mirror of
https://github.com/pbakaus/impeccable.git
synced 2026-09-12 22:26:38 +03:00
eaa70db4704afb5dcc7e13ce6ccd6d56fdb53118
17
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
  Forgeandplamb
|
5ce4a5c6b5 |
Add Hermes Agent as a supported provider
Impeccable now ships a Hermes-compatible bundle under dist/hermes/.hermes/skills/. Hermes reads the Agent Skills spec as-is, so the bundle uses the four spec frontmatter fields (name, description, version, license) plus metadata/compatibility and drops the Claude/Codex-specific extensions Hermes would silently ignore. The .hermes/skills/ tracked root and the regenerated pin.mjs mirrors will be produced by .github/workflows/sync-generated-output.yml after this lands; per AGENTS.md, generated harness churn stays out of feature PRs. What a Hermes user gets: - npx impeccable install --providers=hermes --scope=project writes .hermes/skills/impeccable/ into the cwd. - npx impeccable install --providers=hermes --scope=user honors $HERMES_HOME, so a profile-scoped install (HERMES_HOME=~/.hermes/profiles/forge) lands in the active profile's skills dir, not the default ~/.hermes/. Cross-home HERMES_HOME inheritance is ignored so test isolation holds. - /impeccable registers as a Hermes slash command and routes sub-commands via the Commands table in the skill body, since user-invocable / argument-hint are not honored by Hermes' skill loader. What a Hermes user does NOT get, and why: - No hook surface. Impeccable's PostToolUse/Stop anti-pattern detector on Claude/Codex/Cursor/Grok/GitHub does not translate to Hermes, which has no equivalent tool event lifecycle. The skill body still ships. - No writeOpenAIMetadata, agentFormat, or emitHooks. Hermes has no per-skill tool ACL, no subagent on-disk format, and no hooks.json equivalent. Verified end-to-end with hermes-agent v0.18.2: /impeccable polish and /impeccable critique both load reference/<command>.md and return the documented first step. parse_frontmatter accepts the generated SKILL.md, scan_skill_commands registers /impeccable, and the full default test suite passes (267/267 in the critical files; 0 fail across all suites). |
||
 Paweł Adamczak
|
bf957452c4 | Add Google Antigravity provider support | ||
  Paul BakausandClaude Fable 5
|
fa1177ed9c |
Ship native subagent definitions for GitHub Copilot and Cursor
The github and cursor providers previously received only the generated
degraded/ inline fallbacks. Both harnesses support real custom subagents,
so the build now emits them from the same skill/agents/ source:
- GitHub Copilot: .github/agents/impeccable-<role>.agent.md with portable
frontmatter only (name + description; omitting tools grants all tools,
and Copilot has no documented model/effort/max-turns equivalents).
- Cursor: .cursor/agents/impeccable-<role>.md with name, description,
model: inherit, is_background: false, and readonly derived from the
agent's tool list (true only for the finish reviewer, which declares
neither Write nor Edit). effort/max-turns are skipped because Cursor's
effort option requires an explicit model id.
Agent bodies now also resolve {{scripts_path}} and strip rule markers in
the shared agentFormat pipeline, which fixes the previously unresolved
placeholder in the emitted Claude asset-producer agent.
The CLI installer places agents per scope: project installs write
<repo>/.github/agents/ and <repo>/.cursor/agents/; user-level installs
write ~/.copilot/agents/ (Copilot's user dir, not ~/.github/) and
~/.cursor/agents/, overwriting stale impeccable-* copies. Because
Copilot lets user-level agents shadow same-named project ones, a project
install warns when shadowing copies exist; Cursor gives project agents
precedence, so no warning there.
