mirror of
https://github.com/pbakaus/impeccable.git
synced 2026-09-11 21:57:14 +03:00
10183bd91cba67b6fd535a619689739b6f636f56
202
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Paul Bakaus
|
10183bd91c |
Measure production Live worker phases
Trace worker pickup and derive generation, validation, and publication latency from the durable Live session journal.\n\nAI-assisted: OpenAI Codex. |
||
|
Paul Bakaus
|
aba1067cdf |
Benchmark the production Codex Live worker
Let the browser E2E harness launch an independent production worker, exercise real sub-command selection, and carry realistic product/design context.\n\nAI-assisted: OpenAI Codex. |
||
|
Paul Bakaus
|
27bbf90ede |
Improve Codex Live architecture benchmark
Compare production-equivalent direct and app-server paths, include annotated UI work, expose first-usable latency, and keep semantic quality gates honest.\n\nAI-assisted: OpenAI Codex. |
||
|
Paul Bakaus
|
27a210b04c |
Add Codex Live architecture benchmark
Compare direct Sol execution with cold and persistent app-server paths using identical full-task quality gates, lifecycle timings, and token metrics.\n\nAI-assisted: OpenAI Codex. |
||
|
Paul Bakaus
|
421c1a93f5 |
Harden Live design-system fidelity
Route the full-context benchmark through production worker inputs and preserve established shared-control visual roles during variant amplification.\n\nAI-assisted: OpenAI Codex. |
||
|
Paul Bakaus
|
6d1bd40959 |
Fix Codex quality benchmark gates
Allow valid CSS-only design work and compare JSX component contracts independent of formatting.\n\nAI-assisted: OpenAI Codex. |
||
|
Paul Bakaus
|
92a5589d5d |
Add Codex Live quality benchmark
Benchmark realistic bolder and polish tasks across fast, full-model, and full-context worker profiles with deterministic and independent quality gates.\n\nAI-assisted: OpenAI Codex. |
||
|
Paul Bakaus
|
02b1040280 |
Add Live performance lab and benchmarks
Measure framework and provider latency, enforce fidelity and cleanup gates, and publish reproducible results on the dev-only Live Lab.\n\nAI-assisted: OpenAI Codex. |
||
|
Paul Bakaus
|
2106a2881f |
Improve Live progressive responsiveness
Add transactional progressive publication, durable cancellation, responsive accept cleanup, and framework-safe Svelte and Nuxt previews.\n\nAI-assisted: OpenAI Codex. |
||
 Paul BakausandClaude Fable 5
|
bf2dd7ec13 |
skill v4.0.0-alpha.8: four visitor modes replace the brand/product bifurcation
Field report: impeccable SaaS-ified a developer docs page; the Opus galleries showed the same on an album page. Root cause: two registers force every surface into persuade-or-operate grammar. The register section now names the visitor's mode first (Persuade / Operate / Read / Experience) with mode-borrowing called out as the canonical failure, and PRODUCT.md's register field maps as family (brand = Persuade + Experience, product = Operate + Read) for compatibility. Read mode: comprehension deliverable, navigable structure, chrome out of the way. Experience mode: the artifact leads at every screen size. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> |
||
|
Paul BakausandClaude Fable 5
|
c3aba1e343 |
hooks: two-tier design hook — immediate per-edit rules + full-set Stop deep pass
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>
|
||
 Paul BakausandGitHub
|
da99645a58 |
Add OpenAI plugin submission bundle (#363)
* 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. |
||
|
Paul BakausandGitHub
|
fb6d3e9791 | Soften sheriff stale classification (#360) | ||
|
3e38e595c7 |
Add platform axis (web / ios / android / adaptive) (#269)
* Add a platform axis (web / ios / android / adaptive) to the skill Orthogonal to register: register decides whether design IS or SERVES the product; platform decides the delivery target and which native conventions apply. Set `## Platform` in PRODUCT.md; a missing field defaults to `web`, so legacy projects are unaffected. - extractPlatform() in skill/scripts/context.mjs (mirrors extractRegister); the CLI appends a NEXT STEP directive to read the native reference(s). `adaptive` (Flutter / RN / KMP shipping both iOS and Android) loads both ios.md and android.md. - New reference/ios.md (Apple HIG distilled) and reference/android.md (Material 3 distilled); reference/web.md is a thin pointer. The native refs frame register's role as narrow: platform conformance is the bar, brand lives in the expressive layer the platform gives you, never by breaking the rails. - Setup step 5 loads the native reference(s) when platform is native. Live mode and the detect CLI stay web-only, gated off ios/android/adaptive. - init asks platform right after register; adapt/audit/animate/layout carry short platform divergence notes; all secondary spots thread `adaptive`. - a11y stays in audit.md (loading it at design time makes output timid), so the native refs carry no Accessibility section; audit.md's Platform section owns native a11y. - Tests: extractPlatform unit coverage + skill-behavior scenario 10 (PRODUCT.md platform ios -> agent loads ios.md). Source-first: only skill/, scripts/, tests/, CLAUDE.md, NOTICE.md, the changelog and version are committed; the sync workflow regenerates the provider trees and ./plugin on merge. ios.md / android.md are distilled from the MIT-licensed ehmo/platform-design-skills; attribution in NOTICE.md. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * Address review: gate web tools on native platforms, drop version churn Maintainer-review fixes applied with AI assistance (Claude Code), on top of the rebased platform-axis commit: - Design hook (post-edit and Cursor pre-edit) now resolves the project platform via loadContext + extractPlatform and skips its web rule scan for ios / android / adaptive projects, so React Native / Flutter code never draws web-shaped findings (new hook-lib resolveProjectPlatform / isNativePlatform helpers, covered by unit and subprocess tests). - context.mjs CLI warns on an unrecognized ## Platform value (e.g. a toolchain name like `flutter`) instead of silently defaulting to web; extractRegister / extractPlatform now share extractSectionValue. - Removed reference/web.md: nothing loaded it; CLAUDE.md carries the "web has no extra rulebook" explanation. - init.md: skip live-mode config (Step 6) for native platforms; note the per-app PRODUCT.md pattern for repos shipping web + native. - android.md: Material-everywhere apps that also ship on iPhone still owe iOS OS guarantees (safe areas, Reduce Motion, edge-swipe back). - ios.md: reworded a design-time line that framed Dynamic Type as an accessibility check (a11y stays owned by audit.md). - Renumbered the new skill-behavior scenario to 14 after main's 10-13; updated CLAUDE.md scenario list; added android + unrecognized-value CLI test cases. - No version or changelog changes: versioning happens at release time. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * Tighten platform reference prose Editorial pass on the platform-axis text, applied with AI assistance (Claude Code) under maintainer direction: - ios.md / android.md rewritten to house style: single-line paragraphs (no hard wraps), one-sentence scope intro, deduplicated intro/slop-test, register-compression down to two sentences. In-file attribution paragraphs removed (NOTICE.md owns attribution); "read on top of the register reference" cruft removed (SKILL step 5 and the context.mjs directive already say it). Bans sections dropped: they restated the rules above them; the two additive items (tab-bar overload, hover-dependent affordances) folded into rules. ~40% smaller each. - Sub-command Platform sections (adapt, audit, animate, layout), SKILL step 5, init.md platform prose, and the context.mjs directive trimmed the same way. Build (prose validators, counts) and both test runners green. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * Treat an empty PRODUCT.md section as absent, not the next heading Copilot review catch: extractSectionValue read the next `## ...` heading as the section value when a field was left empty, which made the CLI warn "value `## Product Purpose` is not recognized". Stop at the next heading and return null instead. Regression tests for extractPlatform, extractRegister, and the CLI warning path. Applied with AI assistance (Claude Code) under maintainer direction. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * Only read a token list of both native targets as adaptive Bugbot catch: after the exact platform tokens failed, any Platform line containing the words ios and android was classified adaptive, so negated or explanatory prose ("web only, not ios or android") silently loaded both native refs and skipped the hook, with no warning. The combo parse now accepts only list separators and the two platform words; anything else falls through to the CLI's unrecognized-value WARNING. Regression tests added. Applied with AI assistance (Claude Code) under maintainer direction. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Co-authored-by: Paul Bakaus <paul.bakaus@gmail.com> |
