brief calls for them; the brief always wins. Where the brief leaves the aesthetic free, landing in one of them means your self-check failed. Same one tier deeper: if someone could guess your aesthetic from the category alone, or from category-plus-avoidance, rework until neither answer is obvious.
 
+**Name the aesthetic lane, then test it.** Before committing to moves, say which lane this is (a specimen page, minimal-cool tech, acid maximalism...). Then the inverse test: describe what you're about to build the way a competitor would describe theirs; if that sentence fits the modal page in the category, restart. <!-- rule:brand-typo-pairing-voice --> Currently saturated lanes count as reflexes, not choices, when the brief doesn't require them; the flooded one right now is editorial-typographic (display serif, often italic, small mono labels, ruled separators, monochromatic restraint, no imagery). <!-- rule:brand-typo-reflex-reject-lanes -->
+
+## Persuade and Experience moves
+
+Layout: asymmetric compositions and intentional grid breaks are on the table; fluid spacing with `clamp()` that breathes on larger viewports; for image-led briefs, full-bleed hero imagery with overlaid navigation is a canonical move, letting the photograph be the design. <!-- rule:brand-layout-image-led-hero --> Permissions the Operate world doesn't get: ambitious first-load motion (one orchestrated page-load beats scattered micro-interactions; skipping entrance motion entirely is also a voice), single-purpose viewports (one dominant idea per fold, deliberate pacing), and art direction per section when the narrative demands it; consistency of voice beats consistency of treatment. <!-- rule:brand-permission-first-load-motion -->
+
 Before finishing, verify against SKILL.md's craft floor and run the detector; a bold page that ships mechanical defects is not done.
diff --git a/skill/reference/operate.md b/skill/reference/operate.md
new file mode 100644
index 000000000..c4a87272d
--- /dev/null
+++ b/skill/reference/operate.md
@@ -0,0 +1,60 @@
+# Operate mode depth (and Read notes)
+
+When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
+
+## The product slop test
+
+Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
+
+Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
+
+## Typography
+
+- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data. <!-- rule:product-typo-one-family -->
+- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better. <!-- rule:product-typo-fixed-rem-scale -->
+- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise. <!-- rule:product-typo-tighter-ratio -->
+- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine. <!-- rule:product-typo-line-length -->
+
+## Color
+
+Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor. <!-- rule:product-color-restrained-default -->
+
+- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these. <!-- rule:product-color-state-vocab -->
+- Accent color used for primary actions, current selection, and state indicators only, not decoration. <!-- rule:product-color-accent-only -->
+- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface). <!-- rule:product-color-second-neutral -->
+
+## Layout
+
+- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography. <!-- rule:product-layout-responsive-structural -->
+
+## Components
+
+Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these. <!-- rule:product-components-all-states -->
+
+- Skeleton states for loading, not spinners in the middle of content. <!-- rule:product-components-skeleton-loading -->
+- Empty states that teach the interface, not "nothing here." <!-- rule:product-components-empty-states -->
+- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style. <!-- rule:product-components-consistent-affordances -->
+
+## Motion
+
+- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography. <!-- rule:product-motion-quick-transitions -->
+- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else. <!-- rule:product-motion-state-not-decoration -->
+- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load. <!-- rule:product-motion-no-page-load-sequence -->
+
+## Product bans (on top of the shared absolute bans)
+
+- Decorative motion that doesn't convey state. <!-- rule:product-ban-decorative-motion -->
+- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong. <!-- rule:product-ban-inconsistent-components -->
+- Display fonts in UI labels, buttons, data. <!-- rule:product-ban-display-fonts-ui -->
+- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals). <!-- rule:product-ban-reinvented-affordances -->
+- Heavy color or full-saturation accents on inactive states. <!-- rule:product-ban-heavy-inactive-color -->
+- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first. <!-- rule:product-ban-modal-first-thought -->
+
+## Product permissions
+
+Product can afford things brand surfaces can't.
+
+- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
+- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
+- Density. Tables with many rows, panels with many labels, dense information when users need it.
+- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
diff --git a/skill/reference/product.md b/skill/reference/product.md
index 0c0ec4298..ccd31d2c1 100644
--- a/skill/reference/product.md
+++ b/skill/reference/product.md
@@ -1,60 +1,3 @@
-# Product family depth (Operate and Read surfaces)
+# Moved
 
-When design SERVES the product: app UIs, admin dashboards, settings panels, data tables, tools, authenticated surfaces, anything where the user is in a task. The essentials live in SKILL.md (modes, craft floor); this file is extended depth, written for Operate surfaces. Read surfaces (docs, guides, long-form) take SKILL.md's Read mode plus this file's typography and consistency rules; their prose measure and navigation matter more than component density.
-
-## The product slop test
-
-Not "would someone say AI made this." Familiarity is often a feature here. The test is: would a user fluent in the category's best tools (Linear, Figma, Notion, Raycast, Stripe come to mind) sit down and trust this interface, or pause at every subtly-off component?
-
-Product UI's failure mode isn't flatness, it's strangeness without purpose: over-decorated buttons, mismatched form controls, gratuitous motion, display fonts where labels should be, invented affordances for standard tasks. The bar is earned familiarity. The tool should disappear into the task.
-
-## Typography
-
-- **One family is often right.** Product UIs don't need display/body pairing. A well-tuned sans carries headings, buttons, labels, body, data. <!-- rule:product-typo-one-family -->
-- **Fixed rem scale, not fluid.** Clamp-sized headings don't serve product UI. Users view at consistent DPI, and a fluid h1 that shrinks in a sidebar looks worse, not better. <!-- rule:product-typo-fixed-rem-scale -->
-- **Tighter scale ratio.** 1.125–1.2 between steps is typical. More type elements here than on brand surfaces; exaggerated contrast creates noise. <!-- rule:product-typo-tighter-ratio -->
-- **Line length still applies for prose** (65–75ch). Data and compact UI can run denser; tables at 120ch+ are fine. <!-- rule:product-typo-line-length -->
-
-## Color
-
-Product defaults to Restrained. A single surface can earn Committed (a dashboard where one category color carries a report, an onboarding flow with a drenched welcome screen), but Restrained is the floor. <!-- rule:product-color-restrained-default -->
-
-- State-rich semantic vocabulary: hover, focus, active, disabled, selected, loading, error, warning, success, info. Standardize these. <!-- rule:product-color-state-vocab -->
-- Accent color used for primary actions, current selection, and state indicators only, not decoration. <!-- rule:product-color-accent-only -->
-- A second neutral layer for sidebars, toolbars, and panels (slightly cooler or warmer than the content surface). <!-- rule:product-color-second-neutral -->
-
-## Layout
-
-- Responsive behavior is structural (collapse sidebar, responsive table, breakpoint-driven columns), not fluid typography. <!-- rule:product-layout-responsive-structural -->
-
-## Components
-
-Every interactive component has: default, hover, focus, active, disabled, loading, error. Don't ship with half of these. <!-- rule:product-components-all-states -->
-
-- Skeleton states for loading, not spinners in the middle of content. <!-- rule:product-components-skeleton-loading -->
-- Empty states that teach the interface, not "nothing here." <!-- rule:product-components-empty-states -->
-- Consistent affordances across the surface. Same button shape. Same form-control vocabulary. Same icon style. <!-- rule:product-components-consistent-affordances -->
-
-## Motion
-
-- 150–250 ms on most transitions. Users are in flow; don't make them wait for choreography. <!-- rule:product-motion-quick-transitions -->
-- Motion conveys state, not decoration. State change, feedback, loading, reveal: nothing else. <!-- rule:product-motion-state-not-decoration -->
-- No orchestrated page-load sequences. Product loads into a task; users don't want to watch it load. <!-- rule:product-motion-no-page-load-sequence -->
-
-## Product bans (on top of the shared absolute bans)
-
-- Decorative motion that doesn't convey state. <!-- rule:product-ban-decorative-motion -->
-- Inconsistent component vocabulary across screens. If the "save" button looks different in two places, one is wrong. <!-- rule:product-ban-inconsistent-components -->
-- Display fonts in UI labels, buttons, data. <!-- rule:product-ban-display-fonts-ui -->
-- Reinventing standard affordances for flavor (custom scrollbars, weird form controls, non-standard modals). <!-- rule:product-ban-reinvented-affordances -->
-- Heavy color or full-saturation accents on inactive states. <!-- rule:product-ban-heavy-inactive-color -->
-- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first. <!-- rule:product-ban-modal-first-thought -->
-
-## Product permissions
-
-Product can afford things brand surfaces can't.
-
-- System fonts and familiar sans defaults (Inter, SF Pro, system-ui stacks).
-- Standard navigation patterns: top bar + side nav, breadcrumbs, tabs, command palettes.
-- Density. Tables with many rows, panels with many labels, dense information when users need it.
-- Consistency over surprise. The same visual vocabulary screen to screen is a virtue; delight is saved for moments, not pages.
+Operate and Read depth lives in [operate.md](operate.md). The mode essentials are in SKILL.md. This stub remains because `PRODUCT.md` files with `register: product` and older links point here.
diff --git a/skill/reference/typeset.md b/skill/reference/typeset.md
index d830f4107..4fae7848f 100644
--- a/skill/reference/typeset.md
+++ b/skill/reference/typeset.md
@@ -185,7 +185,7 @@ Use `ch` units for character-based measure (`max-width: 65ch`). Line-height scal
 
 #### Font Selection & Pairing
 
-The tactical selection procedure and the reflex-reject list live in [reference/brand.md](brand.md) under **Font selection procedure** and **Reflex-reject list** (loaded for brand-register tasks). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
+The tactical selection procedure and the reflex-reject list live in [new-work.md](new-work.md) (loaded for new identity work). The rest of this section covers the adjacent knowledge: anti-reflex corrections, system font use, and pairing rules.
 
 ##### Anti-reflexes worth defending against
 
diff --git a/skill/scripts/context.mjs b/skill/scripts/context.mjs
index 15829a157..c13990ee0 100644
--- a/skill/scripts/context.mjs
+++ b/skill/scripts/context.mjs
@@ -940,7 +940,7 @@ async function cli() {
     );
   }
   if (register) {
-    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md; \`reference/${register}.md\` has extended depth for substantial work.`);
+    parts.push(`REGISTER: \`${register}\` (family hint: brand = Persuade/Experience surfaces, product = Operate/Read). Derive the visitor's mode per SKILL.md.`);
   }
   const platform = extractPlatform(ctx.product);
   const nativeRefs =
diff --git a/tests/context.test.mjs b/tests/context.test.mjs
index a71844d2d..2a9f69903 100644
--- a/tests/context.test.mjs
+++ b/tests/context.test.mjs
@@ -839,7 +839,7 @@ describe('context.mjs CLI', () => {
     const res = spawnSync(process.execPath, [SCRIPT_PATH], { cwd: scratch, encoding: 'utf8', env: { ...process.env, IMPECCABLE_NO_UPDATE_CHECK: '1' } });
     assert.equal(res.status, 0);
     assert.match(res.stdout, /REGISTER: `brand`/);
-    assert.match(res.stdout, /reference\/brand\.md/);
+    assert.match(res.stdout, /Derive the visitor's mode per SKILL\.md/);
   });
 
   it('falls back to a generic register directive when no register field is present', async () => {