new-work.md and visualize.md extend their harness-naming clauses with
the Cursor and Copilot invocations. The degraded/ fallbacks keep
shipping for surfaces where the model still fails to delegate.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
||
|
Paul Bakaus
|
06d21dea7d |
Add first-class Grok Build harness support
Emit .grok skills, agents, and PostToolUse/Stop hooks; wire the CLI installer and downloads; fix the plugin install path to #plugin; and document Grok in HARNESSES.md and README. AI assistance: written with Grok Build. |
||
  
|
83c37e453a |
feat: add Mistral Vibe harness support (#373)
* feat: add Mistral Vibe harness support
Mistral Vibe is Mistral AI's open-source CLI coding assistant that ships an
Agent Skills system at .vibe/skills/{name}/SKILL.md with slash-command
invocation, mapping cleanly onto the existing transformer pipeline. Adds
Vibe as a 14th first-class harness:
- PROVIDER_PLACEHOLDERS entry in scripts/lib/utils.js (model, config_file
= AGENTS.md, ask_instruction, command_prefix) mirroring the Qoder shape.
- PROVIDERS entry in scripts/lib/transformers/providers.js with configDir
.vibe and frontmatterFields user-invocable, license, compatibility,
metadata, allowed-tools (Vibe docs do not document argument-hint).
- transformVibe named export in scripts/lib/transformers/index.js for
test-spy parity.
- vibe added to FILE_DOWNLOAD_PROVIDER_CONFIG_DIRS so the download
endpoint accepts /api/download/skill/vibe/* and resolves to
dist/vibe/.vibe/.
- .vibe added to PROVIDER_DIRS, PROVIDER_ALIASES, PROVIDER_DISPLAY,
PROVIDER_INPUT_ORDER, GLOBAL_HARNESS_HINTS, and the normalizeForHash
provider regex in cli/bin/commands/skills.mjs so the CLI detects
existing Vibe installs.
- docs/HARNESSES.md updated: official docs row, frontmatter support
column, directory structure row, and Last verified date bumped.
- docs/DEVELOP.md, README.md (install instructions, providers list,
Supported Tools), .github issue/PR templates, sync-generated-output
workflow, and AGENTS.md extended with Vibe.
The dynamic providers.test.js loop picks up Vibe automatically; all 160
provider tests pass including the 14 new Mistral Vibe cases. The build
regenerates dist/vibe/.vibe/skills/impeccable/ with correct frontmatter
and .vibe-substituted script paths. Generated harness output is left
unstaged per the source-first policy; the sync-generated-output workflow
(now listing .vibe) will commit it back to main after merge.
Co-Authored-By: Mistral Vibe <noreply@mistral.ai>
* Address review on Vibe harness support
Verified the Vibe claims against the docs and the mistralai/mistral-vibe
source, then tightened what the tables say.
- model placeholder: 'Mistral', not 'the model'. Vibe is Mistral's own
first-party CLI, so it belongs with gemini -> Gemini and codex -> GPT
rather than with the provider-agnostic harnesses. SKILL.src.md's one
use of {{model}} now renders 'Mistral is capable of extraordinary
work.' instead of a lowercase 'the model'.
- Docs links point at the skills page, not the product overview, matching
every other row in both tables.
- disable-model-invocation is No, not TBD. The field appears nowhere in
Vibe's source; unknown frontmatter keys are silently ignored.
- Split the directory row into project and global scopes the way the Pi
row already does. Vibe reads .vibe/skills/ and .agents/skills/ at the
project level and ~/.vibe/skills/ and ~/.agents/skills/ globally; the
global .agents dir was missing, and project .agents/skills/ was sitting
in the global column. Sources: vibe/core/paths/_local_config_files.py
and vibe/core/config/harness_files/_paths.py.
- Restored 'Last verified' to 2026-04-28 and dated the Vibe row on its
own. Only that row was checked, and this file warns against trusting
stale claims, so a blanket re-date made ten other rows look fresher
than they are.
AI assistance: written with Claude Code.