||
|
Paul BakausandGitHub
|
149396d91f |
Add PR sheriff automation (#356)
* Add GitHub sheriff test coverage * Fix sheriff bot review feedback * Make sheriff maintainer waits explicit * Fix sheriff waiting label edge cases * Fix stale review blockers in sheriff * Fix sheriff contributor commit detection |
||
 Dustin PersekandGitHub
|
9f49cb85cc | Fix Google Fonts css2 family parsing (#349) | ||
|
|
44c27a72af |
Fix Codex plugin hook load failure; bump skill to 3.9.1 (#333)
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> |
||
|
Paul BakausandClaude Opus 4.8
|
a82f02d1a1 |
Fix skill release tweet CTA to npx impeccable install
The generated skill-release tweet pointed at the deprecated `npx skills add pbakaus/impeccable`; the canonical install/update path is `npx impeccable install`. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
Paul Bakaus
|
1a3f5d78bd | Fix Codex hook manifest schema | ||
 Abdul WahabandGitHub
|
b7d2ad5589 |
Fix: allow skill's bundled node helpers under strict-permission harnesses (#301) (#310)
The skill declared only `Bash(npx impeccable *)` in allowed-tools, but Setup and the no-arg menu shell out to `node {{scripts_path}}/*.mjs`. Under a default-deny Claude Code allowlist those calls are blocked, so Setup fails on context.mjs.
Add a provider-aware `Bash(node {{scripts_path}}/*)` entry and resolve {{scripts_path}} in the frontmatter (the build previously substituted it only in the body). Provider-aware rather than the hardcoded `.claude/...` path the issue suggested, since five providers honor allowed-tools with different script dirs.
|
||
|
|
776c019041 |
Add inline, in-file ignore comments for the detector (#283) (#285)
* Add inline, in-file ignore comments for the detector (issue #283) Complement config ignores with eslint-disable-style waivers that live where they apply and travel with the file when it leaves the repo. The motivating case is a generated/exported standalone document that legitimately uses a first-party brand typeface (on the overused-font list) and is later scanned without .impeccable/config.json present. Marker is comment-syntax-agnostic (works in //, /* */, <!-- -->, #, {/* */}): impeccable-disable <rule>[, <rule>...] [-- reason | : reason] whole file impeccable-disable-line <rule>... same line impeccable-disable-next-line <rule>... next line Bare directive or * means every rule; reason is optional and discarded at scan time. Behavior is suppression, for parity with config ignores. Implementation: - New pure module cli/engine/shared/inline-ignores.mjs (parser + filter, no Node deps). Static-HTML findings have no line number, so only whole-file directives apply there -- exactly the standalone-document case; the regex/text engine additionally honors the line-scoped forms. - Wired into detectText and detectHtml, gated by options.inlineIgnores. - detect CLI applies inline ignores by default; --no-inline-ignores skips just them, --no-config skips config and inline ignores together. Docs: config.md (new section), detector.md, README. skill/reference/hooks.md reversed its prior "inline comments are not supported" guidance and now points the agent to inline waivers for the travels-with-the-file case. Changelog 3.x. Tests: tests/inline-ignores.test.mjs (parser units, detectText/detectHtml integration, CLI end-to-end), registered in the detector suite. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * Reconcile design hook wording with inline ignores Two hook-side fixes prompted by review of the new inline-ignore feature: 1. Clean-ack steer line. The old line ("Keep typography hierarchy, spacing rhythm, and color contrast intentional on the next change.") read as an odd non-sequitur after "No anti-patterns." Reworded the whole clean ack to say what it means: a clean scan only clears the deterministic rule set, not overall design quality, so keep following the design system and skill guidance. Now: "Design hook scanned X. No deterministic design-quality issues found. That does not mean the design is good: keep following the project design system and the impeccable skill guidance." 2. Directive footer. It still told the agent "Do not add source comments such as `impeccable: ignore`; those pollute the code and do not suppress hook findings." That is now misleading: the hook runs the same detector engine as the CLI, which honors inline `impeccable-disable` waivers, so they DO suppress hook findings (consistent with config ignores, which filterFindings already honors). Reworded to: don't silence a real finding to skip fixing it; suppress only after the user confirms intent; prefer a config ignore, and reach for an inline `impeccable-disable <rule>` comment only when the waiver must travel with a file that leaves the repo. Added a hook test asserting an inline `impeccable-disable-line` comment makes the hook scan the file clean (locks in the cross-cutting behavior), and updated the clean-ack / footer assertions to the new wording. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * Address review on inline-ignores parser - Case-insensitive fast-path bail-out (Cursor): the cheap substring guard was lowercase-only while DIRECTIVE_RE has the `i` flag, so a mixed-case marker like `Impeccable-Disable` skipped parsing entirely and never suppressed. Switched the guard to `/impeccable-disable/i.test(...)`. Added a regression test. - Removed the unreachable `-->` branch from TRAILING_CLOSER_RE (Greptile): `--+>` already matches `-->` and any longer dash run. - Replaced the always-truthy lazy-match + `if (sep)` reason strip with an explicit first-separator slice (Greptile): clearer and drops the dead branch. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * Align inline-ignore line numbering with the detector (CRLF/CR endings) parseInlineIgnores split lines with /\r\n|\r|\n/, but detectText numbers lines with split('\n'). On classic `\r`-only endings the two diverged, so a disable-line / disable-next-line directive could key a different line than the finding it should waive (Cursor review). Split on '\n' only, matching the detector exactly; the directive regex already excludes '\r', so a trailing '\r' on CRLF files is never captured into the rule list. Added a CRLF regression test through the real detectText. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
Abdul WahabandGitHub
|
0306b41949 |
Add monorepo context support (#213)
Context files (PRODUCT.md / DESIGN.md) resolve child-first then fall back to the repo root, and /impeccable live lets the user pick a child app in a monorepo. Single-app behavior is unchanged. Closes #202. Co-Authored-By: abdulwahabone |
||
|
|
41ff946121 |
Add GitHub Copilot hook support (CLI + cloud agent) (#279)
* Add GitHub Copilot hook support (CLI + cloud agent) Wire the Impeccable design detector into GitHub Copilot's hook system so direct file edits get the same post-edit design feedback the Claude Code, Codex, and Cursor harnesses already receive. GitHub Copilot's contract differs from the existing harnesses (verified against Copilot CLI 1.0.63): - Repo-level manifest at `.github/hooks/impeccable.json` (read by both the CLI, once committed to the default branch, and the cloud/app agent). - Flat `postToolUse` entries with `bash`/`timeoutSec` and a full-match `matcher` regex; the file-editing tools are `edit` and `create`. - The stdin event uses camelCase `toolName`/`toolArgs`, where `toolArgs` is a JSON *string* carrying the touched file under `path`. - Context is injected via a top-level `additionalContext` string. Changes: - hooks.js: buildGitHubHooksManifest() + route `github` in hooksJsonFor(). - providers.js: emitHooks/hooksManifestRel for the github provider. - hook-lib.mjs: detect the github harness, normalize the camelCase event (parse the JSON-string toolArgs -> tool_input.file_path), and emit the `additionalContext` payload shape. - hook-admin.mjs / skills.mjs: install + idempotent-repair the `.github/hooks/impeccable.json` manifest (bash-aware marker stripping). - hooks.md: document GitHub Copilot as a supported harness. - Tests for the builder, routing, event normalization, and end-to-end run. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * Cover Copilot apply_patch edits in the hook (live-verified) The first cut matched only `edit|create`, the tool names `copilot -p` uses. A live trace against Copilot CLI 1.0.63 in an interactive session showed it edits files via `apply_patch`, whose toolArgs is a raw OpenAI-format patch string (`*** Begin Patch` / `*** Add File:`), not JSON. With the narrow matcher the hook command never ran. - hooks.js / hook-admin.mjs: matcher -> `edit|create|apply_patch`. - hook-lib.mjs: normalizeGitHubEvent now routes apply_patch's raw patch string into tool_input.command (reusing the existing parseApplyPatchPaths / resolveTargetFiles plumbing) and only JSON-parses toolArgs for the edit/create/view tools. tool_name is normalized to apply_patch so the patch path is extracted even if a future build relabels the tool. - Tests: apply_patch matcher assertions, event normalization, and an end-to-end runHook covering the interactive/cloud path. Verified live: a trusted interactive `apply_patch` edit fires the hook and returns the expected `additionalContext` design reminder. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * Address review feedback + add changelog entry - hook-lib.mjs (Bugbot, low): looksLikeApplyPatch no longer misroutes an edit/create event whose edited *content* contains apply_patch markers. A real apply_patch payload is a raw string that does not parse as JSON; an edit payload is a JSON object, so only non-JSON-object strings are treated as apply_patch. Edit events keep extracting `path`. Adds a regression test. - skills.mjs (Bugbot, medium): document why `.github` is intentionally excluded from hookScriptPathForProvider. Its hook manifest is committed and shared (read by the Copilot cloud agent and teammates), so the command must stay portable via `$(git rev-parse ...)`; rewriting it to a machine-local absolute path would break those. GitHub skills are project-scoped, so the project-relative path resolves. - changelog: add an Upcoming (v3.x placeholder) entry for the Copilot hook. Version is not bumped yet (batching with other changes). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
|
793feda5a0 |
Guard plugin/skill version drift in the build (issue #274) (#278)
* Guard plugin/skill version drift in the build (issue #274) The Claude Code marketplace installs from the committed ./plugin subtree, so a version disagreement between the hand-edited manifests and the generated subtree ships stale content under a wrong version. This is the class of bug reported in #274: a version bump that doesn't regenerate ./plugin (e.g. PR #252, where root plugin.json was 3.7.0 while plugin/.claude-plugin/plugin.json was still 3.6.0) merges a drift window onto main, and marketplace/Cowork installs pull the stale subtree. Add a build-time validator that treats root .claude-plugin/plugin.json as the source of truth and fails the build if any of these disagree: - .claude-plugin/marketplace.json plugins[0].version (hand-edited; the post-merge sync workflow never bumps versions, so it can't repair a mismatch here) - plugin/.claude-plugin/plugin.json version (generated subtree) - plugin/skills/impeccable/SKILL.md frontmatter version (bundled skill) It only fires on an inconsistent bump; PRs that don't touch versions keep every file in agreement and stay silent. The pure comparison lives in scripts/lib/validate-plugin-versions.js with direct unit coverage; build.js owns the logging and the non-zero exit. Documents the regenerate-on-bump step in CLAUDE.md's Versioning section. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * Harden version-drift collector against malformed/incomplete manifests Address Greptile review on #278: - Wrap every file read/parse in a sentinel helper (extractFromFile) so a half-edited manifest — the exact state during a version bump — yields a clean "could not parse (...)" diagnostic naming the file instead of a raw JSON.parse stack trace out of build(). - Report a present-but-malformed root plugin.json, or one missing its `version` field, as an explicit error. Previously `undefined` version short-circuited the build wrapper's `source == null` guard and passed silently. collectPluginVersions now returns an `errors` array; build.js fails on errors + mismatches combined, and only the genuinely-absent root manifest is a no-op skip. Adds 4 unit tests: malformed checked manifest, malformed root, missing version field, and the absent-root no-errors case. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * Make SKILL.md frontmatter version read CRLF-tolerant Address Cursor Bugbot review on #278: readSkillFrontmatterVersion only matched `\n` delimiters, while the shared parseFrontmatter in scripts/lib/utils.js accepts `\r?