code-yeongyu/lazycodex

Before Instructions only → After Instructions only

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Instructions only

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Local scripts → After Network or broad shell

75b017473c71 → 49104cf38aa1

- 3 description: "Contribute a verified bug fix for LazyCodex, lazycodex-ai, omo-codex, bundled Codex skills, or upstream Codex CLI bugs. Opens a fork PR only for upstream openai/codex; LazyCodex-owned defects become a verified-fix issue on code-yeongyu/lazycodex (never a PR — that repo is a generated distribution mirror). Use when the user asks to fix a bug, contribute a bug fix, contribute to fix bug, open a PR for a bug, or debug and PR a LazyCodex/Codex defect."
+ 3 description: "Contribute a verified bug fix for LazyCodex, lazycodex-ai, omo-codex, bundled Codex skills, or upstream Codex CLI bugs. LazyCodex-owned defects get a fork PR against code-yeongyu/oh-my-openagent (base dev, source-tree paths under packages/omo-codex/plugin, with the changelog fragment); upstream Codex bugs get a fork PR against openai/codex. code-yeongyu/lazycodex is a generated distribution mirror and never gets a PR. Use when the user asks to fix a bug, contribute a bug fix, contribute to fix bug, open a PR for a bug, or debug and PR a LazyCodex/Codex defect."
- 14 - `code-yeongyu/lazycodex` for LazyCodex, lazycodex-ai, omo-codex, bundled skills, hooks, MCP wiring, installer behavior, marketplace sync, docs, or packaging. Deliverable: a verified-fix issue with the patch embedded. NEVER open a PR or push a branch against this repo — its contents are regenerated from the source tree on every release, so PRs there cannot be merged and will be closed.
+ 14 - `code-yeongyu/oh-my-openagent` (base branch `dev`) for LazyCodex, lazycodex-ai, omo-codex, bundled skills, hooks, MCP wiring, installer behavior, marketplace sync, docs, or packaging. Deliverable: a PR from a fork that edits the source-tree paths under `packages/omo-codex/plugin/` and carries the changelog fragment that repo requires. `code-yeongyu/lazycodex` is a distribution mirror generated from it (its `plugins/omo/` tree is synced from `packages/omo-codex/plugin/`), and the maintainer lands LazyCodex fixes from PRs against oh-my-openagent. NEVER open a PR or push a branch against `code-yeongyu/lazycodex`: its contents are regenerated on every release, so a PR there cannot be merged and will be closed. At most file a short issue there (symptom plus failing input) that links the oh-my-openagent PR; never embed a patch.
- 19 For `openai/codex`, create a fork PR that includes:
+ 19 For `code-yeongyu/oh-my-openagent` and `openai/codex`, create a fork PR that includes:
+ 27 - for `code-yeongyu/oh-my-openagent`: base `dev`, edits at `packages/omo-codex/plugin/...` (never the mirror's `plugins/omo/...` paths), and the changelog fragment `changes/unreleased/<pr-number>.md` that the repo's AGENTS.md describes
- 29 For `code-yeongyu/lazycodex`, create an issue (never a PR) that includes:
- 30 
- 31 - reproduction logs from before the fix
- 32 - the root cause with source evidence
- 33 - the verified patch as a unified diff, produced and tested in a fresh `${TMPDIR:-/tmp}` clone/worktree
- 34 - verification logs from after the fix
- 35 - the `lazycodex-generated` label and the footer tag `Tag: lazycodex-generated`
- 36 - cleanup of temporary worktrees and clones
+ 30 For `code-yeongyu/lazycodex`, deliver no PR and no patch. When a pointer is useful there, file a short issue (symptom plus failing input, the `lazycodex-generated` label and the footer tag `Tag: lazycodex-generated`) that links the oh-my-openagent PR.
- 42 3. Materialize the latest sources under `LAZYCODEX_SOURCE_ROOT="${LAZYCODEX_SOURCE_ROOT:-${TMPDIR:-/tmp}/lazycodex-sources}"`, then decide the target repository. Sync both checkouts on every run and compare them before choosing. Validate cached checkouts before reuse so an incomplete `.git` directory cannot route the fix to the wrong repo:
+ 36 3. Search for an existing lead PR before anything is filed. Search your own open PRs across all repos by the symptom or the changed symbol, then the target repo's open PRs, so a fix that already exists is found first and gets new evidence instead of a duplicate:
+ 37 
+ 38 ```bash
+ 39 gh search prs --author @me --state open "<symbol or error text>"
+ 40 gh search prs --repo code-yeongyu/oh-my-openagent --state open "<symbol or error text>"
+ 41 ```
+ 42 
+ 43 If a matching open PR exists, add evidence to it or report it instead of opening a second one.
+ 44 4. Materialize the latest sources under `LAZYCODEX_SOURCE_ROOT="${LAZYCODEX_SOURCE_ROOT:-${TMPDIR:-/tmp}/lazycodex-sources}"`, then decide the target repository. Sync the checkouts on every run and compare them before choosing. Validate cached checkouts before reuse so an incomplete `.git` directory cannot route the fix to the wrong repo:
+ 90 sync_latest_source code-yeongyu/oh-my-openagent "$LAZYCODEX_SOURCE_ROOT/oh-my-openagent-source"
- 90 4. Create a fresh temporary clone and branch under `${TMPDIR:-/tmp}`. Do not modify the user's current repository for the target fix unless the current repository is itself the requested target and the user explicitly asked for local edits. Apply those resource rules at clone/worktree creation.
- 91 
- 92 ```bash
- 93 TARGET_REPO="code-yeongyu/lazycodex" # or openai/codex
+ 93 5. Create a fresh temporary clone and branch under `${TMPDIR:-/tmp}`. Do not modify the user's current repository for the target fix unless the current repository is itself the requested target and the user explicitly asked for local edits. Apply those resource rules at clone/worktree creation.
+ 94 
+ 95 ```bash
+ 96 TARGET_REPO="code-yeongyu/oh-my-openagent" # or openai/codex
- 106 5. Reproduce the bug in the worktree through the real surface. Save exact command output to `${TMPDIR:-/tmp}/lazycodex-fix-<short-slug>-repro.log`.
- 107 6. Write or update a failing regression test before production changes. Confirm it fails for the bug, not for a missing fixture or typo.
- 108 7. Implement the smallest correct fix. Avoid refactors unless the fix cannot be made safely without one.
- 109 8. Run the regression test, adjacent tests, and the smallest real-surface QA command that proves the user-visible behavior changed.
- 110 9. Commit the verified fix in the worktree. Inspect the status first so the delivered diff cannot be empty or stale:
+ 109 6. Reproduce the bug in the worktree through the real surface. Save exact command output to `${TMPDIR:-/tmp}/lazycodex-fix-<short-slug>-repro.log`.
+ 110 7. Write or update a failing regression test before production changes. Confirm it fails for the bug, not for a missing fixture or typo.
+ 111 8. Implement the smallest correct fix. Avoid refactors unless the fix cannot be made safely without one.
+ 112 9. Run the regression test, adjacent tests, and the smallest real-surface QA command that proves the user-visible behavior changed.
+ 113 10. Commit the verified fix in the worktree. Inspect the status first so the delivered diff cannot be empty or stale:
- 119 10. Build the delivery body for the target:
- 120    - `openai/codex`: generate the PR body with `scripts/create-pr-body.mjs`.
- 121    - `code-yeongyu/lazycodex`: export the verified patch and write the issue body from the Verified-Fix Issue Template below:
- 122 
- 123 ```bash
- 124 PATCH_FILE="${TMPDIR:-/tmp}/lazycodex-fix-<short-slug>.patch"
- 125 git diff "origin/$BASE_BRANCH"..HEAD > "$PATCH_FILE"
- 126 ```
- 127 
- 128 11. Ensure the generated label exists when the target repo allows label management. Keep the footer tag even when label creation is unavailable:
+ 122 11. Build the delivery body for the target:
+ 123    - `code-yeongyu/oh-my-openagent` and `openai/codex`: generate the PR body with `scripts/create-pr-body.mjs` (set `targetRepository` to the repo you are filing against).
+ 124    - `code-yeongyu/oh-my-openagent` only: add the changelog fragment `changes/unreleased/<pr-number>.md` once the PR number exists, in the format `docs/reference/changelog-fragments.md` of that repo defines, and commit it to the same branch.
+ 125 
+ 126 12. Ensure the generated label exists when the target repo allows label management. Keep the footer tag even when label creation is unavailable:
- 139 12. Deliver the fix.
- 140    - `code-yeongyu/lazycodex`: create the verified-fix issue. Never push a branch to this repo and never run `gh pr create` against it:
+ 137 13. Deliver the fix.
+ 138    - `code-yeongyu/oh-my-openagent`: fork, push the branch to the fork, and create the PR against base `dev`. Never push a branch to or run `gh pr create` against `code-yeongyu/lazycodex`:
+ 139 
+ 140 ```bash
+ 141 gh repo fork code-yeongyu/oh-my-openagent --remote --remote-name fork
+ 142 GH_USER="$(gh api user --jq .login)"
+ 143 git push -u fork "$BRANCH_NAME"
+ 144 gh pr create --repo code-yeongyu/oh-my-openagent --base dev --head "$GH_USER:$BRANCH_NAME" --title "<short fix title>" "${LABEL_ARGS[@]}" --body-file "$PR_BODY"
+ 145 ```
+ 146 
+ 147    - `code-yeongyu/lazycodex` (optional pointer): a short issue with the symptom, the failing input and a link to the oh-my-openagent PR, never a diff:
- 156 13. Finish cleanup per Task resources. Run this only when that rule permits removing the worktree and run root; otherwise retain them and report the outstanding cleanup todo:
+ 163 14. Finish cleanup per Task resources. Run this only when that rule permits removing the worktree and run root; otherwise retain them and report the outstanding cleanup todo:
- 169 ## Verified-Fix Issue Template (code-yeongyu/lazycodex)
- 170 
- 171 Write the issue body in English. Embed the patch verbatim so a maintainer can apply it to the source tree:
+ 176 ## Pointer Issue Template (code-yeongyu/lazycodex, optional)
+ 177 
+ 178 Write the issue body in English. It names the symptom and the failing input and links the oh-my-openagent PR; the fix itself lives in that PR:
- 174 ## Problem Situation
+ 181 ## Symptom
- 177 ## Reproduction Logs
- 178 [Exact failing command and relevant log excerpt.]
- 179 
- 180 ## Root Cause
- 181 [Confirmed cause with runtime and source evidence.]
- 182 
- 183 ## Verified Fix
- 184 [What changed and why this is the smallest correct fix.]
- 185 
- 186 ```diff
- 187 [Contents of $PATCH_FILE.]
- 188 ```
- 189 
- 190 ## Verification
- 191 - [RED test output or repro before the fix]
- 192 - [GREEN test output after the fix]
- 193 - [Manual QA command and result]
- 194 
- 195 ---
- 196 This fix was debugged, implemented, and verified with [LazyCodex](https://github.com/code-yeongyu/lazycodex).
+ 184 ## Failing Input
+ 185 [Exact failing command and the shortest log excerpt.]
+ 186 
+ 187 ## Fix
+ 188 [Link to the code-yeongyu/oh-my-openagent PR.]
+ 189 
+ 190 ---
+ 191 This issue was generated by LazyCodex.