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Mistral Vibe <noreply@mistral.ai>
Co-authored-by: Paul Bakaus <paul.bakaus@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
||
|
|
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> |
||
|
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 |
||
 
|
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> |
||
|
|
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 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 |
||
|
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 |
||
 VinaywhoandClaude Opus 4.7
|
4f66eb9c08 |
feat: add Qoder harness support (closes #76)
Qoder ships an Agent Skills system at .qoder/skills/{name}/SKILL.md with
slash-command invocation, mapping cleanly onto the existing transformer
pipeline. Adds Qoder as a 13th first-class harness:
- PROVIDER_PLACEHOLDERS entry in scripts/lib/utils.js (model, config_file,
ask_instruction, command_prefix) mirroring the Pi/Rovo Dev shape.
- PROVIDERS entry in scripts/lib/transformers/providers.js with
configDir=.qoder and the OpenCode/Claude Code frontmatter field set
(user-invocable, argument-hint, license, compatibility, metadata,
allowed-tools), since Qoder docs explicitly support those.
- transformQoder named export in scripts/lib/transformers/index.js for
test-spy parity (kept per CLAUDE.md guidance, even though build.js uses
PROVIDERS directly).
- .qoder added to PROVIDER_DIRS in bin/commands/skills.mjs so the CLI
detects existing Qoder installs.
- HARNESSES.md updated: official docs row, frontmatter support column,
directory structure row, and "Last verified" date bumped.
- DEVELOP.md reference link added.
- .github/ISSUE_TEMPLATE/feature_request.md and PULL_REQUEST_TEMPLATE.md
extended with Qoder in the provider checklists.
- Built .qoder/skills/impeccable/ tree committed (per CLAUDE.md harness
output dirs are tracked so npx skills can read them at install time).
The dynamic providers.test.js loop picks up Qoder automatically; all
non-prefix Qoder cases pass. The pre-existing Windows-only prefix-test
flake affects every provider equally and is out of scope for this PR.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
Paul BakausandClaude Opus 4.6
|
4092ee5f22 |
Move PID file to project root (.impeccable-live.json)
os.tmpdir() returns /var/folders/.../T/ on macOS, not /tmp/. The skill reference was telling the agent to cat /tmp/impeccable-live.json which didn't exist. Moving the PID file to the project root makes it predictable across platforms and project-scoped (multiple projects can run independent live sessions). Changed in: live-server.mjs, live-poll.mjs, live.md reference. Added .impeccable-live.json to .gitignore. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
 Dan Minshew
|
4bff8086d3 | Add harness support for RovoDev | ||
|
Paul BakausandClaude Opus 4.6
|
112317fd05 |
Rebase Trae support onto new factory architecture
Merge main (factory refactor) and adapt Trae to use the config-driven transformer system instead of a standalone trae.js file. Two provider entries (trae-cn, trae) replace the custom dual-directory logic. Also adds placeholderProvider support to the factory for providers that share placeholder configs but need separate output directories. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
Paul BakausandClaude Opus 4.6
|
2d4c7899dd |
Update provider configs from official docs, add HARNESSES.md reference
Research each harness's official documentation to verify and correct
provider frontmatter configs. Remove Codex/Gemini body transforms that
targeted their commands systems, not skills.
- Add compatibility + metadata to Cursor and Agents (Copilot)
- Add allowed-tools to Pi
- Remove Codex $ARGNAME and Gemini {{args}} body transforms
- Add HARNESSES.md as source of truth for harness capabilities
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
||
|
Paul BakausandClaude Opus 4.6
|
6de73abf1b |
Fix invalid YAML frontmatter and consolidate build transformers
Fixes #67: argument-hint values starting with [ were parsed as YAML flow sequences. Replace structured args arrays in source files with pre-formatted argument-hint strings, and quote values starting with [ or { in generateYamlFrontmatter(). Also consolidates 8 nearly-identical transformer files into a single config-driven createTransformer() factory. Adding a new provider now requires only a config object in providers.js instead of a full file. - Replace args source frontmatter with argument-hint strings - Add YAML quoting for values starting with [ or { - Add quote stripping to parseFrontmatter() for round-trip support - Create factory.js + providers.js, delete 8 individual transformers - Replace 16 explicit build.js calls with a loop over PROVIDERS - Consolidate 8 test files into 2 (factory + providers) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |