mirror of
https://github.com/pbakaus/impeccable.git
synced 2026-09-11 21:57:14 +03:00
f704fca29c73871417c19453aa8553852dec0bb6
14
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
  Paul BakausandClaude Opus 5
|
121602079c |
Deliver the report as its own step; retune the lineup
Two failures the trace test found were structural, not model quirks. critique.md described the report's format and then went straight to writing a temp file, with no step saying to output the report. gemini-3.6-flash and luna both responded by bundling heredoc, snapshot write, trend read, and cleanup into one bash call and stopping, leaving a perfect archive nobody had read. A "Deliver the Report" step now precedes persistence, and persistence describes itself as a copy of what was already sent. gemini-3.6-flash failed three consecutive runs before this and its failures afterward all show the report reaching chat. The close is also step 6 of the persistence list rather than a section after it, since the same shape is what fixed delivery. Lineup: gpt-5.6-luna and deepseek-v4-flash out, gpt-5.6-terra in at reasoningEffort high (IMPECCABLE_SKILL_BEHAVIOR_EFFORT overrides), gemini 3.5 to 3.6. Provider options resolve from the model object inside the harness so the 21 runTurn call sites are untouched. Verified the effort actually reaches the API rather than being silently dropped. The Gemini bump was not cosmetic: 3.5-flash passed critique closes twice and 3.6-flash then failed three times against identical text. A version bump inside one family changed the outcome, so the README now treats cross-version carryover as unmeasured. Known floor, recorded: critique closes is flaky on gemini-3.6-flash, 1 run in 3. Two structural attempts moved it from consistently failing to intermittently passing and then stopped paying. claude-sonnet-5 and gpt-5.6-terra are clean. Prepared with AI assistance (Claude Code). Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
Paul BakausandClaude Opus 5
|
ebc63f071a |
Fix critique's close on the right mechanism
The earlier fix in this branch was built on a wrong diagnosis. It assumed a
structured question hides any prose sharing its message, so it split report and
question across two turns. A controlled check showed prose before a question
renders fine; what hides a report is emitting it AFTER the question. The split
therefore fixed nothing and introduced a worse failure: a turn that ends on the
report is a turn that ends, and the questions never arrived at all.
Persistence returns to main's ordering, byte for byte, and the boundary prose is
gone. What replaces it is a position rule: the question is the last thing in the
response.
The trace test added here found two failures beyond the reported one. Critique
can fail to land in three ways, and they are now all asserted:
1. Question emitted before the report, hiding it behind the picker.
2. No close at all: no questions and no skip line, so polish inherits nothing.
3. Report authored into the persistence heredoc and never written to chat,
leaving a perfect snapshot and a user who sees nothing.
Mode 3 predates this branch entirely. Persistence step 1 now says the temp file
is an archive copy, not delivery.
The Codex final-question gate is promoted out of its <codex> fence, where it was
stripped for three of four providers, and the skip branch is now a countable
threshold (fewer than 3 Priority Issues) rather than a judgment call.
Known floor, recorded in the suite README: gpt-5.6-luna passes 1 run in 6 and
deepseek-v4-flash is flaky. claude-sonnet-5 and gemini-3.5-flash are consistent.
Prepared with AI assistance (Claude Code).
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
||
|
Paul BakausandClaude Opus 5
|
0e5c6cbe17 |
Keep critique's report out of the question's message
The critique report and the AskUserQuestion call shipped in one assistant message, so the report stayed hidden until the user answered the picker and the command read as if it had never run. Reorder critique's persistence steps so the temp-file cleanup runs after the report and trend line are sent. That cleanup now ends the message carrying the report, leaving the questions to open a fresh one. Both critique.md and overdrive.md state the constraint and why it exists, so the ordering is not an unexplained sequence a model can optimize away. Overdrive additionally moves its direction descriptions inside the question options, where the user is actually reading them. Also fix the ask_instruction splices. The placeholder is a complete sentence, but five call sites spliced it mid-sentence and shipped text like "stop and STOP and call the AskUserQuestion tool to clarify. before expanding it". Every call site is now sentence-initial and the twelve lowercase provider values are capitalized to match, with a comment in utils.js pinning the contract. Record a workflow-contract baseline for the current model lineup. The two failures seen while validating this change are pre-existing: bolder refinement fails on deepseek-v4-flash identically with bolder.md reverted to HEAD, and redesign replaces DESIGN is flaky on assertions driven by new-work.md, which this change does not touch. Prepared with AI assistance (Claude Code). Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
Paul BakausandClaude
|
9213e1bcd1 |
Fix stale section pointer and critique score denominators
Two true positives from the Bugbot review on PR #397. document.md seed mode told the agent to run "Select one direction" for paths A, D, or E. new-work.md has neither that heading nor the A/D/E lettering since the workshop was restructured into named subsections, so a literal read could skip the world-and-surface flow entirely. Point at "Create or replace the visual world" and "Commit the world" instead. critique.md let the heuristic table renormalize to an applicable maximum when heuristics are scored n/a, but the report template hardcoded ??/40, the rating bands only mapped raw numbers out of 40, and the persisted meta carried total_score with no denominator. Trends could silently compare 24/32 against 30/40 as if they were the same scale. The template now prints the applicable max, the bands fall back to percentages for partial sets, the snapshot records max_score and na_heuristics, and the trend line states its denominator or breaks it out per run when they disagree. critique-storage.mjs serializes frontmatter key-agnostically, so the new keys need no code change. Co-Authored-By: Claude <noreply@anthropic.com> |
||
|
Paul BakausandClaude Fable 5
|
7557935fdb |
Expand concept system: modes, ratings, re-roll, breadth strategy
