Paul's Opus gallery observation: every impeccable 05-experimental-album
generation reads decidedly SaaS while frontend-design's open with the
art itself, especially at narrow viewports. Cause: the brand register
prescribed stop-the-scroll/earn-the-click/convert for ALL brand
surfaces. Split the register's deliverable by surface: product/service
pages convert; cultural surfaces (album, portfolio, publication, body
of work) lead with the artifact, recede the interface, and treat
conversion grammar as a category error — the visitor meets the work in
the first viewport at every screen size.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Paul: everything should be bold, nothing bland; bold is neither
decoration nor clutter but commitment to the concept, whose form the
concept chooses (maximal or severely clean, drenched or monochrome,
piercing copy, the product demonstrating itself). Replaces the
'spend your boldness in one place' rule imported from frontend-design,
whose one-bold-element-on-a-quiet-page framing pulled pages toward the
tasteful softness the galleries showed losing. The signature becomes
where the concept peaks rather than the only place it lives.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Paul's spot-check of the Fable validation galleries: frontend-design's
lektor generations read vastly more distinctive and subject-faithful
despite losing the overall pairwise verdict on craft. The arena agrees
on the axis (distinctiveness 8-31 at n=5). Two additions to the core:
the opening viewport is a thesis (open with the most characteristic
thing in the subject's world, with a concrete memory test), and an
explicit polish-is-the-floor counterweight so the craft floor stops
reading as a mandate for quiet.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Eval evidence showed the per-edit PostToolUse stream fires overwhelmingly
on copy-level rules (em-dash-overuse ~97x/session) and measurably makes
models more conservative, while a full-detector pass at completion is what
actually fixes contrast/padding/glow. Split the hook accordingly:
- Per-edit (PostToolUse) now surfaces only IMMEDIATE_TIER_RULES: broken
output (broken-image, text-overflow, clipped-overflow-container,
body-text-viewport-edge), objective contrast/legibility failures
(low-contrast, gray-on-color, tiny-text), single-property mechanical
slop (gradient-text, dark-glow), and design-system drift (the four
design-system-* rules, which compound if left uncorrected). Everything
else defers. Override with hook.perEditRules: "all" in
.impeccable/config.json. Tiering is off for Cursor/Copilot harnesses,
which have no Stop pass wired, so nothing gets silently dropped there.
- Stop deep pass (runStopHook): runs the FULL rule set over every UI file
touched this session (tracked via the existing hook.cache.json session
state; deferred-only edits now mark the file touched), dedupes against
everything already surfaced per-edit, honors ignore-rule/file/value and
inline disables, reuses the [impeccable@1] envelope, and no-ops fast
when no UI files were touched. Emits hookSpecificOutput
{ hookEventName: "Stop", additionalContext } per the Claude Code SDK
Stop contract (conversation continues so the model can act on it).
Second Stop fire is silent - deep-pass findings are remembered.
- Wiring: Stop entries (timeout 30) in plugin/hooks/hooks.json, the
.claude settings + .codex hooks manifests (transformers + hook-admin
repair path). Claude Code and Codex both dispatch a native Stop event;
Cursor's stop hook is inconsistently dispatched (pre-write gate stays)
and Copilot's agentStop/sessionEnd don't inject model context, so
neither gets a Stop entry - documented in reference/hooks.md.
- Tests: tiering split/override/harness gating, Stop dedupe + silent
no-touched-files + ignore machinery + kill switches; existing per-edit
tests moved to immediate-tier rule ids. 181 tests green; smoke-tested
the built dist skill end to end (glow surfaced per-edit, em-dash only
at Stop, second Stop silent).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Pairwise evals on Fable one-shot (6-task regression set, opus-4-8 judge,
position-bias-cancelled): the hand-distilled ~55-line lean core beat the
heavy v4 core 66% overall / 67% craft head-to-head, and moved the
decisive win-rate vs frontend-design from 13% to 27% (40% with the
completion-time QA scan; craft went positive 6-5 for the first time).