\n`. A bundled SKILL.md saved with CRLF line endings would parse to a null version and trip a false mismatch against root plugin.json even when the version line is correct. Match the shared parser's `\r?\n` tolerance and drop the `$` anchor on the version line (it would not match before a `\r`). Adds CRLF coverage for both readSkillFrontmatterVersion and collectPluginVersions. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * Re-trigger CI (no file change) CI did not fire for 5cda9f6b; force a fresh run on the current tree. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
Paul BakausandGitHub
|
8b0c895703 |
[codex] Fix CLI skill update detection (#257)
* Fix CLI skill update detection * Preserve linked skills during install refresh * Keep existing installs working offline * Respect provider scope during install refresh |
||
|
Paul BakausandClaude Opus 4.8
|
795e8ed5e5 |
fix(skill): bundle detector config dependency so critique runs (#254)
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> |
||
|
Paul BakausandGitHub
|
51d01e3a5f |
[codex] Add design-aware detector rules (#252)
* Add design-aware detector rules * Fix design-aware detector noise * Unify CLI and hook detector ignores * Fix remaining design-system review findings * Add detector ignore CLI * Fix design detector review findings * Fix design color source false positives * Fix core test suite registration * Add design-aware detector docs * Fix font priority design-system parsing * Fix color ignore value matching |
||
|
|
8cf2be110d |
feat(cli): interactive hook consent + unified .impeccable/config.json (#245)
* feat(cli): interactive hook consent + unified .impeccable/config.json Make the design-hook install a conscious choice and unify scattered config into one file. Interactive consent - On an interactive `skills install`/`update`, the CLI explains what the hook does and offers to install it (default yes), then records the per-developer decision in the gitignored `.impeccable/config.local.json`, so it never re-asks. A recorded decision or an already-installed hook short-circuits; `-y`/non-TTY keeps the historical install-by-default behavior; `--no-hooks` is a one-off skip that records nothing. The trigger keys on "is the hook installed?" + "is there a recorded decision?", not a brittle version check. Unified config - `.impeccable/config.json` (shared) and `.impeccable/config.local.json` (gitignored) now hold all Impeccable settings: hook settings under a `hook` key, plus top-level `updateCheck`. `/impeccable hooks` writes the `hook` subtree, preserving siblings. The hook runtime reads `hook.quiet` and `hook.auditLog`; context boot reads `updateCheck`. The legacy `IMPECCABLE_HOOK_DISABLED|QUIET|LOG` and `IMPECCABLE_NO_UPDATE_CHECK` env vars still work and override config; docs now lead with config and treat env vars as a legacy note. - No backward compat for the pre-unification `hook.json`/`hook.local.json` (the hook shipped an hour ago; nothing in the wild uses it). This repo's own hook config is migrated to `.impeccable/config.json`. The CLI and skill scripts are separate trees, so a small CLI-side config module (cli/lib/impeccable-config.mjs) duplicates the config-path and .git/info/exclude handling; comments flag the duplication. Tests: new cli config unit test; skills-cli consent tests (declined skips, accepted installs, --no-hooks records nothing); hook.test.mjs back-compat removed and quiet/auditLog-from-config + gitexclude coverage added. Full suite green. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(hooks): preserve sibling config fields + resolve audit log from event cwd (Bugbot) Two Bugbot findings: - High: `/impeccable hooks` edits replaced the whole `hook` object with the merge-helper output, dropping fields those helpers don't manage — so an `ignore-value --local` could wipe the recorded install consent and make the CLI re-prompt. writeConfig now merges over the existing hook object, keeping consent/quiet/auditLog. - Medium: config-based audit logging resolved hook.auditLog from process.cwd(), which can differ from the hook event's project root (and Cursor's pre-edit hook passed no cwd). The hook now stamps the resolved project root on the audit entry, and writeAuditLog reads config from entry.cwd when present. Tests: a /impeccable hooks edit preserves consent + quiet; writeAuditLog resolves config auditLog from entry.cwd, not the fallback cwd. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(hooks): resolve a relative auditLog path against the project root (Bugbot) A relative hook.auditLog was read from the project root but written relative to the hook process cwd, so when those differ the log went to the wrong place. writeAuditLog now resolves a relative target (from env or config) against the same project root it reads config from. Absolute and ~/ paths are unchanged. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * Fix hook consent recovery and smoke config * Fix hook consent explainer for Cursor * Fix empty hook target consent --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
|
9c0012d4e1 |
feat(hooks): package design hook in plugin, install to settings.local.json (#243)
* 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>
|
||
|
672517f76e |
Add automatic design hook install and exceptions (#170)
* 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 Bakaus
|
1863a44b23 | Clean up notes and tools | ||
|
Paul Bakaus
|
324cec73a4 | Reorganize contributor docs | ||
|
Paul BakausandGitHub
|
05f9797957 | Remove deprecated cleanup migration (#240) | ||
|
Paul BakausandGitHub
|
8735be3712 | Extract live browser DOM helpers (#239) | ||
|
Paul BakausandGitHub
|
f24f9fca8b | Refactor live browser script assembly (#235) | ||
|
Paul BakausandGitHub
|
b41836ce0e |
Extract manual Apply live server module (#233)
* Extract manual apply live server module * Fix core suite registry for docs integrity |
||
|
Paul Bakaus
|
325aeaf239 | Organize skill script support modules | ||
|
Paul Bakaus
|
972f5b18be | Improve generated output sync workflow | ||
|
Paul BakausandGitHub
|
9381269a82 | Fix Firefox DevTools extension paths (#231) | ||
|
3d1be6238c |
feat(extension): build and ship a Firefox add-on (#188)
Derive a Gecko-compatible manifest at build time and package extension-firefox.zip alongside the Chrome zip: - background service worker is declared as an event-page `scripts` entry (top-level listeners + in-memory Map run unchanged on Gecko) - browser_specific_settings.gecko with id, strict_min_version 140.0, and data_collection_permissions (required by AMO; honored on 140+) - packZip helper parameterized over cwd/excludes; `*.DS_Store` strips junk at every depth and .DS_Store is excluded from the staging copy - guard against a missing background.service_worker shape CI now builds the extension and runs a pinned `web-ext@8 lint` over the staged Firefox tree (innerHTML warnings are non-blocking); the unpacked staging dir is excluded from the uploaded artifact. The release script attaches both zips and points to AMO. Bumps the extension to v1.2.0 with a changelog entry. Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Co-authored-by: Paul Bakaus <paul.bakaus@gmail.com> |
||
  |
642adb5e84 |
chore(deps-dev): bump archiver from 7.0.1 to 8.0.0 (#224)
* chore(deps-dev): bump archiver from 7.0.1 to 8.0.0 Bumps [archiver](https://github.com/archiverjs/node-archiver) from 7.0.1 to 8.0.0. - [Release notes](https://github.com/archiverjs/node-archiver/releases) - [Changelog](https://github.com/archiverjs/node-archiver/blob/master/CHANGELOG.md) - [Commits](https://github.com/archiverjs/node-archiver/compare/7.0.1...8.0.0) --- updated-dependencies: - dependency-name: archiver dependency-version: 8.0.0 dependency-type: direct:development update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com> * Fix archiver 8 ZIP creation --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Paul Bakaus <paul.bakaus@gmail.com> |
||
|
Paul BakausandGitHub
|
82801a4894 |
[codex] Improve CI test coverage (#212)
* Improve CI test coverage * Stabilize live E2E harness * Shard live E2E CI * Cache live E2E CI dependencies * Stabilize live E2E smoke CI * Update generated live browser bundles * Tighten live E2E smoke runtime * Prevent live E2E smoke hangs * Stabilize live E2E CI coverage * Fix stale accept DOM cleanup * Regenerate live browser outputs |
||
|
Paul BakausandClaude Opus 4.8
|
4fda4a0ece |
Serve _data/api JSON in dev server
app.js fetches /_data/api/commands.json and patterns.json, but those are build artifacts written into site/public/_data/ by scripts/build.js. The plain `astro dev` server never runs that build, so the homepage 404'd on both in dev. Extract generateApiData into scripts/lib/api-data.js (shared by the build and a new scripts/gen-dev-api.mjs prebuild), and run the prebuild before astro dev so `bun run dev` serves the same payloads as production. site/public/_data/ stays gitignored. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
|
83dd99bf9f |
refactor(codex): drop the .codex/agents sidecar; rely on nested skill agents (#173)
Codex auto-discovers subagents bundled inside an installed skill's own agents/ folder, so the separate .codex/agents/*.toml sidecar was redundant. - cli: remove installCodexAgents/isCodexLikely and their install/update calls - context.mjs: remove the CODEX_AGENT_MISSING self-heal directive - build: drop codex agentFormat so no top-level .codex/agents is emitted; the nested in-skill .toml bundling is the whole delivery - remove the tracked .codex/agents/*.toml and the gitignore exception - docs + build.test.js updated for the nested layout - CLI patch version bump; skill version unchanged Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
Paul BakausandClaude Opus 4.8
|
92b744beb0 |
feat(site): new Neo Kinpaku social card, sitewide OG default
Replaces the retired light/magenta OG card with a brand-true Kinpaku card (lacquer ground, champagne Alumni Sans headline, kinpaku-gold accent, kintsugi-seam art). Headline: "Design fluency for every AI harness." Command count is read live from command-metadata.json. - scripts/generate-og-image.js: rewritten to render the Kinpaku card via Playwright at 2x and downscale with sharp; outputs og-image-v2.jpg - Base.astro: emit og:image + summary_large_image on every page with a sitewide default (was homepage-only); pages override via ogImage prop - og-image.jpg renamed to og-image-v2.jpg for cache-busting; index.astro reference updated - CLAUDE.md: document `bun run og-image` regeneration + cache-bust steps - .gitignore: ignore .og-build scratch Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
Paul BakausandClaude Opus 4.8
|
7253b3870a |
Deliver the Codex asset-producer subagent reliably (#161)
Codex reads custom subagents from .codex/agents/*.toml, a directory separate from where it reads skills (.agents/skills). Skill installers (notably `npx skills add`, see vercel-labs/skills#1290) only carry the skills/ subtree, so the asset-producer agent was never delivered. - build: bundle the codex .toml inside the skill dir for the variants Codex loads as a skill (agents, codex), so it travels with the skill. - cli: skills install/update now write .codex/agents/ for Codex-likely projects (a .agents target or a global ~/.codex); update heals a missing sidecar. Non-Codex projects are untouched. - context.mjs: on boot under a Codex install, emit a self-healing CODEX_AGENT_MISSING directive pointing at the bundled copy when the project's .codex/agents/ definition is absent. Self-resolves on copy. CLI 2.2.0 -> 2.3.0 (published). Skill stays 3.5.0 (unpublished); the note is folded into the existing 3.5.0 changelog entry. 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 |
||
|
Paul BakausandGitHub
|
e1d3ea0b6f |
Detector architecture v2: static engine, benchmarks, lab, and visual contrast (#156)
* Add detector benchmark lab and visual contrast fallback * Expand visual contrast fixture coverage * Add browser visual contrast fallback * Show visual contrast overlays in detector lab * Fix detector lab short viewport layout * Fix detector lab visual overlays * Add visual contrast to browser scan overlays * Avoid browser scroll jumps during visual contrast scans * Resolve visual contrast lazily on scroll * Refresh detector lab visual counts lazily * Update pnpm lockfile for static parser deps * Address Bugbot detector API comments * Report extension visual contrast errors * Refactor detector into engine modules * Address Bugbot detector comments * Fix latest Bugbot detector notes * Fix visual contrast fixture labels * Refine detector lab fixtures * Fix stale detector overlay references * Fix detector lab fixture URLs * Fix typography lab fixture highlights * Fix typography lab page-level signal * Fix visual overlay lifecycle cleanup * Remove dead spotlight timer cleanup * Make browser async APIs reject consistently |
||
|
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 |