Catalog: mode-aligned staging surfaces (persuade/operate/read/experience), star ratings on approvals feeding challenger draw weights, family retirements, authoring strategy and territory guide, rework and breadth authoring rounds, composition mining from rejected worlds. Seed: six challengers (two per tier), --reroll chains, --mode staging filter, rating-weighted draws. New-work: Present/visualize/re-roll flow, image-gen requirement, register-neutral vocabulary. Pipeline: per-mode staging prompts with split frames, hero-from-board reference generation, render-safety guards. Labs: ratings UI, unrated filter, mode chips, composition approve-guard. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> |
||
|
Paul Bakaus
|
2b1f36c43e |
Add concept world catalog and review workflow
AI-assisted: prepared by Codex at Paul's request. |
||
|
Paul BakausandClaude Fable 5
|
2c62f0f4f9 |
de-SaaS the skill: mode-aware rules, neutral runtime injections, diversified examples
Fix batch from the visitor-mode bias audit. The skill's four modes (Persuade / Operate / Read / Experience) now reach the places that were still hard-coded to a SaaS-marketing default: - palette.mjs: rewrote 45 seed blurbs in material/world terms. The 29 tech-tool-world moods (13 Linear-indigo variants, 6 Figma-era, 5 climate-tech, 3 fintech, 2 Glossier DTC, incl. seed-201's docs-page CTA red) lose all company names and product-category words; Aesop trimmed from 17 blurbs to 4 and Klim from 7 to 4, excess rewritten as unnamed material terms. Also carries the earlier bg-block rewrite (brand refs out of the composition doc). - init.md: register explainer now names the four modes and the family each belongs to (stored value stays brand/product for compatibility); Conversion & proof interview + PRODUCT.md section gated to Persuade surfaces only (Experience/Read get no CTA/belief-ladder/proof). - critique.md: Nielsen heuristics 7 and 10 may score n/a on Persuade and Experience surfaces, total renormalized to the applicable max, snapshot records which were n/a; working-memory examples diversified beyond dashboard/pricing anatomy. - Register headers in bolder/delight/quieter/colorize/layout/animate/ typeset renamed from Brand:/Product: to Persuade + Experience: / Operate + Read:; typeset and layout gain one Read-specific sentence (steady reading measure; navigable linearity). - animate.md: plan checklist and implementation order lead with feedback and transitions; the single entrance moment comes after, scoped to modes that invite it. - codex.md: mock inventory says "primary-action treatment (when the surface has one)" instead of assuming a CTA. - delight.md: loading/empty-state/console-egg examples diversified beyond SaaS; streaks/badges scoped to Operate surfaces with recurring tasks. - distill.md: step-removal and next-action lines neutralized away from signup/checkout/CTA vocabulary. - document.md: canonical button label GET STARTED -> SAVE CHANGES; signature components gain a non-marketing example. - antipatterns registry: single-font rule renamed to "Single font without hierarchy" with a description that permits one family when weight/size contrast carries hierarchy. Staged provider copies regenerated via build:skills:release for the touched files only. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> |
||
|
Paul Bakaus
|
bcd16381cf | harden critique so that it runs in sub-agents more often in harnesses other than Claude and Codex | ||
|
Paul BakausandClaude Opus 4.8
|
f7f2bfc800 |
feat(detector): deprecate --fast (now a no-op, full scan always)
Since the jsdom removal the static HTML/CSS analysis is fast (~4ms/file) and covers every rule, so the regex-only `--fast` path only loses coverage (it ran ~10 of 41 rules) for no real speed win. It's a foot-gun: a `--fast` scan can read "clean" because most rules silently don't run. Deprecate gracefully rather than hard-remove: the flag is still accepted (so existing CI scripts don't break) but ignored, with a one-line stderr notice, and the full scan always runs. Dropped from --help and the example. Removed the `--fast` suggestion from the many-files warning and from critique.md's scan guidance. Ships to users via a CLI release (npm) and rides the next skill release in the bundled detector. Tests updated to assert the deprecation behavior. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
 
|
9ffd3211d5 |
Neo Kinpaku design system + Live Mode v3 (#169)
* Add neo kinpaku design system page * skill: rip out baked-in category recipes and saturated-default motion tropes Programmatic bias mining (impeccable-evals) traced four major defects back to specific lines in this skill that contradicted SKILL.md's own first-order-reflex warning: - brand.md "Pairing and voice" prescribed four category→aesthetic recipes (editorial → serif+sans, tech/dev/fintech → tight tracking, consumer/food/travel → script/display serif, creative → rule-break). These directly drove OpenAI's 76% extreme-negative letter-spacing on tech briefs and Anthropic/Google's 28-34% italic-serif-display slop on editorial/food briefs. Replaced with one sentence: the shape depends on the brand, not on the brand's category. - brand.md "Brand permissions" had "Typographic risk. Enormous display type, unexpected italic cuts, mixed cases, hand-drawn headlines, a single oversize word as a hero." — a four-for-one slop driver behind 97% OpenAI comically-large H1, 42% bad-SVG illustration, and the editorial-italic slop. Deleted outright. - typeset.md and teach.md repeated the same category recipes; trimmed to the principle without the recipe. - SKILL.md Typography: added a hard hero-H1 ceiling (clamp() max ≤ 6rem ≈ 96px), with a <codex> block to make it explicit since OpenAI over-indexes here (97% ≥128px vs 24% for Anthropic). - animate.md, bolder.md, brand.md: removed "staggered reveals" and "scroll-triggered transitions" as the prescribed default ambitious motion. By 2026 that's the saturated AI tell, not a choreography. Reserved stagger for legitimate list-sibling rhythm. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * skill: anti-cream + codex-specific defect bans + universal slop bans Second pass after measuring more biases against the eval corpus. - SKILL.md Color: explicit "cream/sand/beige body bg is the saturated AI default of 2026" rule. Tone down the "tint every neutral" line so it doesn't read as "default to warm-tinted near-white" (which OpenAI hits at 74% and Anthropic at 31%-47%). - SKILL.md Absolute bans: add universal bans for two slop patterns detected at 55-95% across providers — tiny uppercase tracked eyebrow above every section (the 2023-era kicker that's now AI grammar) and numbered section markers (01/02/03). Also explicit "text that overflows its container is the universal defect on tablet/mobile." - SKILL.md Absolute bans → <codex> block: ban the GPT-specific defects Paul annotated repeatedly — `border:1px solid` + soft-wide-shadow (≥16px blur) "ghost cards", `border-radius:32px+` over-rounding, hand-drawn/sketchy SVG illustrations (loose-sketch / *-sketch classes, feTurbulence paper-grain filters), repeating-linear-gradient stripes, "X theater" AI-slop copy phrases. - SKILL.md Motion → <gemini> block: the image :hover transform tell (38% Google skill-on rate). Hover effects on images add no info; the image isn't an action target. Animate card chrome, not the image. - SKILL.md Typography: hard display letter-spacing floor ≥-0.04em (OpenAI defaults to -0.075em → cramped). Existing hero ceiling <codex> block extended with the letter-spacing rule. - codex.md Step A example: stop seeding "warm-grounded (deep oxblood + cream)" as the warm-palette template, which primes the cream default. - colorize.md Tinted backgrounds: stop printing the literal cream recipe `oklch(97% 0.01 60)`; replace with brand-anchored guidance. - document.md examples: warm-ash-cream → cool-paper so the example doesn't seed cream as the canonical neutral example. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * skill: universal anti-slop bans + contrast/font-count/all-caps-body rules Third pass after measuring the rest of the cross-provider matrix: - Color: explicit "Verify contrast" rule. Low-contrast text fires at 68% across all providers skill-on (90+% off). The most common failure is muted gray body on a tinted near-white; light-gray-for- elegance is named as the single biggest cause of unreadable AI pages. - Typography: max-3-font-families rule. Overused-fonts (>4 families) fires at 28% Anthropic / 36% Google / 0% OpenAI skill-on; >50% off. Also: universal "no all-caps body copy" (moved from brand-only ban to Shared design laws since product-register also overuses caps). - Copy: anti-aphoristic-cadence ban targets Anthropic's signature "X. No Y." / "X. Just Y." voice (63% skill-on copy-slop rate, 77% off — the worst rate in the matrix). Once-is-voice / three-or-more- is-tell framing per the runner's copy-slop detector. - Copy: anti-SaaS-buzzword-string ban with the literal phrase list the detector watches for (streamline/empower/supercharge, trusted- by-leading, best-in-class/enterprise-grade/cutting-edge, etc). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * skill: strengthen anti-cream rule across full warm-neutral band Smoke validation showed the cream fix worked for Google + OpenAI but Anthropic Sonnet italian-restaurant still shipped `--paper: oklch(90% .018 88)` — cream just outside the L≥95% band the rule cited. Broaden the rule: - Band: OKLCH L 0.84-0.97, C < 0.06, hue 40-100 (was 95-97% / 60-95). - Name the token-name tells explicitly (paper / cream / sand / bone / flour / linen / parchment / wheat / biscuit / ivory) — the model defaults to one of these regardless of what hex it lands on. - Call out the specific brief patterns ("warm, traditional, family- coastal-Italian" / "editorial-restraint") that the model translates into cream by reflex. Then provide three explicit non-cream options: saturated brand color, true off-white at C=0, or darker mid-tone. Warmth in the brand is carried by accent + typography + imagery, not by body bg. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * v3.2.0: skill bias-fix release Bumps version from 3.1.1 to mark the four-commit skill cleanup that rips out baked-in category recipes (brand.md), saturated-default motion tropes (staggered reveals everywhere), the cream/sand body-bg AI tell, codex-specific defects (1px+wide-shadow, over-rounding, hand-drawn SVGs, stripes, X-theater copy), the extreme-letter-spacing default, and universal slop bans (all-caps eyebrow on every section, numbered-section markers, all-caps body, font-family-count > 3, aphoristic copy cadence, SaaS buzzword strings). Plus a hard hero-H1 ceiling (clamp() ≤6rem) and a Gemini-specific image:hover transform block. Validated against ~190 post-fix samples — see impeccable-evals biases tab for per-provider deltas. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * drop "no pure black/white" rule entirely The rule was contested in the design world and causing more damage than good — pushing every page into the tinted-near-white default which is the cream/sand AI tell we already explicitly ban elsewhere. Vercel, SVKMS, Brutalist sites, et al. use pure black/white successfully; the skill shouldn't second-guess that. Skill markdown deletions: - SKILL.md Color: drop the "Never use #000 or #fff" bullet. - color-and-contrast.md: drop the "Never Use Pure Gray or Pure Black" subsection, the "Never pure black" table-row prescription, and the "Avoid: Using pure black for large areas" bullet. - colorize.md: drop the "NEVER use pure black or pure white for large areas" bullet. - polish.md: drop the "Tinted neutrals: No pure gray or pure black" half of the bullet (the gray-on-color bullet survives). Detector code (cli/engine): - registry/antipatterns.mjs: remove the `pure-black-white` entry. - rules/checks.mjs: remove the three `findings.push({ id: 'pure-black-white', ... })` emit points (inline #000 bg, Tailwind bg-black class, plain-HTML scan path). - engines/regex/detect-text.mjs: remove the two pure-black-white regex rules (CSS `background: #000…` + Tailwind `bg-black`). - detect-antipatterns-browser.js: regenerated via scripts/build-browser-detector.js. Tests: - detect-antipatterns-fixtures.test.mjs: invert the assertion that pure-black-white fires; expect it to NOT fire post-v3.2. Drop the Tailwind bg-black-opacity edge-case test (no longer relevant). - detect-antipatterns.test.js: drop the standalone "detects pure- black-white in styled-components" test and remove pure-black-white from the multi-detector assertions in PricingCard, globals.css, and GlobalStyle.tsx tests. 166 bun tests pass; 24 node fixture tests pass. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * skill: strip example patterns from copy rules, strengthen gemini block v3.2 rerun validation surfaced two issues: 1. Copy-slop detector fires more on Gemini under v3.2 (48% → 84%) than under no-skill baseline. Root cause: the anti-aphoristic-cadence rule printed the literal "X. No Y." / "X. Just Y." patterns as examples, and Gemini imitated them as the recommended voice. Same recipe-becomes- bias trap we hit with brand.md:116's "Enormous display type, unexpected italic cuts, mixed cases, hand-drawn headlines" enumeration. Fix: describe the cadence as a rhythm ("serious statement, then punchy short negation") without printing literal patterns. Buzzword list trimmed to a single inline phrase family rather than quoted strings. 2. Gemini image:hover transform Gemini-tell hadn't dropped (31% off → 32% v3.2). Strengthen the <gemini> block: explicit "Never animate <img> elements on hover", call out the Tailwind group-hover:scale / group-hover:rotate / group-hover:translate parent-hover patterns by name (Gemini was reaching for these via Tailwind even though the prior text talked about :hover on the image directly). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * skill: simplify context loading and inline register directive Replaces load-context.mjs's JSON output with a tight markdown block from the renamed context.mjs. The script now extracts PRODUCT.md's `## Register` field and appends a `NEXT STEP:` directive naming the matching reference (brand.md / product.md), which moved Gemini from skipping the register load entirely to honoring it. Drops the `.impeccable.md` auto-migration; makes IMPECCABLE_CONTEXT_DIR a lazy escape hatch consulted only when the default paths come up empty. Setup is now four bullets in one list. The DESIGN.md nudge is gone; in its place, a "familiarize with the existing design system" step that calls out CSS / tokens / running app as authoritative sources alongside DESIGN.md. The standalone `### Register` H3 stays for the cascade rules (task cue → surface → register field). New LLM-backed test suite at tests/skill-behavior/ runs five scenarios against claude-haiku-4-5, gpt-5.4-mini, and gemini-3.1-flash-lite via Vercel AI SDK. Captures real tool traces, asserts on context.mjs calls, brand.md loads, and teach.md fallback. Skips cleanly when API keys are unset. 13-14/15 pass; only stable failure is the v3.2.0-era gpt-mini S4 "don't re-run" regression. Adds @ai-sdk/google as devDep and the test:skill-behavior npm script. Touches em-dashes in skill/SKILL.md and four reference files so `bun run build:skills` passes its skill-prose validator. teach.md and document.md drop their "re-run the loader to refresh session cache" steps since the agent's own write is now the freshest source. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * skill: merge orphan reference files into command sub-skills + inline S-tier invariants Two related restructurings: 1. SKILL.md now carries the cross-domain invariants that catch defects in any project (contrast/placeholder/gray-on-color, similar-font pairing, text-wrap, tabular-nums, centered-stack default, Flex/Grid choice, auto-fit grids, semantic z-index, reduced motion, stagger vs section-fade, premium motion materials, focus-visible, placeholders-aren't-labels, dropdown overflow trap, button/link copy). Greenfield-only rules (theme picking, color strategy, tinted neutrals) live under "New projects only". 2. Reference files merged into their command counterparts: - spatial-design.md -> layout.md - motion-design.md -> animate.md - color-and-contrast.md -> colorize.md - responsive-design.md -> adapt.md - ux-writing.md -> clarify.md - typography.md -> typeset.md (bolder.md redirected) - cognitive-load.md + heuristics-scoring.md + personas.md -> critique.md craft.md and shape.md "load references" lists updated to new file homes. interaction-design.md stays standalone (no 1:1 command verb). Net: 36 -> 27 reference files. Same content, fewer files, no orphaned reference loaded only from craft.md. Also extends the routing rules: if the user's first word doesn't match a command but the intent clearly maps to one, load that command's reference and proceed as if invoked. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * skill: add sub-command + existing-project scenarios; move sub-command load to step 2 Adds three new LLM-backed scenarios to tests/skill-behavior: - S6: `/impeccable polish` → loads polish.md - S7: `/impeccable audit` → loads audit.md - S8: existing SvelteKit project (PRODUCT.md + DESIGN.md + src/app.css + src/lib/components/*.svelte + src/routes/+page.svelte) → agent reads at least one project code file to understand the existing design system S6/S7 surface a real model-floor: gpt-5.4-mini reads brand.md, reads the target index.html, and just does the polish/audit without ever loading the sub-command reference. Stronger SKILL.md wording didn't move it. Captured in the README baseline as a known weakness. Claude and Gemini honor the load reliably. To fix Gemini on S6/S7, sub-command reference loading is now Setup step 2 (right after context.mjs), not step 4 — placing it before the model gets focused on "doing the work". Step 3 (design-system familiarization) is tightened to require at least one project code read even when a sub-command reference loads in step 2, so Claude doesn't laser-focus on the sub-command flow and skip the broader exploration. Two new fixtures: MINIMAL_LANDING_HTML (a tiny static landing page for S6/S7) and SVELTE_PROJECT_FILES (a minimal SvelteKit scaffold with tokens, components, and a routes/+page.svelte for S8). Both designed to look real enough that agents treat them as production code. Suite is now 24 tests across three providers; baseline is 21-22/24, with the stable failures being gpt-5.4-mini scenarios 6 and 7. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * skill: add reveal-animation safety rule (must enhance, not gate visibility) Class-triggered visibility transitions pause on hidden tabs and headless renderers. The italian-restaurant smoke produced a build where 2 sections shipped opacity:0 because the CSS transition never advanced past currentTime=0 (timeline paused). Added one-liner under Motion to prevent the antipattern: reveals must enhance an already-visible default, never gate content visibility on a class-triggered transition. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * skill: restore prescriptive cream/sand/beige paragraph Bisection across 5 historical skill commits on Gemini 3.5 flash fast lane n=3 found that |
||
|
Paul Bakaus
|
bc1894889e |
Improve critique skill reliability
- add provider-specific block compilation and tests - bundle detector scripts for skill critique runs - harden critique orchestration, browser handling, and storage |
||
|
|
93a13f9882 |
Critique persistence: per-run snapshots, ignore list, polish reads as signal (#153)
* critique-storage: new helper for per-run snapshot persistence Adds skill/scripts/critique-storage.mjs with: - slugFromTarget(): mechanically derive a stable slug from a resolved file path or URL (NOT from the user's natural-language phrasing), so the same target lands in the same stream across runs even when dev-server ports drift or the user phrases it differently. - writeSnapshot(): writes .impeccable/critique/<timestamp>__<slug>.md with a small YAML frontmatter (timestamp, slug, target, total_score, p0_count, p1_count) plus the report body. - readLatestSnapshot(): newest snapshot for a slug, used by polish. - readTrend(): last N frontmatter entries for a slug, used by critique to print the score trend line. - readIgnoreList(): non-empty non-comment lines from ignore.md, the ONLY input critique consumes from prior runs. No separate index.json. The snapshot files are the single source of truth; trend reader globs them and parses frontmatter. Deleting a snapshot removes it from the trend cleanly with no orphan rows. CRITIQUE_DIR constant + getCritiqueDir / getCritiqueIgnorePath added to impeccable-paths.mjs alongside the existing live-dir helpers. 19 unit tests in tests/critique-storage.test.mjs cover slug stability, URL and file inputs, round-trip read/write, trend filtering by slug, and ignore-list parsing. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * critique: persist snapshot per run, respect ignore.md Two new steps wired into the critique flow: - Setup: Resolve Target and Load Ignore List. Before gathering assessments, resolve the user's natural-language target ("the homepage") to a concrete artifact, compute the slug via critique-storage.mjs, and read ignore.md. Matching findings drop silently from the report. This is the only prior-run input critique consumes; anchoring on prior findings would defeat independent assessment. - Persist the Snapshot. After the report is finalized (before Ask the User), write it to .impeccable/critique/<ts>__<slug>.md with structured frontmatter, then surface a one-line trend ("Trend for index-astro: 24 → 28 → 32") and the written path. First run says "no trend yet". Persistence is fire-and-forget; failures print and move on rather than blocking the rest of the flow. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * polish: read latest matching critique as fix backlog When polish is invoked after critique on the same target, the critique's P0/P1 findings are the right backlog; don't re-derive them. Adds a Setup step that resolves the target, computes the slug via critique-storage.mjs slug, and reads the latest matching snapshot via critique-storage.mjs latest. Found → use those P0/P1 items as the polish backlog and mention the snapshot path. Not found → proceed independently from a clean slate. Explicitly does NOT read snapshots for other targets (cross-target context is pollution). Explicitly does NOT cascade to atomic moves (bolder, quieter, clarify, animate, etc.); those act on a specific selection where the page-level critique would be noise. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * gitignore: .impeccable/critique/, opt ignore.md back in Per-run critique snapshots are local artifacts (same precedent as .impeccable/live/sessions/), but ignore.md carries user-curated deferrals that may be worth sharing across a team. Negate-pattern keeps it trackable while the snapshot files stay local. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * polish: reframe prior critique as additional signal, not backlog Three corrections to the previous polish.md addition: - "Polish is usually invoked after critique" is wrong; people polish without ever running critique. Dropped the presumption. - "This is the only command that auto-reads prior critique" leaks cross-command scope into polish's reference file. Dropped. - Treating critique findings as THE polish backlog biased polish to only fix what critique flagged, skipping its own checklist. The critique is one input among many; fold its P0/P1 items into the polish list, then do the normal pass. Now lives as a short item 4 in Pre-Polish Assessment ("Pull in any prior critique — optional signal") instead of a top-level Setup section. Less prominent, doesn't presume invocation order. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * critique-storage: drop the ignore subcommand, read ignore.md directly The ignore-list helper did nothing the model can't do inline: read a markdown file, skip blank and #-prefix lines. It added a tool roundtrip for no real value. Other helpers earn their keep by doing work the model can't trivially do (path normalization, filename generation, glob + frontmatter parsing); ignore-list did not. Removed: - `ignore` CLI subcommand - readIgnoreList() module export + its tests - getCritiqueIgnorePath() from impeccable-paths.mjs (now dead code) Critique.md step 3 now just says "read .impeccable/critique/ignore.md if it exists" and explains the format inline. Simpler. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * critique-storage: caller meta cannot override timestamp or slug Spotted by Cursor Bugbot on the PR. writeSnapshot built frontmatter as { timestamp, slug, ...meta } so a caller-supplied meta blob (parsed from the IMPECCABLE_CRITIQUE_META env var) could silently clobber the computed timestamp and slug. The filename keeps the computed values, so the frontmatter would drift from the filename and readTrend would attribute scores to wrong timestamps with no visible error. Swap to { ...meta, timestamp, slug } so internal values always win. Add a regression test that passes corrupt meta and asserts the frontmatter still matches the filename. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
e7e923c4ef |
Skill + craft cleanup, detector hardening, native subagent pipeline (#152)
* skill: drop quality tiers, keep the real brand-craft guardrails Codex's craft/brand pass introduced fast/ship/showpiece "quality bars" plus brand-specific build gates, asset ledgers, sub-agent review, and self-graded fallback labels. In practice those tiers became escape hatches rather than craft pressure: the final output should always be 10/10, and the real decision points are splashiness and maximalism, not quality. Removed: - All quality-bar / showpiece / fast / ship framing in shape.md and craft.md - Standalone Brand Direction (#4) and Asset Requirements (#10) sections in shape's brief; renumbered back to 1-10 - The Brand hard rules section in brand.md (folded its real prohibitions into the existing Imagery and Brand bans sections) - Brand-specific build-gate item, mock-fidelity bullet, production-bar bullet, present-step bullet in craft.md - Asset ledger ceremony in craft Step 4 - Review-only sub-agents and "self-reviewed fallback, not independently validated" machinery in craft.md and polish.md - The For brand surfaces, assess hard failures subsection in polish.md and the brand checklist row - tests/brand-showpiece-reference.test.mjs (and its package.json wiring) Kept (the real nuggets): - Asset-substitution prohibition: image-led briefs ship real/generated assets or canvas/SVG/WebGL, not generic CSS panels, cards, bullets, or copy - Repeated tiny uppercase tracked kicker labels as a brand ban - Detector/QA output is defect evidence only, never proof of quality - "What visual assets are real content here?" discovery question - Inspect each major section individually for brand and long-form work - repeated-section-kickers detection rule + fixture - CLI improvements (JSON to stdout, -json/-fast aliases, severity field) - critique.md: npx impeccable detect --json fix Harness output dirs refreshed via bun run build. Full test suite (186) passes. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * skill: strip gate ceremony; require shape pause; allow compact briefs The setup gate table and IMPECCABLE_PREFLIGHT banner pushed every craft run through ritual restatement (PRODUCT.md → original prompt → round 1 → round 2 → 70-line "confirmed brief" → critique → summary, all saying the same thing). Replaced with imperative prose that still demands the same work but skips the user-facing telemetry. Specifically: SKILL.md - Drop the Setup gate table and IMPECCABLE_PREFLIGHT banner. - Keep the imperative steps explicitly: load context, identify register and load brand.md or product.md, AND load the matching command reference (craft.md / shape.md / etc.) when a sub-command is invoked. The command-reference step is non-negotiable; without craft.md loaded the agent skips the shape-and-confirm pause. craft.md - Drop the Build Gate / Craft Contract formal sections; replace with one paragraph stating prerequisites. - Step 1 explicitly requires ending the response after presenting the shape output; the user must confirm before any code lands. Allows a compact 3-5 bullet brief when the prompt + PRODUCT.md already pin direction (full 10-section structure reserved for genuinely ambiguous tasks). - Step 3 image gate skips silently when image generation isn't natively available; no user-facing announcement. - Step 6 explicitly legitimizes "first pass clean, shipping" as a valid endpoint and bans inventing fake defects to demonstrate iteration. shape.md - Cap discovery at 1 round by default; second round only when first leaves material gaps. - Adds an "assert-then-confirm, not menu-with-escape" rule: when PRODUCT.md and the prompt make one option obvious, name it and ask for confirm or override instead of enumerating "Restrained / Committed / Or something else?" as a real choice. - Phase 2 brief has two forms now: compact (default for clear briefs) and full structured (genuinely ambiguous). Open Questions can't double as leading-with-Recommend; if you'd write "Recommend: X", decide X. - Image gate same as craft.md. Validated end-to-end with a Haiku skill-on observability run: agent loads craft.md plus the brief's recommended implementation refs, pauses for one productive question (accent color, trace fidelity, CTA), and ships an artifact with zero side-tab violations vs. the original v1 baseline. Cost trades up modestly for that quality. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * craft.md Step 6: Reading the screenshot is the inspection, not taking it A v4 eval run took 4 targeted screenshots (hero, mobile, tablet, query-section) and then never Read any of them back. The agent treated browser_screenshot itself as "I inspected" and shipped without the multimodal feedback loop ever closing. Detector caught the resulting slop (5+ side-tab violations) on adjacent runs that did the same thing. Step 6 now spells out the pattern explicitly: take the screenshot, then Read the resulting PNG so its image content enters the conversation as multimodal input, then critique what you actually see in the image. With a check: "if your critique could have been written without looking at the image, you didn't look at the image." Validated with v5b: agent took 6 screenshots, Read all 6 back, and shipped with zero detector findings (vs the previous greenfield runs that hit 1-12 findings each). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * craft + brand: framework foundation, build-pipeline respect, image verification Three closely-linked additions surfaced by an eval-harness session investigating why the agent always shipped flat single-file HTML and zero imagery on greenfield brand briefs. 1. craft.md gains a new Step 0 "Project Foundation" before Shape. Detects existing framework / component library / icon set and uses what's there. Greenfield: ask the user via AskUserQuestion with sensible defaults framed by the brief (Astro for content/ brand sites, SvelteKit/Next/Nuxt for app surfaces, single index.html only for one-shot demos). Skipping the framework decision and writing flat HTML "to satisfy the spec" produces work that reads as a 2018 prototype regardless of visual quality. 2. craft.md Step 5 production bar gains two bullets: - Respect the build pipeline. Edit source files and run the project's `npm run build`; do not write to build/ / dist/ / .next/ directly with cat/heredoc/Bash redirects. Bypassing the pipeline skips asset hashing, image optimization, code splitting, and CSS extraction. - Verify external image URLs before referencing them. Use an image-search MCP, web-fetch tool, or browser if available; guessed photo IDs ship as broken-image placeholders. 3. brand.md "Imagery" section: - Generalizes the Unsplash URL guidance to "verify URLs before referencing them" with a hierarchy: image-search MCP > web-fetch > confidence-restricted manual selection > fewer photos. - Tightens the tech/dev-tool exception. Old line "zero imagery can be correct" gave models a permission slip. New framing keeps the underlying truth (typography + code + diagrams primarily carry voice) but raises the floor: imagery still earns its place when it serves the brief, and skipping it requires naming the typographic/diagrammatic move that's carrying the visual weight instead. "Zero imagery is the failure mode of laziness, not restraint." Eval-harness corpus that prompted this: 19/19 brand landing tasks shipped 0 images each, including ones where Opus had taste enough to break the dev-tool color default lane. The skill needs to teach both halves of the decision; the harness shouldn't have to nudge. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * detector: body-text-viewport-edge rule + OKLCH/var-resolution + anchor-inherit FP fixes New rule: body-text-viewport-edge flags body paragraphs that render flush against the left/right viewport edges (no container padding). Tested via the new tests/fixtures/antipatterns/body-text-viewport-edge.html fixture (3 flag cases, 5 pass cases) and the test in detect-antipatterns-browser. False-positive class fixes — all jsdom-mode only (real browsers resolve the cascade correctly so these gates stay inert there). Five related gaps that compounded into ~14× spurious contrast findings on Tailwind v4 pages with OKLCH color tokens: • OKLCH parser. jsdom returns the literal "oklch(...)" string from getComputedStyle; the detector now converts to sRGB via Björn Ottosson's matrices. Handles Tailwind v4's compact minified form "oklch(21.5%.02 50)" (no space after %). • var() resolution. resolveBackground + checkElementColors now accept the existing customPropMap and parse `var(--color-paper)` etc. as proper RGB via the new parseColorResolved helper. • bg-color before bg-image. The old order bailed on any gradient ancestor before checking for a solid background-color underneath, causing the body's decorative paper-grain gradient to be measured against instead of the page's actual `bg-paper` cream. • body/html-level gradient → white fallback. When the only opaque ancestor we can read is body/html with a gradient overlay (and jsdom can't decompose `background: var(--paper) gradient` to extract the solid color), return white instead of falling through to resolveGradientStops — which was picking up paper-grain noise colors and using them as the bg. • Anchor-inherit workaround for jsdom :link UA specificity. Tailwind v4's preflight declares `a { color: inherit }` (0,0,1). jsdom's UA stylesheet has `:link { color: blue }` at (0,1,1) and wins the cascade. Real Chrome wraps :link in :where() (0,0,0) so the page rule wins. When the page declares the inherit rule AND we see jsdom's default `rgb(0,0,238)` on an anchor, walk to the nearest non-anchor ancestor and use its color. • Alpha-fallback safety gate. When text has alpha<1 AND we couldn't find an opaque ancestor (effectiveBg null), skip the contrast finding. Covers any remaining FP class the deeper fixes miss. Verified end-to-end against an Opus iter-1 artifact on Tailwind v4 with 14 cream/cream FPs + 2 blue-link UA FPs before; 0 findings after, while the color.html fixture's 12 real low-contrast cases continue to flag (verified via direct detectHtml calls). cli/engine/detect-antipatterns-browser.js is the generated browser distribution — regenerated from .mjs via scripts/build-browser-detector.js (no manual edits to the generated file). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * craft.md: tighten verbose passages, de-codex Step 6, cut redundancies Cumulative reduction: 218 → 155 lines (-29%). Step 0: drop the "Why this matters" paragraph at the end. The body of Step 0 already makes the framework-pick point; the paragraph just re-explains it with extra rhetoric. Step 1: replace the 4-sentence "you must end your response" block with a single line. The original said the same thing three different ways. Step 3: trim the conditional / defensive scaffolding (Purpose subsection, "do not skip because the eventual UI is semantic..." paragraph, duplicated approval-loop guidance). Mock fidelity inventory preserved. Step 4: drop the "keep UI text semantic" sentence; it duplicates Step 5's "Semantic first" rule. The rasterized-vs-semantic decision rule stays. Step 5: tighten each production-bar bullet to bold-lead + specifics format. All 15 rules preserved (real content, mock ingredients, semantic first, spacing/alignment, typography, state coverage, interaction quality, icon set, build pipeline, image URL verification, optimized imagery, premium motion, maintainability, technical cleanliness, ask-when-uncertain). Step 6: rewrite around "look at what you built like a designer would — your eyes are whatever the harness gives you." Drops Codex-specific "In Codex, use browser-use" bias. Drops the verbose 3-step Read pattern (condensed to one sentence). Drops the 1-8 numbered checklist (replaced by a tight paragraph). Keeps the load-bearing rules: read the PNG, don't fabricate iteration, mock fidelity reference, exit bar = studio defensibility. Step 7: drop the closing "Iterate based on feedback. Good design is rarely right on the first pass" preachy filler. All em-dashes converted to semicolons / colons / periods to satisfy the skill prose validator. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * build: native subagent pipeline + Codex-only asset producer Adds an agent cross-compile pipeline alongside the existing skill pipeline. Sources live at skill/agents/*.md; providers that declare agentFormat (codex-toml, claude-md) emit native subagent files. An optional providers: <list> field on an agent gates which harnesses get a copy; default (no field) ships everywhere. The impeccable-asset-producer agent is opt-in to Codex only. It's useful for Codex's native image generation path and is untested elsewhere; Claude has no native image gen anyway. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * brand: inverse-test + cultural-symbol palette guardrail Two additions to the brand register reference: - Inverse slop test: describe the page the way a competitor would describe theirs. If that sentence fits the modal landing page in the category, restart. - Palette guardrail: when a cultural-symbol palette is the obvious pull, reach past it. Let cultural reading come from typography, imagery, and copy. Harness mirrors regenerated; some also catch up to the image- verification paragraph from |
||
|
|
e587004ee4 |
Refactor: cleaner top-level directory structure (#138)
* refactor(content): merge content/site/ into site/content/ Phase 1 step 1 of the directory restructure. The dual content tree was called out in CLAUDE.md as cleanup; both trees were already in sync except for anti-patterns-catalog.js, which moves to site/data/. - Delete content/site/skills/ and content/site/tutorials/ (duplicates of site/content/, which is what Astro's content collection actually reads). - Move content/site/anti-patterns-catalog.js -> site/data/. - Update scripts/lib/sub-pages-data.js and scripts/build.js to read from site/content/ and site/data/. - Drop content/site/ from validateProse target list (site/content was already there). - Rewrite the "Two content trees" section in CLAUDE.md as a single-tree pointer; update stale dev-server text mentioning the deleted server/index.js. Tests: 186/186 pass. Skills build: clean. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * refactor(skill): rename source/skills/impeccable/ -> skill/ Phase 1 step 2 of the directory restructure. The path was redundantly nested ("source/" wrapper plus "skills/impeccable/" — singular content hidden behind the plural). Collapses to flat skill/SKILL.md + skill/reference/ + skill/scripts/. - Move source/skills/impeccable/ -> skill/. - Rewrite scripts/lib/utils.js readSourceFiles(): drop the multi-skill iteration (CLAUDE.md commits to a single user-invocable skill); read skill/SKILL.md directly. - Update scripts/build.js, scripts/generate-og-image.js, and the sub-pages data layer to point at skill/. - Update tests/lib/utils.test.js: drop the "multi-skill" and "dir-name fallback" cases, update single-skill paths to skill/. - Update tests/build.test.js similarly: drop "multiple skills" integration test, update paths. - Update non-glob path joins in tests/framework-fixtures.test.mjs, tests/live-e2e/session.mjs, tests/live-e2e/agents/llm-agent.mjs, tools/live-loop.mjs. - Update prose/text references in CLAUDE.md, AGENTS.md, DEVELOP.md, README.md, scripts/lib/sub-pages-data.js, bin/commands/skills.mjs, site/data/anti-patterns-catalog.js, site/pages/docs/[...slug].astro, docs/adr-live-variant-mode.md, docs/plans/. Eval framework note: the separate impeccable-evals repo reads ../impeccable/source/skills/impeccable/ and needs a coordinated rename to ../impeccable/skill/. Tests: 186/186 pass. Skills build: clean. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * refactor: rename docs/ -> notes/ Phase 1 step 3 of the directory restructure. The internal docs/ dir (ADRs and plans) clashed with the site's /docs route. Renaming it "notes/" makes the difference unambiguous: notes/ is project-internal process, /docs is the user-facing route under site/pages/docs/. No code references the dir; the rename is a clean git mv. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * refactor(site): move public/ under site/public/ Phase 2 step 4 of the directory restructure. Public assets and the Astro publicDir now live alongside the rest of the site, so site/ is fully self-contained for static content. - git mv public site/public. - astro.config.mjs: add publicDir: './site/public'. Astro defaults to ./public at the project root, so the override is required. - scripts/build.js: write generated _data, _headers, _redirects, _routes.json, and js/detect-antipatterns-browser.js into site/public/. Also delete the dead _REMOVED() Bun static-site builder (replaced by Astro at #130; the placeholder no longer earns its keep). - scripts/build.js validateProse: replace the stale public/index.html reference (deleted at the Astro migration) with site/pages/index.astro in the count-validation file list, restoring homepage drift detection. - scripts/generate-og-image.js: write OG image into site/public/. - scripts/screenshot-antipatterns.js: read examples from + write screenshots to site/public/antipattern-{examples,images}/. - scripts/lib/sub-pages-data.js: load command demos from site/public/js/demos/commands. - .gitignore: rename the public/* generator-output entries to site/public/*. - CLAUDE.md: refresh CSS/data-file paths (still pointing at the old pre-Astro public/css/ + public/js/ tree), point the changelog and command-add checklists at site/pages/index.astro and site/scripts/data.js + site/scripts/components/framework-viz.js. Cloudflare Pages note: functions/ stays at the repo root because CF Pages auto-discovers it there with no configuration knob to relocate. Moving it under site/ would either break deployment or require a build-time copy step that adds more complexity than the cleanup is worth. Tests: 186/186 pass. Skills + site build clean. _headers, _redirects, _routes.json, _data/ all land in build/ correctly. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * refactor(cli): consolidate bin/ + src/ + lib/ under cli/ Phase 2 step 5 of the directory restructure. The CLI surface was split across three top-level dirs whose names were easy to mistake for each other (especially src/ vs source/ pre-step-2). Consolidates under cli/. - git mv bin -> cli/bin (CLI entry + skills sub-command) - git mv src -> cli/engine (detect-antipatterns engine + browser variant) - git mv lib -> cli/lib (download-providers helper) Update package.json: - bin.impeccable: cli/bin/cli.js - main + exports: cli/engine/detect-antipatterns.mjs and the ./browser variant - files: ["cli/", "LICENSE"] Update internal references: - cli/bin/cli.js: dynamic import points at ../engine/, package.json read goes one level deeper (../../package.json). - functions/api/download/[type]/[provider]/[id].js + bundle/[provider].js: cli/lib/download-providers.js path. - scripts/build.js, scripts/build-browser-detector.js, scripts/build-extension.js: cli/engine path constants. - scripts/lib/sub-pages-data.js, scripts/lib/utils.js, skill/scripts/ live-server.mjs: comment refs. - tests/detect-antipatterns{,-browser,-fixtures}.test.{js,mjs}, tests/windows-path-fix.test.js: import + read paths. - AGENTS.md, CLAUDE.md: doc paths. Verified: - npx node cli/bin/cli.js --version, --help, detect --help all work. - bun run build, bun run build:browser, bun run build:extension all clean. Browser detector lands at cli/engine/detect-antipatterns-browser.js; extension/detector/detect.js still emits to the same location. - bun run test: 186/186 pass. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: update browser-detector paths missed in cli/ rename Bugbot caught two runtime path leaks where the comment got renamed to cli/engine/ but the actual code still used the old src/ segment. - skill/scripts/live-server.mjs: detectPaths array now joins cli, engine, detect-antipatterns-browser.js for both the repo-relative lookup (4 dirs up from .claude/skills/impeccable/scripts/ to repo root) and the npm node_modules fallback. Without this fix, the detection overlay would silently not load during live-server sessions. - scripts/build.js: the post-build copy of the browser detector into site/public/js/ was reading from src/. The if (fs.existsSync(...)) guard meant the copy was silently skipping, so antipattern-examples pages would 404 on /js/detect-antipatterns-browser.js once the site was deployed. Tests: 186/186 pass. Build clean. site/public/js/detect-antipatterns-browser.js re-emits as expected. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: cleanup-deprecated import path missed an extra .. in cli/ rename Bugbot caught three call sites in cli/bin/commands/skills.mjs that import '../../skill/scripts/cleanup-deprecated.mjs'. Pre-rename, that was correct from bin/commands/ (one parent to bin/, one to repo root). After moving the file from bin/commands/ to cli/bin/commands/, the path is one directory deeper, so it needs three .. segments to reach the repo root. Without the fix, every cleanup invocation throws on import and gets swallowed by the surrounding try/catch — silent skip. cli/bin/cli.js's package.json read already uses '../../package.json' (the same depth pattern), confirming three levels is correct. Verified: dynamic import resolves and exports the expected functions. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore: sweep stale path/file references missed in the restructure Same root cause as the two bugbot finds: some references in moved or related files weren't tracked because they didn't match a simple sed pattern. Caught the rest by walking each moved dir's depth and each Astro-migration deletion. Stale path references (post-Astro migration, missed earlier): - CLAUDE.md: legacy URL redirects "live in server/index.js" -> point at the actual sources (scripts/build.js generateCFConfig + site/public/_redirects). - AGENTS.md: counts.js path (public/ -> site/public/), changelog file (public/index.html -> site/pages/index.astro), screenshots note (public/ -> site/), source-of-truth dirs (source/, src/ -> skill/, cli/). - tests/detect-antipatterns-browser.test.mjs: comment about routes "in server/index.js". - skill/reference/live.md: workflow.css example for "this repo" was pre-Astro (public/css/) -> site/styles/. (User-project Vite/Next example unchanged.) Stale path that pointed at moved files: - tests/skills-cli.test.js: CLI path was '..', 'bin', 'cli.js'; now '..', 'cli', 'bin', 'cli.js'. Test isn't wired into bun run test but it would have failed if invoked. Dead files (orphaned by Astro migration, never cleaned up): - tests/server/download-validation.test.js: imported from ../../server/lib/{validation,api-handlers}.js which were deleted in |