18/18 lean samples ran context.mjs + palette.mjs vs a minority under the
heavy core: shorter instructions get followed. Context weight itself was
suppressing both compliance and boldness.
Structure: persona + brief-wins + existing-worlds + subject-grounding +
plan/self-check + boldness + prove-don't-claim + commit + calibration +
compressed craft floor + two-paragraph registers. Commands table kept;
the no-arg context-aware menu logic moved to reference/routing.md (read
on demand in the only case that is inherently interactive). Provider
blocks and rule anchors preserved.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Judge rationales across cand-v4a2 arenas: competitor wins by showing
the product working (mix panels, comparison tables, live demos) and by
signatures big enough to organize the page; our samples claim, decorate,
and sometimes stop at the hero.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Eval evidence (cand-v4a1-prose): palette.mjs handed a random violet seed
to the Polish-TV lektor brief and the model anchored on it, overriding
subject-grounding; craft/shape user gates can't fire in one-shot runs
and each model improvises around them. Seed is now a reflex-check that
yields to a subject-dictated palette; craft/shape gain an explicit
unattended mode (same bar, no waiting); init interview is skipped when
no user can respond.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Per Paul's guidance: (1) existing committed design systems are the
bread-and-butter case and get a first-class core rule (work inside the
world, no parallel colors/fonts/styles, no perf regressions); (2) a
redesign that discards the current look is new identity work and runs
the full concept/tokens/signature process instead of anchoring to the
incumbent skeleton (the lektor failure); (3) the reflex-reject font list
and physical-object font procedure are brand-register rules, moved out
of the universal Commit section — system stacks and workhorse UI faces
are legitimate, often correct, for product UI, stated positively in the
product register.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
One-shot evals on Fable 5 (impeccable-evals notes/fable-oneshot-craft-plan.md)
showed the reference-file architecture failing: models skip the register
reads, so most design guidance never reaches them, and skill-on collapses
toward bare-model output (0/9 pairwise wins vs frontend-design on r10).
SKILL.md is now self-contained for one-shot work: persona, the-brief-wins
rule, ground-it-in-the-subject, a plan/tokens/signature/self-check process
gate, commitment guidance, a compact inline craft floor, and distilled
brand/product registers. Reference files remain as sub-command flows and
optional depth. The enumerated absolute-bans list is retired from prose;
mechanical slop enforcement moves to the detector/hook.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* Add OpenAI plugin submission bundle
Build a Codex-native OpenAI plugin with bundled hooks, public listing metadata, submission guidance, privacy coverage, and regression tests.
AI assistance: OpenAI Codex prepared and validated these changes under maintainer direction.
* Fix provider script command rendering
Replace heuristic rewrites across executable scripts with one explicit provider marker, render pinned shortcuts per target harness, and remove the personal email from the public publisher manifest.
Addresses automated review feedback on PR #363.
AI assistance: OpenAI Codex prepared and validated these changes under maintainer direction.
Codex loads bundled plugin lifecycle hooks from `hooks/hooks.json` using a
strict schema that accepts only the top-level `hooks` field. The
plugin-packaged manifest carried a top-level `description`, so Codex rejected
the whole manifest with `unknown field description, expected hooks` and the
post-edit design detector never registered (issue #330).
Drop `description` from `buildClaudePluginHooksManifest()` and regenerate
`plugin/hooks/hooks.json`. The Claude Code plugin path is unaffected (it only
reads the `hooks` object). Add a regression assertion for the plugin artifact
and bump the skill version to 3.9.1.
Claude-Session: https://claude.ai/code/session_013GTTHY6uHwESUyAgjUEm7x
Co-authored-by: Claude <noreply@anthropic.com>
* Point DESIGN.md spec links at the open-source GitHub spec.
The Stitch docs site is client-rendered and unreliable for agent fetch; the
google-labs-code/design.md repo tracks the latest machine-readable spec.
Co-authored-by: Cursor <cursoragent@cursor.com>
* Sync plugin and harness copies after DESIGN.md spec link update.
build:release copies skill/reference into plugin/ and all harness dirs, so
refresh those generated outputs here instead of leaving plugin/ stale.
Co-authored-by: Cursor <cursoragent@cursor.com>
* Use raw GitHub URL for DESIGN.md spec in agent-facing refs.
The blob URL serves HTML; raw.githubusercontent.com returns plain markdown
that agents can fetch directly.
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
The bundled detector's cli/main.mjs imports ../../lib/impeccable-config.mjs,
which in the source CLI resolves to cli/lib/impeccable-config.mjs. The skill
build only copies cli/engine/** into scripts/detector/**, leaving that
dependency behind, so from the bundled scripts/detector/cli/main.mjs the same
import resolved to scripts/lib/impeccable-config.mjs and failed with
"Cannot find module .../lib/impeccable-config.mjs". /impeccable critique (and
any detector-backed command) crashed on startup for every provider since #252.
Teach the detector bundler to copy out-of-bundle engine dependencies into the
skill's scripts/lib/, and add a build test that walks every bundled script and
asserts each relative import resolves to another bundled file, so a future
out-of-bundle dependency fails the test instead of the user.
Skill v3.7.1 (patch). CLI unchanged — the engine resolves fine in the CLI's
own tree; only the skill bundling was wrong.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(hooks): package design hook in plugin, install to settings.local.json
Three related changes to how the Impeccable design hook is distributed,
plus an unrelated build fix discovered along the way.
Package the hook in the Claude Code plugin
- The marketplace / `/plugin install` path previously shipped the skill and
agents but no hook, so those users never got the design detector. The build
now emits `plugin/hooks/hooks.json` (auto-discovered at the plugin root),
resolving the script via `${CLAUDE_PLUGIN_ROOT}` so it works wherever Claude
Code unpacks the plugin instead of assuming a `.claude/skills/` layout.
CLI installs the hook into settings.local.json, not shared settings.json
- `npx impeccable skills install/update` now writes the Claude hook to the
gitignored `.claude/settings.local.json` (a machine-local install side
effect) rather than the team-shared `settings.json`, which could otherwise
be committed and break for teammates without the skill installed.
- Graceful handling (leave-it-never-duplicate): if our hook already lives in
the shared `settings.json` (a legacy install or a deliberate user move), it
is honored in place and never duplicated into the local override, which
would otherwise run the detector twice per edit.
- The skill's `/impeccable hooks on|off` toggle is unaffected: it only writes
`.impeccable/hook.json`, never the settings files.
Fix universal.zip build failure under archiver v8
- `archiver` was bumped to v8 (now ESM, factory function removed) but
`scripts/lib/zip.js` still used the old `archiver('zip', ...)` API, so every
build silently failed to produce `dist/universal.zip` (the skill-release
artifact). Switched to `new ZipArchive({...})`.
Also folds in a pre-existing local rename of the hook status message
("Scanning design" -> "Checking UI changes") and its regenerated provider
output.
Tests: new coverage for the plugin-packaged hook manifest and the
shared-settings honor-in-place path; existing CLI assertions moved to
settings.local.json. Full suite green.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(cli): detect hook by marker, not file existence (Bugbot)
hookInstalledForProvider treated any existing settings.local.json (or
hooks.json) as proof the hook was installed. Those files commonly hold
unrelated local settings, so the already-installed `skills install` path
would skip repairing a genuinely missing hook that `update` would add.
Detect the Impeccable marker in the file instead of mere existence. Adds a
test for the exact case: a settings.local.json with only permissions still
triggers hook repair and preserves the unrelated content.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test(build): fail loud on a broken release zip + cover the zip writer
Close the gap that let the archiver v8 break ship a 0-byte universal.zip
with a green test suite:
- createProviderZip no longer swallows failures. It throws on a missing
source, an archive with zero entries, or a 0-byte output, and build() now
exits non-zero on any such rejection. A build that can't produce its release
artifact fails instead of deploying an empty bundle.
- New tests/zip.test.mjs exercises the real zip writer and round-trips through
extract-zip (the unpacker the CLI uses): a valid bundle unpacks to the skill
tree, and the empty/missing-source cases throw. Wired into the core suite so
it runs in `bun run test`.
Why this matters: the prior CLI e2e tests stub the bundle as a local
directory, so they never built, downloaded, or unzipped a real archive. The
zip writer had no coverage and failed soft, so Dependabot's archiver 7->8
major bump merged green and the deploy shipped an unusable bundle.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(cli): scope hook marker scan to the hooks subtree + prune local dupes (Bugbot)
Two follow-ups from Bugbot:
- fileHasImpeccableHookMarker scanned the whole settings file as raw text, so
an unrelated string (e.g. a permissions allow entry that mentions the hook
path) could falsely read as an installed hook and block install/repair or
the shared-settings skip. Now it parses the JSON and scans only the `hooks`
subtree.
- When the hook is honored in the shared settings.json, copyProviderHooks
skipped the local write but left a stale hook in settings.local.json from an
earlier machine-local install, so Claude Code loaded both and ran the
detector twice per edit. It now prunes the local copy (preserving unrelated
local settings, dropping the file if only our scaffolding remained).
Adds tests for both: a permissions string mentioning the hook path still
triggers repair, and a shared hook prunes the stale local duplicate while
keeping unrelated permissions.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs: add PRD for design detector hook integration
Plans a PostToolUse hook for Claude Code and Codex that runs the
existing design detector after every relevant file write and feeds
findings back to the agent as advisory system-reminder context. No
implementation in this commit; covers UX, technical design, build
pipeline changes, distribution, coverage tradeoffs, and rollout.
Co-authored-by: Cursor <cursoragent@cursor.com>
* docs: revise hook PRD with best-practices review
Folds in the P0/P1/P2 findings from an online best-practices critique
against the official Claude Code and Codex hook references plus 10+
2026 community guides and similar prior-art tools (claw-hooks,
claude-code-hooks-mastery).
Key changes:
- Exec form everywhere (Codex snippet was shell form), with Windows
rationale.
- Default timeout dropped from 10s to 5s.
- Re-entrancy guard (CLAUDE_HOOK_DEPTH) and per-file edit counter.
- Session-scoped finding dedup promoted from open question to v1.
- Per-language inline-ignore syntax map (HTML/JSX/CSS/JS).
- Hard-skip rules for sensitive paths and generated/lock files.
- Honest framing about Claude Code lacking per-plugin hook disable.
- Honest framing about Bash-written files being invisible in v1.
- Codex Windows-not-supported call-out, feature flag note, trust ceremony detail.
- Optional NDJSON audit log via IMPECCABLE_HOOK_LOG.
- Findings cap lowered 8 → 5 with attention-budget rationale.
- Versioned envelope ([impeccable@1]) on rendered template.
- Expanded test plan, decision log, and stdin payload appendix.
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(hooks): ship the design detector hook for Claude Code and Codex
Implements docs/hooks-prd.md: a PostToolUse hook that runs the
impeccable design detector after every Edit/Write/MultiEdit on a UI
file and pushes findings into the agent's next-turn context as a
short system reminder. Silent on clean files. Never blocks an edit.
Why this matters: today, design slop (side-tab borders, gradient
text, purple/cyan palettes, bounce easing, etc.) only gets caught
when a human notices or someone explicitly runs /impeccable audit.
The hook closes the loop at the moment slop is written.
What ships in v1
- skill/scripts/hook.mjs: PostToolUse entry. Reads stdin, runs the
detector in-process (no `npx impeccable` cold start), emits
hookSpecificOutput.additionalContext when fresh findings exist.
- skill/scripts/hook-lib.mjs: extracted helpers (config, cache,
filter, render, audit log, runHook orchestrator). 100% unit-testable.
- skill/scripts/hook-session-start.mjs: SessionStart greeting,
gated by a project-scannable probe + 30-day throttle.
- skill/scripts/hook-admin.mjs: backs /impeccable hooks
on/off/status/ignore-rule/ignore-file/reset.
Hardening built in
- Re-entrancy guard (IMPECCABLE_HOOK_DEPTH) so the hook can never
recursively spawn itself.
- Hard-skip regexes for sensitive paths (.env, .pem, id_rsa,
secrets, credentials, .git) and generated/lock/build output. These
fire before the file is even read; cannot be turned off via config.
- Path-traversal check on the inbound file_path.
- Session-scoped dedup keyed by (session, file, rule, line) so the
same finding never lands in context twice. Prevents the ~12.5K
wasted tokens per chatty session called out in the PRD.
- Per-(session, file) edit counter with a one-shot suppression
notice on the 7th edit, silent after.
- Fail-open contract: every error path returns exit 0 with no
stdout. Optional NDJSON audit log via IMPECCABLE_HOOK_LOG.
Three kill switches (precedence high to low):
1. IMPECCABLE_HOOK_DISABLED env var (1/true/yes/on, case-insensitive)
2. .impeccable/hook.json `enabled: false`
3. /impeccable hooks off slash command (writes the JSON)
Inline ignores are language-aware. `// impeccable: ignore <rule>` for
JS/TS, `<!-- impeccable: ignore <rule> -->` for HTML/Vue/Svelte/Astro,
`{/* impeccable: ignore <rule> */}` for JSX/TSX, `/* impeccable:
ignore <rule> */` for CSS. `*` matches any rule. Directive applies
to the next non-blank line. Same shape as ESLint, Stylelint, Biome.
Build pipeline
- scripts/lib/transformers/hooks.js: per-provider hooks.json
builders, plus the slim .codex-plugin/plugin.json manifest.
- providers.js: emitHooks: 'claude' for claude-code, emitHooks:
'codex' for codex and agents. Codex also emits emitCodexPlugin.
- factory.js: emits hooks/hooks.json next to the skills tree.
- build.js: syncs hooks/ into harness roots and into the slim
plugin/ subtree; writes .codex-plugin/plugin.json. Build is
idempotent (verified: 98 staged files unchanged across two runs).
Claude Code wiring uses exec form (command + args) and the
${CLAUDE_PLUGIN_ROOT} placeholder. Matcher: Edit|Write|MultiEdit.
`if:` glob filters to UI extensions before spawning Node. PostToolUse
timeout 5s, SessionStart timeout 3s.
Codex wiring uses ${PLUGIN_ROOT} (Codex's native placeholder),
matcher Edit|Write|apply_patch, no `if:` analog (the script does the
extension filter). macOS and Linux only; hooks are disabled on
Windows in current Codex builds. The trust ceremony and feature flag
are documented in README.md.
Routing
- /impeccable hooks lives outside the 23-command router table on
purpose: it is plumbing, not a design skill. The hidden
routing slot is added to SKILL.md alongside pin/unpin so the LLM
knows to dispatch it. The 23-command count and all stale-count
validators remain happy.
Tests
- tests/hook.test.mjs: 38 unit tests covering env parsing, config
load + defaults + malformed, cache round-trip + GC,
ignoreRules/minSeverity/inline ignores (all four languages),
globbing with **/*/{a,b}, render template with cap + clamp + 0-line
prefix drop, audit log NDJSON, payload event-name parameterization,
re-entrancy, kill switches, sensitive-path + generated-path +
traversal skips, allowlist filter, config ignoreFiles, edit
counter cycle including the 7th-edit notice, MultiEdit and
apply_patch payload shapes, detector throw swallow, malformed
stdin, missing file race.
- tests/hook-build.test.mjs: 18 integration tests covering hook
manifest shape (matcher, timeouts, exec form, if: glob, placeholders),
Codex differences (${PLUGIN_ROOT}, no if:, no SessionStart),
Codex plugin manifest (no inline hooks field to avoid the
duplicate-file error), routing across the hooksJsonFor table, and
presence of all three committed artifacts plus the bundled detector
the runtime relative-import path depends on.
Full suite: 175 bun tests + 186 node tests, all green.
Docs
- README.md: new "Design hook" section explaining default behavior,
per-project / global / inline disable paths, the JSON schema knobs,
the audit log debug flag, and the slop / a11y coverage split.
- HARNESSES.md: flips the `hooks` row for Codex from No -> Yes
(Claude was already Yes), adds a per-harness hook-surface table
with the manifest location and matcher each provider uses.
Open questions from the PRD intentionally deferred to v2: Bash-write
blind spot, effort-aware suppression, Stop-hook session summary,
per-rule severity, async hook mode. None block v1.
Co-authored-by: Cursor <cursoragent@cursor.com>
* Fix Codex hook scanning: apply_patch paths and co-located stylesheets
Parse file targets from Codex apply_patch command bodies, co-scan imported
and sibling CSS when UI components are edited, drop the git-sweep PostToolUse
group, and align Codex SessionStart manifest and trust docs with the official
hooks spec.
Co-authored-by: Cursor <cursoragent@cursor.com>
* Gitignore hook session cache and drop local test HTML
Hook dedup/throttle state in .impeccable/hook.cache.json is per-project
runtime data like other .impeccable/ sidecars. Remove an untracked
bad-nested-flexbox scratch page from site/public/.
Co-authored-by: Cursor <cursoragent@cursor.com>
* Fix Claude Code hook: drop Edit-only if filter so Write/MultiEdit fire
Claude's if permission rule binds to one tool name, so Edit(*.{…}) never
spawned the hook on Write or MultiEdit despite the matcher listing them.
Extension filtering now lives in hook-lib on both Claude and Codex.
Co-authored-by: Cursor <cursoragent@cursor.com>
* Surface Cursor design findings via stop-hook followup
Replace dropped postToolUse additional_context with afterFileEdit recording
and a one-shot stop followup_message so anti-pattern nudges reach the agent.
Co-authored-by: Cursor <cursoragent@cursor.com>
* Fix design hook packaging and scans
* Fix Cursor hook pending bucket fallback
* Fix Sass hook scan coverage
* Fix Cursor hook review findings
* Fix session start dead hook normalization
* Fix hook config and relative scan paths
* Remove SessionStart design hook
* Remove redundant afterFileEdit normalization
* Fix Cursor suppression and module style scans
* Fix sensitive path hook filter
* Fix disabled Cursor stop hook emission
* Refresh hook harness artifacts
* Fix Cursor hook manifest install
* Add hook ignore-value support
* Ignore hook runtime files locally
* Fix Codex plugin hook packaging
* fix: address PR review bot findings
Block numeric hook depth counters from re-entering.
Avoid following stylesheet imports from traversal-looking hook targets.
* fix: gate ignore-value suggestions by supported rules
Only render exact ignore-value commands when the same finding can be suppressed by ignoreValues.
* Package Codex plugin as hook-only
* Remove Codex plugin packaging
* Recover hook install probe plumbing
* Remove Codex hook packaging follow-up doc
* Remove extra hook docs and skill wording changes
* Install real design hooks via skills CLI
* Add provider hook smoke runner
* Fix Cursor hook delivery with preToolUse gate
* Simplify Cursor hook install to preToolUse
* Clarify confirmed hook exceptions
* Persist hook ignores in shared config
* Guard font hook exceptions
* Fix hook install after main rebase
* Fix hook scan target handling
* fix: address hook review findings
* Address hook review feedback
* Stabilize DeepSeek insert live fixture
* Fix Cursor hook Python shell write bypass
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Paul BakausandClaude Fable 5
github-actions[bot]