This preview is limited. See the complete change on GitHub.

Compare on GitHub

Before Not checked yet → After Local scripts

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Instructions only → After Network or broad shell

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Instructions only

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Instructions only → After Network or broad shell

75b017473c71 → 49104cf38aa1

- 12 - `code-yeongyu/lazycodex` for LazyCodex, lazycodex-ai, omo-codex, marketplace, bundled skill, hook, MCP, installer, or packaging bugs. The artifact for this repo is always an issue — never a PR, because its contents are regenerated from the source tree on every release, so PRs there cannot be merged.
- 13 - `openai/codex` for upstream Codex CLI bugs that reproduce without LazyCodex or are caused by Codex core behavior. This is the only repo where this skill may create a PR.
+ 12 - `code-yeongyu/lazycodex` for LazyCodex, lazycodex-ai, omo-codex, marketplace, bundled skill, hook, MCP, installer, or packaging bugs. The artifact for this repo is always an issue, never a PR: it is a distribution mirror generated from `code-yeongyu/oh-my-openagent` (its `plugins/omo/` tree is synced from `packages/omo-codex/plugin/`), so PRs there cannot be merged. A fix for these defects goes to `code-yeongyu/oh-my-openagent` as a fork PR (base `dev`, source-tree paths, changelog fragment) through `$lcx-contribute-bug-fix`; the mirror issue stays short and links that PR.
+ 13 - `openai/codex` for upstream Codex CLI bugs that reproduce without LazyCodex or are caused by Codex core behavior. A PR may be created here.
- 93 7. Search for an existing issue in the selected repo before creating a new one. Search the other repo too when the ownership boundary is close:
+ 93 7. Search for an existing issue or lead PR before creating anything new. Search your own open PRs across all repos first (`gh search prs --author @me --state open "<symbol or error text>"`), then the selected repo, and the other repo too when the ownership boundary is close:
- 114 11. Create a PR only when the target repo is `openai/codex` AND the user asked for a PR, the fix is already implemented on a branch, or the smallest correct fix can be safely made there. Never create a PR or push a branch against `code-yeongyu/lazycodex` — always file an issue there, embedding the verified patch in the Proposed Fix section when one exists. Apply the `lazycodex-generated` label to every PR created by this skill. Otherwise create an issue with fix guidance.
+ 114 11. Create a PR only when the target repo is `openai/codex` or `code-yeongyu/oh-my-openagent` (the source of the LazyCodex mirror, base `dev`) AND the user asked for a PR, the fix is already implemented on a branch, or the smallest correct fix can be safely made there; use `$lcx-contribute-bug-fix` for the fix workflow. Never create a PR or push a branch against `code-yeongyu/lazycodex`: file a short issue there (symptom and failing input) that links the oh-my-openagent PR, with no patch. Apply the `lazycodex-generated` label to every PR created by this skill. Otherwise create an issue with fix guidance.
- 179 Use this only when a PR is the right artifact, which is only ever for `openai/codex`:
+ 179 Use this only when a PR is the right artifact, which is only ever for `openai/codex` or `code-yeongyu/oh-my-openagent`:
- 229 For a PR from a branch pushed to a fork — `openai/codex` only, never `code-yeongyu/lazycodex`:
+ 229 For a PR from a branch pushed to a fork, against `openai/codex` or `code-yeongyu/oh-my-openagent` (never `code-yeongyu/lazycodex`):
- 262 - a PR or pushed branch targeting `code-yeongyu/lazycodex` — file the issue instead, always
+ 262 - a PR or pushed branch targeting `code-yeongyu/lazycodex` — send a fix PR to `code-yeongyu/oh-my-openagent` and keep any mirror issue short, always

Compare on GitHub

Before Not checked yet → After Instructions only

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Instructions only → After Instructions only

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Instructions only

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Instructions only → After Instructions only

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Instructions only

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Local scripts → After Network or broad shell

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Local scripts

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Local scripts → After Network or broad shell

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Local scripts

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Network or broad shell → After Network or broad shell

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Network or broad shell

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Network or broad shell → After Network or broad shell

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Network or broad shell

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Network or broad shell → After Network or broad shell

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Network or broad shell

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Local scripts → After Network or broad shell

75b017473c71 → 49104cf38aa1

- 29 python3 scripts/find-agent-sessions.py list --limit 20
- 30 python3 scripts/find-agent-sessions.py find "commit" --from 7d --platform senpi --platform opencode
- 31 python3 scripts/find-agent-sessions.py find "proxy" --platform openclaw --platform droid --platform amp
- 32 python3 scripts/find-agent-sessions.py find "refactor" --platform oh-my-pi --platform gajae-code
- 33 python3 scripts/find-agent-sessions.py find --query "deploy" --query "token usage" --workers 64
- 34 python3 scripts/find-agent-sessions.py find --query "opencode bug" --query "fix opencode" --query "OpenCode parent session" --include-subagents --workers 64
- 35 python3 scripts/find-agent-sessions.py read <session-id>
+ 29 python3 -B scripts/find-agent-sessions.py list --limit 20
+ 30 python3 -B scripts/find-agent-sessions.py find "commit" --from 7d --platform senpi --platform opencode
+ 31 python3 -B scripts/find-agent-sessions.py find "proxy" --platform openclaw --platform droid --platform amp
+ 32 python3 -B scripts/find-agent-sessions.py find "refactor" --platform oh-my-pi --platform gajae-code
+ 33 python3 -B scripts/find-agent-sessions.py find --query "deploy" --query "token usage" --workers 64
+ 34 python3 -B scripts/find-agent-sessions.py find --query "opencode bug" --query "fix opencode" --query "OpenCode parent session" --include-subagents --workers 64
+ 35 python3 -B scripts/find-agent-sessions.py read <session-id>
- 38 Use `python` instead of `python3` on systems where that is the available executable.
+ 38 Use `python` instead of `python3` on systems where that is the available executable. Keep `-B`: the skill can live inside a signed app bundle, and Python bytecode caches written next to the scripts break its signature.
- 110 python3 scripts/find-agent-sessions.py list --platform codex --from 7d
- 111 python3 scripts/find-agent-sessions.py find "deploy" --platform codex
- 112 python3 scripts/find-agent-sessions.py read <session-id> --platform codex
+ 110 python3 -B scripts/find-agent-sessions.py list --platform codex --from 7d
+ 111 python3 -B scripts/find-agent-sessions.py find "deploy" --platform codex
+ 112 python3 -B scripts/find-agent-sessions.py read <session-id> --platform codex

Compare on GitHub

Before Not checked yet → After Local scripts

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Instructions only → After Instructions only

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Instructions only

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Network or broad shell → After Network or broad shell

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Network or broad shell

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Network or broad shell → After Network or broad shell

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Network or broad shell

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Network or broad shell → After Network or broad shell

75b017473c71 → 49104cf38aa1

- 8 This file is a router over `references/`; the rules live there. The flow is brief -> build -> subtract -> verify. The bar is restraint with a visible hierarchy: one primary action, the important thing first, nothing on the screen without a job. A quiet, correct screen that holds its hierarchy at 390 and 1440 in both themes is a finish. Atmosphere, motion, and award-grade surface work are opt-in: build them when the brief asks (a named brand, "premium", "make it stunning", a marketing page), never by default for an internal tool, dashboard, admin screen, report, or figure.
+ 8 This file is a router over `references/`; the rules live there. The flow is ground -> brief -> build -> subtract -> verify. The bar is restraint with a visible hierarchy: one primary action, the important thing first, nothing on the screen without a job. A quiet, correct screen that holds its hierarchy at 390 and 1440 in both themes is a finish. Atmosphere, motion, and award-grade surface work are opt-in: build them when the brief asks (a named brand, "premium", "make it stunning", a marketing page), never by default for an internal tool, dashboard, admin screen, report, or figure.
+ 18 | A new screen or flow, a redesign ("this looks bad", "make it better"), or design-system creation or rework | ALSO `references/design/grounding.md` (step 0 below). |
- 25 | Writing or modifying frontend code; auditing performance, SEO, accessibility, quality | `references/perfection/README.md` (+ `react-perf-tooling.md` before any React audit). Lighthouse 100 in every category on real Playwright Chromium, won in the architecture. Design and perfection load together for implementation work. |
+ 26 | Writing or modifying frontend code; auditing performance, SEO, accessibility, quality | `references/perfection/README.md`, `references/perfection/craft-floor.md`, and `references/perfection/detect.md` (+ `react-perf-tooling.md` before any React audit). Lighthouse 100 in every category on real Playwright Chromium, won in the architecture. Design and perfection load together for implementation work. |
+ 32 
+ 33 ## 0. Ground: know the product and the bar before designing
+ 34 
+ 35 For a new screen or flow, a redesign, or design-system work, run `references/design/grounding.md` first. It reads the guideline source in full, defines the ideal state for the product's personas and journeys, and writes every gap into a ledger. The brief and the build close rows of that ledger. A small change reads the ledger when `DESIGN.md` has one.
- 46 Take the branch in `references/design/README.md` Phase 0 first (a small change on a surface with no `DESIGN.md` follows its small-change rule), and on a React project its Phase 0.5 tooling check: `DESIGN.md` (or, under the small-change rule, the styled sibling) exists before components do, and every colour, size, and spacing value traces to a token in it. Then build to these rules; `/visual-qa` verifies them afterwards and should find nothing new.
+ 51 Take the branch in `references/design/README.md` Phase 0 first (a small change on a surface with no `DESIGN.md` follows its small-change rule), and on a React project its Phase 0.5 tooling check: `DESIGN.md` (or, under the small-change rule, the styled sibling) exists before components do, and every colour, size, and spacing value traces to a token in it. A new system is built in this order: colour roles in both themes, then type and spacing, then components, which start from shadcn/ui anatomy (or the project's own kit) restyled with the tokens, never invented shapes. Then build to these rules; `/visual-qa` verifies them afterwards and should find nothing new.
- 48 - **Hit targets.** Touch layouts: at least 44x44 pt (44 CSS px) per interactive element, 8-12 pt between neighbours. Pointer-only: about 10 px beyond the glyph. Grow the hit area with padding or a pseudo-element, never the glyph; adjacent bar buttons share continuous hit areas.
+ 53 - **Hit targets.** Touch layouts: at least 44x44 pt (44 CSS px) per interactive element, 8-12 pt between neighbours. Pointer-only: at least 24x24 CSS px (WCAG 2.5.8), about 10 px beyond the glyph. Grow the hit area with padding or a pseudo-element, never the glyph; adjacent bar buttons share continuous hit areas.
- 50 - **States.** A control ships with hover, pressed, focus-visible, and disabled states beside its default. A data view ships empty (offering the next action), loading (a placeholder at once, a spinner only past about a second), error (cause beside the object), and offline.
- 51 - **Keyboard.** Every action reachable in reading order with a visible focus ring; Escape closes the topmost overlay; Enter triggers the non-destructive default; standard shortcuts keep their meaning; icon-only controls carry an accessible name and a tooltip.
+ 55 - **States.** A control ships with hover, pressed, focus-visible, and disabled states beside its default. It keeps one box in every state: the label, icon, and spinner swap inside slots that exist in all states (a min-width sized to the longest label, a spinner overlaying the hidden label), so width, height, and padding never change when the state does, and an arrow or spinner never adds padding when it appears. A data view ships empty (offering the next action), loading (a placeholder at once, a spinner only past about a second), error (cause beside the object), and offline.
+ 56 - **Keyboard.** Every action reachable in reading order with a visible focus ring that no sticky bar or overlay covers; Escape closes the topmost overlay; Enter triggers the non-destructive default; standard shortcuts keep their meaning; icon-only controls carry an accessible name and a tooltip.
+ 59 - **Browser surfaces.** Text selection, the caret, visible scrollbars, the focus ring, link underline offset, and tabular numerals are themed from the palette in both themes; none ships as the browser default. `references/perfection/craft-floor.md` has the property for each.
+ 60 - **Type and spacing floor.** Each heading step (display to h3, and the smallest heading to body) differs by at least 1.25x, and body-family roles that sit closer also differ by weight, colour or case; the space above a section heading is at least 1.5x the space below it; the gap between groups is at least 2x the gap inside one; body text runs 65-75 characters per line on desktop; display type stays at or under 6rem and tracking at or above -0.04em unless the chosen style route sets its own. Check computed values, not the source.
- 61 - **No coloured bar on one side of a box, rounded or square, and no accent outline on a rounded card, decorative or state.** A card, callout, warning, cover block, stat tile, testimonial, alert, or list row never carries a coloured stripe on one side: `border-left: 4px solid <accent>` or `border-l-4 border-indigo-500`, a coloured `::before`/`::after` bar inside it, an inset `box-shadow` stripe, or a hard-stop gradient band or gradient `border-image` along one edge. A rounded card never wears a 2px-or-wider accent outline either (`border: 2px solid var(--primary)`, `ring-2 ring-indigo-500`, an inset ring). Both read as generated whether they decorate the box or mark it selected, focused, or active, and an accent underline under a heading, tab, or link counts too: use a neutral 1px rule, or set the text itself in the accent ink. Give the card its identity another way: a tonal surface (one ink at a low alpha, or the next step of the surface ramp), an eyebrow or heading set in the accent ink, a leading glyph, or more space between groups. Encode state with one ink at many alphas (hover/selected/active washes), a check glyph for selection, and tonal layering for focus. The coloured edges that stay allowed: keyboard `focus-visible` rings, validation states on form inputs, neutral 1px hairlines and dividers between rows or sections, table rules, and a blockquote's neutral rule. This covers pre-existing instances on any surface you touch.
+ 68 - **No coloured bar on one side of a box, rounded or square, and no accent outline on a rounded card, decorative or state.** A card, callout, warning, cover block, stat tile, testimonial, alert, or list row never carries a coloured stripe on one side: `border-left: 4px solid <accent>` or `border-l-4 border-indigo-500`, a coloured `::before`/`::after` bar inside it, an inset `box-shadow` stripe, or a hard-stop gradient band or gradient `border-image` along one edge. A rounded card never wears a 2px-or-wider accent outline either (`border: 2px solid var(--primary)`, `ring-2 ring-indigo-500`, an inset ring). Both read as generated whether they decorate the box or mark it selected, focused, or active, and an accent underline under a heading, tab, or link counts too: use a neutral 1px rule, or set the text itself in the accent ink. Give the card its identity another way: a tonal surface (one ink at a low alpha, or the next step of the surface ramp), a heading set in the accent ink, a leading glyph, or more space between groups. Encode state with one ink at many alphas (hover/selected/active washes), a check glyph for selection, and tonal layering for focus. The coloured edges that stay allowed: keyboard `focus-visible` rings, validation states on form inputs, neutral 1px hairlines and dividers between rows or sections, table rules, and a blockquote's neutral rule. This covers pre-existing instances on any surface you touch.
+ 70 - **Detect after the build renders.** Once the page renders, run the detect SDK on it at 1440 and 390 with reflow on (`references/perfection/detect.md`): `detectPage({ kind: "url", url }, { reflow: true })` from code, or `bun $SKILL_DIR/scripts/detect/cli.ts --reflow <url-or-html-files>`. It reads the rendered page (contrast on the painted background, type scale, heading order, overflow, decoration and copy tells). Fix every error and warning before `/visual-qa`; record a decision for each advisory.
+ 73 - **No invented proof.** Testimonials, quotes, customer logos, ratings, user counts, and prices come from the project or stay out. A section that needs proof the project does not have is cut, or ships as an empty slot labelled for the owner to fill; a "sample" testimonial is still a fabricated one.
+ 74 - **No prop decoration.** A device tilted for effect, a floating reassurance card, decorative coordinates, sparkles, and ornaments that say nothing about the product are the generated version of "premium". A product preview shows a real state of the product, with its text readable at the rendered size.
+ 75 - **No repeated formula.** A treatment that carries one heading (a serif line with an italic accent phrase, a gradient word, a headline-subtitle pair) becomes a template when every section repeats it; so does one image reused across sections. Use each once, where it means something.
+ 78 - **No dated or borrowed surface.** Glass and blur panels (they read as a clone of a popular open-source chat app), neumorphism, mesh-gradient heroes, heavy drop shadows, and 2019-era SaaS illustration date a draft on sight. Surfaces come from `DESIGN.md` section 7; a material ships only when the brief or a concrete reference supplies it.
+ 79 - **No generated scaffold.** No kicker label above a heading, no icon tile stacked over a heading in a grid of same-size cards, no hero metric (a giant number with a small label and supporting stats), no card inside a card, no neutral gray text on a coloured surface, no monospace as a "technical" costume, and no zero-offset coloured glow standing in for a shadow. `references/perfection/craft-floor.md` gives the replacement for each, and says when the brief or its chosen route brings one back.
- 71 After the draft renders and the lint exits 0, walk every element on the screen and ask what the user could not do or know without it. No answer: delete it, whatever the reference or the previous version showed. Then open the brief's required-content list and confirm every item is still on the screen by name, with its own control or field. Subtraction that merges two required inputs into one, drops a datum, or shortens required copy is a regression, not a cleanup. Record what you removed under "Left out on purpose".
+ 84 After the draft renders and the lint exits 0, walk every element on the screen and ask what the user could not do or know without it. No answer: delete it, whatever the reference or the previous version showed. Then open the brief's required-content list and confirm every item is still on the screen by name, with its own control or field. Subtraction that merges two required inputs into one, drops a datum, or shortens required copy is a regression, not a cleanup. Record what you removed under "Left out on purpose". Then count the controls: a secondary action most visits do not need moves into a menu or to the object it acts on, and groups separate by whitespace, not by boxes and borders. Fewer controls with room around them is the target.
- 75 Done is the `/visual-qa` gate, not your own glance. It owns the visual checks; this skill keeps build rules. Hand it the brief (B7 checks the primary action and priorities), the `Layout:` line (A12), the required-content list (Pass A), and, for a changed surface, the `before` set so it runs Before/after mode and the pair shows what improved. Its review loop is bounded (its Step 4 sets the budget): defects earn another round, and taste findings are recorded and stop it. A concrete reference runs reference-fidelity mode. Pass design-system decisions, evidence, and unresolved debt into `/review-work` for significant work.
+ 88 Done is the `/visual-qa` gate, not your own glance. It owns the visual checks; this skill keeps build rules. Hand it the brief (B7 checks the primary action and priorities), the `Layout:` line (A12), the required-content list (Pass A), and, for a changed surface, the `before` set so it runs Before/after mode and the pair shows what improved. Its review loop is bounded (its Step 4 sets the budget): defects earn another round, and taste findings are recorded and stop it. A concrete reference runs reference-fidelity mode. Fix passes are scoped: after the first build, each fix names one change and the regions it owns (a token fix may own every region) and leaves everything else untouched, because a whole-page "make it better" pass breaks what was already right. Pass design-system decisions, evidence, and unresolved debt into `/review-work` for significant work.
+ 89 
+ 90 Every UI or design-system deliverable states its WCAG 2.2 AA result. Probe the built surface in the real browser and put a table in the deliverable (PR body, change description, or reply): one row per item below, PASS / FAIL / N/A, with its evidence. A FAIL is fixed, or recorded as accepted debt in `DESIGN.md` section 8 with the user's sign-off.
+ 91 
+ 92 - **Contrast** (1.4.3, 1.4.11): text 4.5:1 (large 3:1), icons and control edges 3:1, both themes, placeholder text included.
+ 93 - **Focus** (2.4.7, 2.4.11): Tab through every control and screenshot each ring; none missing, none entirely hidden by a sticky bar or overlay (the AA line; the target is none covered at all).
+ 94 - **Target size** (2.5.8): every pointer target at least 24x24 CSS px, or an undersized one whose 24 px circle, centred on it, intersects no other target and no other undersized target's circle. Exempt: inline links in a sentence, targets the browser draws unstyled, a target with a same-function equivalent that passes, and a size the information requires.
+ 95 - **Keyboard** (2.1.1, 2.1.2): every action works from the keyboard, and focus never gets trapped.
+ 96 - **Reflow and text spacing** (1.4.10, 1.4.12): at 320 CSS px no content scrolls sideways, except content that needs two dimensions (a data table, a map, a diagram); with line-height 1.5, paragraph spacing 2em, letter spacing 0.12em, and word spacing 0.16em applied, nothing clips or overlaps.
+ 97 - **Dragging, authentication, help, entry** (2.5.7, 3.3.8, 3.2.6, 3.3.7): a single-pointer alternative for every drag, no cognitive test to sign in unless an alternative exists, paste and password managers work, or the test is object or personal-content recognition, help in the same place on every page, nothing asked twice in one flow. N/A only when the surface has none of these.
+ 98 - **State-stable controls** (build rule above): read each control's `getBoundingClientRect()` in every state (idle, hover, loading, success, disabled); width and height match across states.
+ 99 - **System and surfaces** (build rules above): colour roles exist in `DESIGN.md` before any component; each component names its shadcn/ui or project-kit source; a grep of the shipped styles finds no `backdrop-filter`, neumorphic double shadows, or mesh-gradient backgrounds unless the brief or a concrete reference supplies them.
+ 100 
+ 101 On the grounded path, close the gap ledger row by row: each fixed gap has its before/after pair and the check that proves it.
- 79 `design/` holds one architecture file (`design-system-architecture.md`: the `DESIGN.md` structure, 8 sections plus a greenfield-only Research Log), 12 taste skills (Layer A: how to execute), 70 brand design systems (Layer B: what it looks like), and the project-original routers in the table above. `_INDEX.md` catalogs all 83 with mood-to-brand mappings; read it when routing is not obvious. Most non-trivial work loads one Layer A + one Layer B. `README.md` carries the `DESIGN.md` gate, the style routing flow, stacking rules, and Phase Final.
+ 105 `design/` holds one architecture file (`design-system-architecture.md`: the `DESIGN.md` structure, 8 sections plus a greenfield-only Research Log and the grounding gap ledger), 12 taste skills (Layer A: how to execute), 70 brand design systems (Layer B: what it looks like), and the project-original routers in the table above. `_INDEX.md` catalogs all 83 with mood-to-brand mappings; read it when routing is not obvious. Most non-trivial work loads one Layer A + one Layer B. `README.md` carries the `DESIGN.md` gate, the style routing flow, stacking rules, and Phase Final.
- 104 `ui-ux-db/`: `README.md` documents the search CLI and the master-plus-overrides persistence pattern. Run it from the ruleset directory so it finds `data/`:
+ 130 `ui-ux-db/`: `README.md` documents the search CLI and the master-plus-overrides persistence pattern. The CLI finds `data/` next to itself, so run it from the user's project directory: `--persist` writes `design-system/` into the current directory, and the skill directory can sit inside a signed app bundle that must never change. Keep `-B` for the same reason:
- 107 python3 $SKILL_DIR/references/ui-ux-db/scripts/search.py "<query>" --design-system -p "Project"   # design-system generation
- 108 python3 $SKILL_DIR/references/ui-ux-db/scripts/search.py "<query>" --domain <domain>             # product style typography color landing chart ux react web prompt
- 109 python3 $SKILL_DIR/references/ui-ux-db/scripts/search.py "<query>" --stack <stack>               # html-tailwind react nextjs vue svelte astro swiftui react-native flutter shadcn jetpack-compose
+ 133 python3 -B $SKILL_DIR/references/ui-ux-db/scripts/search.py "<query>" --design-system -p "Project"   # design-system generation
+ 134 python3 -B $SKILL_DIR/references/ui-ux-db/scripts/search.py "<query>" --domain <domain>             # product style typography color landing chart ux react web prompt
+ 135 python3 -B $SKILL_DIR/references/ui-ux-db/scripts/search.py "<query>" --stack <stack>               # html-tailwind react nextjs vue svelte astro swiftui react-native flutter shadcn jetpack-compose

Compare on GitHub

Before Not checked yet → After Network or broad shell

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Instructions only → After Network or broad shell

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Instructions only

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Instructions only → After Network or broad shell

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Instructions only

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Local scripts → After Network or broad shell

75b017473c71 → 49104cf38aa1

- 3 description: "Contribute a verified bug fix for LazyCodex, lazycodex-ai, omo-codex, bundled Codex skills, or upstream Codex CLI bugs. Opens a fork PR only for upstream openai/codex; LazyCodex-owned defects become a verified-fix issue on code-yeongyu/lazycodex (never a PR — that repo is a generated distribution mirror). Use when the user asks to fix a bug, contribute a bug fix, contribute to fix bug, open a PR for a bug, or debug and PR a LazyCodex/Codex defect."
+ 3 description: "Contribute a verified bug fix for LazyCodex, lazycodex-ai, omo-codex, bundled Codex skills, or upstream Codex CLI bugs. LazyCodex-owned defects get a fork PR against code-yeongyu/oh-my-openagent (base dev, source-tree paths under packages/omo-codex/plugin, with the changelog fragment); upstream Codex bugs get a fork PR against openai/codex. code-yeongyu/lazycodex is a generated distribution mirror and never gets a PR. Use when the user asks to fix a bug, contribute a bug fix, contribute to fix bug, open a PR for a bug, or debug and PR a LazyCodex/Codex defect."
- 14 - `code-yeongyu/lazycodex` for LazyCodex, lazycodex-ai, omo-codex, bundled skills, hooks, MCP wiring, installer behavior, marketplace sync, docs, or packaging. Deliverable: a verified-fix issue with the patch embedded. NEVER open a PR or push a branch against this repo — its contents are regenerated from the source tree on every release, so PRs there cannot be merged and will be closed.
+ 14 - `code-yeongyu/oh-my-openagent` (base branch `dev`) for LazyCodex, lazycodex-ai, omo-codex, bundled skills, hooks, MCP wiring, installer behavior, marketplace sync, docs, or packaging. Deliverable: a PR from a fork that edits the source-tree paths under `packages/omo-codex/plugin/` and carries the changelog fragment that repo requires. `code-yeongyu/lazycodex` is a distribution mirror generated from it (its `plugins/omo/` tree is synced from `packages/omo-codex/plugin/`), and the maintainer lands LazyCodex fixes from PRs against oh-my-openagent. NEVER open a PR or push a branch against `code-yeongyu/lazycodex`: its contents are regenerated on every release, so a PR there cannot be merged and will be closed. At most file a short issue there (symptom plus failing input) that links the oh-my-openagent PR; never embed a patch.
- 19 For `openai/codex`, create a fork PR that includes:
+ 19 For `code-yeongyu/oh-my-openagent` and `openai/codex`, create a fork PR that includes:
+ 27 - for `code-yeongyu/oh-my-openagent`: base `dev`, edits at `packages/omo-codex/plugin/...` (never the mirror's `plugins/omo/...` paths), and the changelog fragment `changes/unreleased/<pr-number>.md` that the repo's AGENTS.md describes
- 29 For `code-yeongyu/lazycodex`, create an issue (never a PR) that includes:
- 30 
- 31 - reproduction logs from before the fix
- 32 - the root cause with source evidence
- 33 - the verified patch as a unified diff, produced and tested in a fresh `${TMPDIR:-/tmp}` clone/worktree
- 34 - verification logs from after the fix
- 35 - the `lazycodex-generated` label and the footer tag `Tag: lazycodex-generated`
- 36 - cleanup of temporary worktrees and clones
+ 30 For `code-yeongyu/lazycodex`, deliver no PR and no patch. When a pointer is useful there, file a short issue (symptom plus failing input, the `lazycodex-generated` label and the footer tag `Tag: lazycodex-generated`) that links the oh-my-openagent PR.
- 42 3. Materialize the latest sources under `LAZYCODEX_SOURCE_ROOT="${LAZYCODEX_SOURCE_ROOT:-${TMPDIR:-/tmp}/lazycodex-sources}"`, then decide the target repository. Sync both checkouts on every run and compare them before choosing. Validate cached checkouts before reuse so an incomplete `.git` directory cannot route the fix to the wrong repo:
+ 36 3. Search for an existing lead PR before anything is filed. Search your own open PRs across all repos by the symptom or the changed symbol, then the target repo's open PRs, so a fix that already exists is found first and gets new evidence instead of a duplicate:
+ 37 
+ 38 ```bash
+ 39 gh search prs --author @me --state open "<symbol or error text>"
+ 40 gh search prs --repo code-yeongyu/oh-my-openagent --state open "<symbol or error text>"
+ 41 ```
+ 42 
+ 43 If a matching open PR exists, add evidence to it or report it instead of opening a second one.
+ 44 4. Materialize the latest sources under `LAZYCODEX_SOURCE_ROOT="${LAZYCODEX_SOURCE_ROOT:-${TMPDIR:-/tmp}/lazycodex-sources}"`, then decide the target repository. Sync the checkouts on every run and compare them before choosing. Validate cached checkouts before reuse so an incomplete `.git` directory cannot route the fix to the wrong repo:
+ 90 sync_latest_source code-yeongyu/oh-my-openagent "$LAZYCODEX_SOURCE_ROOT/oh-my-openagent-source"
- 90 4. Create a fresh temporary clone and branch under `${TMPDIR:-/tmp}`. Do not modify the user's current repository for the target fix unless the current repository is itself the requested target and the user explicitly asked for local edits. Apply those resource rules at clone/worktree creation.
- 91 
- 92 ```bash
- 93 TARGET_REPO="code-yeongyu/lazycodex" # or openai/codex
+ 93 5. Create a fresh temporary clone and branch under `${TMPDIR:-/tmp}`. Do not modify the user's current repository for the target fix unless the current repository is itself the requested target and the user explicitly asked for local edits. Apply those resource rules at clone/worktree creation.
+ 94 
+ 95 ```bash
+ 96 TARGET_REPO="code-yeongyu/oh-my-openagent" # or openai/codex
- 106 5. Reproduce the bug in the worktree through the real surface. Save exact command output to `${TMPDIR:-/tmp}/lazycodex-fix-<short-slug>-repro.log`.
- 107 6. Write or update a failing regression test before production changes. Confirm it fails for the bug, not for a missing fixture or typo.
- 108 7. Implement the smallest correct fix. Avoid refactors unless the fix cannot be made safely without one.
- 109 8. Run the regression test, adjacent tests, and the smallest real-surface QA command that proves the user-visible behavior changed.
- 110 9. Commit the verified fix in the worktree. Inspect the status first so the delivered diff cannot be empty or stale:
+ 109 6. Reproduce the bug in the worktree through the real surface. Save exact command output to `${TMPDIR:-/tmp}/lazycodex-fix-<short-slug>-repro.log`.
+ 110 7. Write or update a failing regression test before production changes. Confirm it fails for the bug, not for a missing fixture or typo.
+ 111 8. Implement the smallest correct fix. Avoid refactors unless the fix cannot be made safely without one.
+ 112 9. Run the regression test, adjacent tests, and the smallest real-surface QA command that proves the user-visible behavior changed.
+ 113 10. Commit the verified fix in the worktree. Inspect the status first so the delivered diff cannot be empty or stale:
- 119 10. Build the delivery body for the target:
- 120    - `openai/codex`: generate the PR body with `scripts/create-pr-body.mjs`.
- 121    - `code-yeongyu/lazycodex`: export the verified patch and write the issue body from the Verified-Fix Issue Template below:
- 122 
- 123 ```bash
- 124 PATCH_FILE="${TMPDIR:-/tmp}/lazycodex-fix-<short-slug>.patch"
- 125 git diff "origin/$BASE_BRANCH"..HEAD > "$PATCH_FILE"
- 126 ```
- 127 
- 128 11. Ensure the generated label exists when the target repo allows label management. Keep the footer tag even when label creation is unavailable:
+ 122 11. Build the delivery body for the target:
+ 123    - `code-yeongyu/oh-my-openagent` and `openai/codex`: generate the PR body with `scripts/create-pr-body.mjs` (set `targetRepository` to the repo you are filing against).
+ 124    - `code-yeongyu/oh-my-openagent` only: add the changelog fragment `changes/unreleased/<pr-number>.md` once the PR number exists, in the format `docs/reference/changelog-fragments.md` of that repo defines, and commit it to the same branch.
+ 125 
+ 126 12. Ensure the generated label exists when the target repo allows label management. Keep the footer tag even when label creation is unavailable:
- 139 12. Deliver the fix.
- 140    - `code-yeongyu/lazycodex`: create the verified-fix issue. Never push a branch to this repo and never run `gh pr create` against it:
+ 137 13. Deliver the fix.
+ 138    - `code-yeongyu/oh-my-openagent`: fork, push the branch to the fork, and create the PR against base `dev`. Never push a branch to or run `gh pr create` against `code-yeongyu/lazycodex`:
+ 139 
+ 140 ```bash
+ 141 gh repo fork code-yeongyu/oh-my-openagent --remote --remote-name fork
+ 142 GH_USER="$(gh api user --jq .login)"
+ 143 git push -u fork "$BRANCH_NAME"
+ 144 gh pr create --repo code-yeongyu/oh-my-openagent --base dev --head "$GH_USER:$BRANCH_NAME" --title "<short fix title>" "${LABEL_ARGS[@]}" --body-file "$PR_BODY"
+ 145 ```
+ 146 
+ 147    - `code-yeongyu/lazycodex` (optional pointer): a short issue with the symptom, the failing input and a link to the oh-my-openagent PR, never a diff:
- 156 13. Finish cleanup per Task resources. Run this only when that rule permits removing the worktree and run root; otherwise retain them and report the outstanding cleanup todo:
+ 163 14. Finish cleanup per Task resources. Run this only when that rule permits removing the worktree and run root; otherwise retain them and report the outstanding cleanup todo:
- 169 ## Verified-Fix Issue Template (code-yeongyu/lazycodex)
- 170 
- 171 Write the issue body in English. Embed the patch verbatim so a maintainer can apply it to the source tree:
+ 176 ## Pointer Issue Template (code-yeongyu/lazycodex, optional)
+ 177 
+ 178 Write the issue body in English. It names the symptom and the failing input and links the oh-my-openagent PR; the fix itself lives in that PR:
- 174 ## Problem Situation
+ 181 ## Symptom
- 177 ## Reproduction Logs
- 178 [Exact failing command and relevant log excerpt.]
- 179 
- 180 ## Root Cause
- 181 [Confirmed cause with runtime and source evidence.]
- 182 
- 183 ## Verified Fix
- 184 [What changed and why this is the smallest correct fix.]
- 185 
- 186 ```diff
- 187 [Contents of $PATCH_FILE.]
- 188 ```
- 189 
- 190 ## Verification
- 191 - [RED test output or repro before the fix]
- 192 - [GREEN test output after the fix]
- 193 - [Manual QA command and result]
- 194 
- 195 ---
- 196 This fix was debugged, implemented, and verified with [LazyCodex](https://github.com/code-yeongyu/lazycodex).
+ 184 ## Failing Input
+ 185 [Exact failing command and the shortest log excerpt.]
+ 186 
+ 187 ## Fix
+ 188 [Link to the code-yeongyu/oh-my-openagent PR.]
+ 189 
+ 190 ---
+ 191 This issue was generated by LazyCodex.
- 270 - a PR or pushed branch targeting `code-yeongyu/lazycodex` — deliver the verified-fix issue instead, always
- 271 - a PR or verified-fix issue without a failing-before and passing-after test
- 272 - a PR or verified-fix issue without a real-surface QA command
+ 265 - a PR or pushed branch targeting `code-yeongyu/lazycodex` — send the fix as a PR against `code-yeongyu/oh-my-openagent` instead, always
+ 266 - a PR for a defect that already has an open lead PR found by the search in step 3
+ 267 - a PR without a failing-before and passing-after test
+ 268 - a PR without a real-surface QA command
- 274 - a verified-fix issue without the patch embedded in a `diff` block
+ 270 - an issue on `code-yeongyu/lazycodex` that embeds a patch

Compare on GitHub

Before Not checked yet → After Local scripts

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Instructions only → After Network or broad shell

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Instructions only

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Instructions only → After Network or broad shell

75b017473c71 → 49104cf38aa1

- 12 - `code-yeongyu/lazycodex` for LazyCodex, lazycodex-ai, omo-codex, marketplace, bundled skill, hook, MCP, installer, or packaging bugs. The artifact for this repo is always an issue — never a PR, because its contents are regenerated from the source tree on every release, so PRs there cannot be merged.
- 13 - `openai/codex` for upstream Codex CLI bugs that reproduce without LazyCodex or are caused by Codex core behavior. This is the only repo where this skill may create a PR.
+ 12 - `code-yeongyu/lazycodex` for LazyCodex, lazycodex-ai, omo-codex, marketplace, bundled skill, hook, MCP, installer, or packaging bugs. The artifact for this repo is always an issue, never a PR: it is a distribution mirror generated from `code-yeongyu/oh-my-openagent` (its `plugins/omo/` tree is synced from `packages/omo-codex/plugin/`), so PRs there cannot be merged. A fix for these defects goes to `code-yeongyu/oh-my-openagent` as a fork PR (base `dev`, source-tree paths, changelog fragment) through `$lcx-contribute-bug-fix`; the mirror issue stays short and links that PR.
+ 13 - `openai/codex` for upstream Codex CLI bugs that reproduce without LazyCodex or are caused by Codex core behavior. A PR may be created here.
- 93 7. Search for an existing issue in the selected repo before creating a new one. Search the other repo too when the ownership boundary is close:
+ 93 7. Search for an existing issue or lead PR before creating anything new. Search your own open PRs across all repos first (`gh search prs --author @me --state open "<symbol or error text>"`), then the selected repo, and the other repo too when the ownership boundary is close:
- 114 11. Create a PR only when the target repo is `openai/codex` AND the user asked for a PR, the fix is already implemented on a branch, or the smallest correct fix can be safely made there. Never create a PR or push a branch against `code-yeongyu/lazycodex` — always file an issue there, embedding the verified patch in the Proposed Fix section when one exists. Apply the `lazycodex-generated` label to every PR created by this skill. Otherwise create an issue with fix guidance.
+ 114 11. Create a PR only when the target repo is `openai/codex` or `code-yeongyu/oh-my-openagent` (the source of the LazyCodex mirror, base `dev`) AND the user asked for a PR, the fix is already implemented on a branch, or the smallest correct fix can be safely made there; use `$lcx-contribute-bug-fix` for the fix workflow. Never create a PR or push a branch against `code-yeongyu/lazycodex`: file a short issue there (symptom and failing input) that links the oh-my-openagent PR, with no patch. Apply the `lazycodex-generated` label to every PR created by this skill. Otherwise create an issue with fix guidance.
- 179 Use this only when a PR is the right artifact, which is only ever for `openai/codex`:
+ 179 Use this only when a PR is the right artifact, which is only ever for `openai/codex` or `code-yeongyu/oh-my-openagent`:
- 229 For a PR from a branch pushed to a fork — `openai/codex` only, never `code-yeongyu/lazycodex`:
+ 229 For a PR from a branch pushed to a fork, against `openai/codex` or `code-yeongyu/oh-my-openagent` (never `code-yeongyu/lazycodex`):
- 262 - a PR or pushed branch targeting `code-yeongyu/lazycodex` — file the issue instead, always
+ 262 - a PR or pushed branch targeting `code-yeongyu/lazycodex` — send a fix PR to `code-yeongyu/oh-my-openagent` and keep any mirror issue short, always

Compare on GitHub

Before Not checked yet → After Instructions only

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Instructions only → After Instructions only

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Instructions only

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Network or broad shell → After Network or broad shell

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Network or broad shell

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Network or broad shell → After Network or broad shell

75b017473c71 → 49104cf38aa1

- 3 description: "Applies strict, modern language practice (typed errors, exhaustive match, tests that can fail) for Python, Rust, TypeScript, JavaScript, and Go. Use for work on .py, .rs, .ts, .js, or .go files."
+ 3 description: "Applies strict, modern language practice (typed errors, exhaustive match, tests that can fail) for Python, Rust, TypeScript, JavaScript, and Go. Use for work on .py, .rs, .ts, .js, or .go files, and whenever a test or spec file is written, reshaped, reviewed, or deleted: the four-question test authoring gate and the junk-test classes live here."
+ 27    | any test file (`*.test.*`, `*.spec.*`, `*_test.go`, `test_*.py`, `*_test.py`, under `test/`, `tests/` or `__tests__/`), or a change that adds, reshapes, or deletes a test | the language row above PLUS `references/testing/README.md` (the authoring gate) and `references/testing/junk-classes.md` (the table the gate reviewer applies) |
- 34 ## Shared philosophy (all three languages)
+ 35 ## Shared philosophy (all four languages)
- 50 6. **Tests are the behavior of record, and only tests that can fail count.** READ the tests covering the area BEFORE you change it: do they encode the intent, cover this path, pass? One wrong before your change is a FINDING — never edit it green. Reproduce a bug before fixing it. The run proves the change; add a test ONLY where the repository keeps tests for this behavior AND a regression would otherwise pass unnoticed — sized like its neighbors, never restating the change. See the test discipline below.
+ 51 6. **Tests are the behavior of record, and only tests that can fail count.** READ the tests covering the area BEFORE you change it: do they encode the intent, cover this path, pass? One wrong before your change is a FINDING — never edit it green. Reproduce a bug before fixing it. The run proves the change; add a test ONLY where the repository keeps tests for this behavior AND a regression would otherwise pass unnoticed — sized like its neighbors, never restating the change. The authoring gate and the junk-class table are in `references/testing/`.
- 56 ### The shape of the test pyramid
- 57 
- 58 Where the repository keeps these rungs, test at the cheapest rung that observes the behavior:
- 59 
- 60 | Rung | Count | Purpose | Speed budget |
- 61 |---|---|---|---|
- 62 | **Unit** | many | Pure-function correctness for every meaningful input class (happy + edges + boundaries + error paths) | < 10 ms each |
- 63 | **Integration** | some | The real adapter against the real downstream (DB, queue, HTTP) — via `testcontainers`, `httptest`, or equivalent. NEVER a unit test pretending to be integration. | < 1 s each |
- 64 | **E2E scenario** | few | One narrative per user-visible outcome. Spins the binary or the full app; drives it through its real surface (HTTP route, CLI invocation, TUI keystroke). Asserts the *observable outcome*, not internal state. | seconds, run on CI |
- 65 
- 66 A user-visible outcome you never drove through its real surface is unverified — a green unit suite does not stand in for that run.
- 67 
- 68 ### Given / When / Then is mandatory
- 69 
- 70 Every test — unit, integration, E2E — is structured by these three blocks. Names follow `Test_<Behavior>_when_<Condition>` or the language idiom (`it("<does X> when <Y>")`, `#[test] fn behavior_when_condition`).
- 71 
- 72 ```
- 73 Given: the preconditions and fixtures
- 74 When:  the single action under test
- 75 Then:  the observable outcome AND only that outcome
- 76 ```
- 77 
- 78 One `When` per test. Multiple `When`s = multiple tests. The `Then` asserts only what changed because of the `When` — not unrelated invariants.
- 79 
- 80 ### Less mock, the better
- 81 
- 82 Mocks are a last resort, not a default. The priority order:
- 83 
- 84 1. **Real object.** Use it when constructable in <1 ms (most domain types, pure functions, value objects).
- 85 2. **In-memory fake.** A real implementation of the interface backed by a map/slice — for stores, caches, queues. The fake has its OWN test that proves it behaves like the real one.
- 86 3. **Testcontainer / sandbox.** Real Postgres, real Redis, real S3-compatible (MinIO), via `testcontainers`. Slow but truthful.
- 87 4. **HTTP-level fake.** `httptest.Server` (Go), `respx` (Python), `msw` (TS) — fake at the wire, not at the SDK.
- 88 5. **Mock.** Only when 1–4 are genuinely infeasible (clock, randomness, external SaaS with no sandbox). Then mock the **narrowest** seam — never an entire service. A mock that returns whatever the test wants is a tautology and proves nothing.
- 89 
- 90 **The rule**: if your test fails when the production code's *implementation* changes but its *behavior* did not, the test is over-mocked. Delete the mock; assert on observable outputs.
- 91 
- 92 ### Efficient AND accurate — both, not either
- 93 
- 94 - **Accurate**: the test fails for the bug it names, and only that bug. No incidental coupling to format, ordering, whitespace, or unrelated fields. Assert on the *contract*, not on the dump.
- 95 - **Efficient**: the whole unit suite runs in < 30 seconds on a developer laptop. The whole integration suite in < 5 minutes. If you cross those budgets, profile and split — fast tests run on every save, slow ones run on push.
- 96 - **Deterministic**: no `sleep`, no wall-clock dependence, no order dependence (`-shuffle=on`, pytest-randomly, vitest random seed). Inject a `Clock`. Subscribe to the event, do not poll for it. Time-based flake is a bug, not a test issue.
- 97 - **Isolated**: every test starts from a known fixture and tears down. `t.TempDir()`, `t.Setenv()`, transactional rollback for DB tests. Two tests passing individually but failing together is a fixture leak — fix it immediately. Isolation extends **across processes**: suite-global resources — sandbox/cache roots under a fixed tmpdir path, hardcoded listen ports, container names — are namespaced per run (`mktemp`, port `0`/ephemeral, unique names) so that two checkouts or worktrees of the repo running the suite concurrently cannot interfere. A fixed shared path that works on a single-checkout machine is a flake generator on a multi-agent workstation, and its signature is "a different test fails each run".
- 98 
- 99 ### Prompt tests: NEVER assert prose
- 100 
- 101 **FORBIDDEN — NO EXCEPTIONS: a test MUST NOT assert natural-language prompt text.** `expect(prompt).toContain("based on GPT-5.6")`, `not.toContain("old wording")`, `toMatchSnapshot()` on prose, grepping a sentence fragment — every one of these is pretend-coverage. It stays green while the behavior it claims to guard breaks, then blocks every legitimate rewording until someone bumps the pinned string. A reviewer MUST block it as HIGH; deleting such a test is a fix, not a coverage loss. "A nearby test already does it" is not a defense — that test is the disease, not the convention.
- 102 
- 103 Assert ONLY what a machine consumes:
- 104 
- 105 - the builder's routing decision — `expect(getPromptSource(model)).toBe("gpt-5-6")`, never the sentence that routing produces
- 106 - a structural token the runtime dispatches on — a tool name, a tag like `<agent-identity>`, a parsed frontmatter field
- 107 - the conditional the code enforces — skill loaded → tool present; `verbose=false` → directive absent
- 108 - a routing-bearing trigger fragment inside a parsed frontmatter `description` that a router (code or an LLM skill-picker) dispatches on — pin the *minimal fragment that carries the routing decision*, never the surrounding style prose. Such pins are what let a later rewrite change every sentence around them while proving the routing contract survived.
- 109 
- 110 If no machine consumes the text, there is no seam: write NO test and say so in the PR; review guards prose. When you DELEGATE test-writing, hand the child the behavior the test must distinguish ("fails if override precedence breaks"), never a ready-made assertion string, prompt fragment, or marker to copy — a prescribed mechanism that is wrong gets implemented faithfully, and the error ships with a green suite.
- 111 
- 112 ### Anti-patterns the skill rejects
- 113 
- 114 | Anti-pattern | Why it fails | Fix |
- 115 |---|---|---|
- 116 | A test that restates the change (pins a constant, a string, a rename, a call) | Cannot fail for any regression; certifies the diff, not the behavior. | The run is the proof. Delete the test. |
- 117 | One mega-test asserting 12 things | First failure hides the next 11. | Split by `Then` clause — one assertion class per test. |
- 118 | Mocking every collaborator | Test passes regardless of real behavior. | Use a fake or the real thing. Mock only true unmockables. |
- 119 | `time.sleep(0.1)` to "let it finish" | Flake guaranteed. | Subscribe to the completion signal; bounded await. |
- 120 | Snapshot tests for everything | Locks formatting, not behavior. | Snapshots for *structure* (CLI help, JSON shape). Assertions for *behavior*. |
- 121 | Removing a failing test to "unblock CI" | You just deleted a bug report. | Fix the code or fix the test — never delete to silence. |
- 122 | `assert result is not None` and stopping there | Passes when result is garbage. | Assert the *value*, not its existence. |
- 123 | Expected value derived from the output under test (`expect(config.prompt).toBe(getPrompt(config.model))` when the criterion is about `config.prompt`) | Recomputes a projection of the output and compares it to itself — passes even when the artifact is built from the wrong input. | Derive the expected value from the test's *input*: `expect(config.prompt).toBe(getPrompt(inputModel))` (independent known-good builder fed the fixture's input), or a stable builder routing decision. |
- 124 | Override/precedence fixture equal to its fallback (override == system default) | The assertion passes whether or not the code honored the override — precedence is never exercised. | Make every value the code must select, preserve, or override differ from its fallback. Prove it: temporarily force the regression the test names, watch it fail, revert. |
- 125 | Single happy-path E2E, no edges | Most bugs live on edges. | Edges are unit-test territory — but include at least one E2E that exercises an error path. |
+ 57 Tests are code: the language gate above applies to them, plus [`references/testing/README.md`](references/testing/README.md) (the contract every language's recipes assume) and [`references/testing/junk-classes.md`](references/testing/junk-classes.md) (the table the gate reviewer applies to every test in a diff). Read both before adding, reshaping, or deleting a test.
+ 58 
+ 59 **The authoring gate.** Before a test exists, answer all four; a missing answer means do not add it yet.
+ 60 
+ 61 1. What observable behavior, invariant, or independent contract does it protect?
+ 62 2. What credible regression makes it fail?
+ 63 3. Why does existing coverage not already catch that failure? One primary owner per contract, at the strongest boundary; extend a table row before adding a near-duplicate, a copy in another package, or a replay through a wrapper.
+ 64 4. Does it need a production seam (export, flag, getter, wrapper, injection hook) no production caller needs? Then test at the real boundary instead.
+ 65 
+ 66 The README owns the shape (Given / When / Then, the pyramid, the mock ladder, determinism, isolation, the prompt-test rule) and the "test your test" step: break the production owner, watch the test go red for the intended reason, restore byte for byte. A test that fails on the unchanged base is a bug to fix at its owner; one your own change turns red is fixed at the code or at the test; neither is deleted or edited green to unblock a run.
- 183 | Bootstrap a new project | `scripts/python/new-project.py` | `scripts/rust/new-project.py` | `scripts/typescript/new-project.ts` | `scripts/go/new-project.py` |
+ 124 | Bootstrap a new project | `bun run scripts/python/new-project.ts` | `bun run scripts/rust/new-project.ts` | `bun run scripts/typescript/new-project.ts` | `bun run scripts/go/new-project.ts` |
+ 202 # Any language, test files you touched: the junk classes a regex can see (candidates for "test your test")
+ 203 bun run scripts/typescript/check-test-junk.ts <changed test paths>
- 281 7. **Tests?** Is the behavior I just introduced locked by a test that would fail if I revert this commit?
+ 224 7. **Tests?** Does every test I added or reshaped answer the four-question authoring gate (`references/testing/README.md`), go red when I break its production owner, and match no row of `references/testing/junk-classes.md`? Where the repository keeps tests for a behavior I introduced and a regression would otherwise pass unnoticed, is it covered at its owner, not by a copy or a change certificate?
- 303 | Recent branch contains AI-authored patterns (broad except, dead helpers, vague comments, oversized files, redundant post-action verification), OR the user says "remove slop", "clean AI code", "deslop" | `remove-ai-slops` | Tests pinned FIRST, then categorized parallel cleanup, then quality gates. Behavior-preserving. |
+ 246 | Recent branch contains AI-authored patterns (broad except, dead helpers, vague comments, oversized files, redundant post-action verification, junk tests), OR the user says "remove slop", "clean AI code", "deslop" | `remove-ai-slops` | Behavior locked by gate-passing tests FIRST, then categorized parallel cleanup (junk tests included, each cut proven by a mutation), then quality gates. Behavior-preserving. |
- 392 This skill activates whenever you are writing or modifying any `.py`, `.pyi`, `.rs`, `.ts`, `.tsx`, `.mts`, `.cts`, `.js`, `.jsx`, `.mjs`, `.cjs`, `.go` file, or any project manifest (`pyproject.toml`, `Cargo.toml`, `package.json`, `tsconfig.json`, `.oxlintrc.json`, `.oxfmtrc.json`, `go.mod`, `go.sum`, `.golangci.yml`, `Taskfile.yml`, `buf.yaml`, `sqlc.yaml`). **Even one-off scripts get the full treatment** - that is the whole point of `uv run` + PEP 723, `rust-script`, `bun run`, and `go run` + `//go:build ignore`: production hygiene with throwaway ergonomics.
+ 335 This skill activates whenever you are writing or modifying any `.py`, `.pyi`, `.rs`, `.ts`, `.tsx`, `.mts`, `.cts`, `.js`, `.jsx`, `.mjs`, `.cjs`, `.go` file, any test or spec file in those languages, or any project manifest (`pyproject.toml`, `Cargo.toml`, `package.json`, `tsconfig.json`, `.oxlintrc.json`, `.oxfmtrc.json`, `go.mod`, `go.sum`, `.golangci.yml`, `Taskfile.yml`, `buf.yaml`, `sqlc.yaml`). **Even one-off scripts get the full treatment** - that is the whole point of `uv run` + PEP 723, `rust-script`, `bun run`, and `go run` + `//go:build ignore`: production hygiene with throwaway ergonomics.

Compare on GitHub

Before Not checked yet → After Network or broad shell

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Instructions only → After Network or broad shell

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Instructions only

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Instructions only → After Network or broad shell

75b017473c71 → 49104cf38aa1

- 3 description: "Removes AI-generated code smells from branch changes or an explicit file list behind regression tests. Use when the user asks to clean up, deslop, or remove AI-slop patterns from recent changes."
+ 3 description: "Removes AI-generated code smells from branch changes or an explicit file list behind regression tests, including junk tests (prose pins, source greps, copied inventories, mock echoes), each proven by its class's rule before a cut. Use when the user asks to clean up, deslop, remove AI-slop patterns, or prune tests from recent changes."
- 48 The agent looks for these nine categories. The first three are stylistic, the next three are structural, the next two are about hidden cost, and the last is about behavior coverage.
+ 48 The agent looks for these ten categories. The first three are stylistic, the next three are structural, the next two are about hidden cost, the ninth is tests, and the last is size.
- 89 ### Behavior coverage
- 90 9. **Missing tests** — behavior present in changed files that is not locked by any regression test. The fix is not to remove code but to ADD the narrowest test that pins the behavior. EXCEPTION: a PROSE file (prompt, `SKILL.md`, rule, markdown) has no behavioral seam — do NOT add a text/word-count/phrase pin for it; that guards a diff, not behavior. Cover only a machine-consumed value (parsed field, sentinel a runtime greps, a doc JSON sample through its real validator) or leave it to review.
- 91 
- 92 ### Structural
+ 89 ### Tests
+ 90 9. **Tests: missing or junk** — tests are code in scope like any other file, judged by the one table in the `programming` skill, `references/testing/junk-classes.md` (junk classes, retention bar, R/F/C/D marks, proof rule). Two directions:
+ 91    - **Missing**: a behavior in the changed files that no test guards, where the repository keeps tests for that kind of behavior and a regression would otherwise pass unnoticed. ADD the narrowest test that passes the four-question authoring gate (`references/testing/README.md`); name its owner contract. A PROSE file (prompt, `SKILL.md`, rule, markdown) has no behavioral seam: cover only a machine-consumed value (parsed field, sentinel a runtime greps, a doc JSON sample through its real validator) or leave it to review.
+ 92    - **Junk**: mark every in-scope test declaration `R` / `F` / `C` / `D`. A `D` or `C` needs the proof the table names for its class BEFORE the cut: for a behavior class (cannot fail, mock echo, source grep, duplicate contract, layer replay, implementation mirror, fabricated postcondition, input transcript) a mutation of the production owner run against the candidate and its named keeper on the unmodified test tree; for a prose pin the assertion line plus the repo's prose rule; for a change certificate the revert that turns it red; for a seam keeper the `knip`/grep showing no production caller; for a copied inventory the generator or consumer that owns it; for a capability restatement the delivery test that owns the promise (none: `F`, not `D`); for near-duplicate cases the one table that keeps every old assertion (typecheck after). A misnamed test is re-marked by what its assertions check, never cut for its name. A mutation proves `D` only when the keeper goes red and the candidate stays green (cannot fail) or both go red (redundant); a candidate that is the ONLY red is `R`, or `C` into the keeper and re-run. Mutations run in Phase 4b, serially, by the orchestrator, never by a batch worker. A test-only production seam (export, flag, getter, reset hook) whose last test was deleted goes with it.
+ 93    - KEEP: everything under the retention bar (public API, protocol, config, migration, storage, security, platform, shipped-copy equality, Node-compat suites, issue regressions, machine-consumed text). A test that is red on the unchanged base is a product bug to report, never a deletion. Static or slow is never a reason to delete.
+ 94 
+ 95 ### Size
- 150 3. **If behavior is uncovered or weakly covered, write the narrowest regression test that pins current behavior BEFORE editing the file.** Tests should pin observable outputs, not implementation details. A PROSE file (prompt/`SKILL.md`/rule/markdown) is exempt — its wording is not behavior; skip the test and rely on review, or assert only a machine-consumed value.
- 151 4. Run the test suite (or at minimum the relevant tests). They must be **green** before any cleanup begins.
- 152 
- 153 If you cannot establish a green baseline (e.g., test runner is broken), STOP and report. Do not proceed with cleanup on unverified ground.
+ 153 3. **If a behavior the cleanup could change is uncovered, write the narrowest test that passes the authoring gate (`programming/references/testing/README.md`) BEFORE editing the file**, and name the behavior it guards. It asserts observable outputs at the real boundary, never the implementation shape the cleanup is about to change, and never a value derived from the code under test. A PROSE file (prompt/`SKILL.md`/rule/markdown) is exempt: its wording is not behavior; skip the test and rely on review, or assert only a machine-consumed value.
+ 154 4. Run the test suite (or at minimum the relevant tests). A test that is red on the unchanged base is recorded as a bug (baseline-red list), excluded from every proof, and neither fixed in this pass nor deleted; everything else must be **green** before any cleanup begins.
+ 155 5. Run the `programming` skill's static detector over every in-scope test file, the ones written in step 3 included: `bun run <programming skill dir>/scripts/typescript/check-test-junk.ts <test files>` (exit 1 lists `file:line` per junk class it can see: source grep, prose pin, fixed sleep, `.only`/`.skip`, self-comparison, lower-bound cardinality). Its findings are category-9 candidates for the Tests Ledger (marked `R`/`F`/`C`/`D` by the table once its proof runs), never automatic cuts, and a test from step 3 that it flags is rewritten before the pass continues.
+ 156 
+ 157 Only a broken runner stops the pass: if the suite cannot run at all, STOP and report. Do not proceed with cleanup on unverified ground.
- 159 - **Delete entirely** — the behavior is not needed (YAGNI, speculative, dead on arrival).
+ 163 - **Delete entirely** — the behavior is not needed (YAGNI, speculative, dead on arrival); for a test, its contract is already owned by a keeper or it has none (category 9, with the proof).
- 186 Order rule (safest → riskiest): comments → dead code → defensive → duplication → complexity → abstraction/boundary → performance → tests → oversized-modules. This minimizes blast radius of any one change.
+ 190 Order rule (safest → riskiest): comments → dead code → defensive → duplication → complexity → abstraction/boundary → performance → tests (`F` rows; `D`/`C` wait for Phase 4b) → oversized-modules. This minimizes blast radius of any one change.
- 190 Files are processed by `deep-low` category agents with the `$omo:remove-ai-slops` skill loaded, **batched 5 at a time in parallel**. The executable skill name is `remove-ai-slops`. The `deep-low` category gives the agent enough thoroughness to correctly evaluate the 9 categories and respect the KEEP rules without slipping into surface fixes; the 5-wide batch is the sweet spot — more than 5 creates result-merging noise and context contention, fewer wastes parallelism.
+ 194 Files are processed by `deep-low` category agents with the `$omo:remove-ai-slops` skill loaded, **batched 5 at a time in parallel**. The executable skill name is `remove-ai-slops`. The `deep-low` category gives the agent enough thoroughness to correctly evaluate the 10 categories and respect the KEEP rules without slipping into surface fixes; the 5-wide batch is the sweet spot — more than 5 creates result-merging noise and context contention, fewer wastes parallelism.
- 216 Then evaluate EVERY category defined in this skill's "Categories (what counts as slop)" section, applying that section's KEEP and REFACTOR rules verbatim — the Categories section you have loaded is canonical, do not work from a restated subset.
- 217 
- 218 Apply changes in this order (safest → riskiest): comments → dead code → defensive → duplication → complexity → abstraction/boundary → performance → oversized-modules.
+ 220 Then evaluate EVERY category defined in this skill's "Categories (what counts as slop)" section, applying that section's KEEP and REFACTOR rules verbatim — the Categories section you have loaded is canonical, do not work from a restated subset. For a test file, do NOT cut yet: mark every declaration R/F/C/D against `programming/references/testing/junk-classes.md` and return one ledger row per D/C/F (`| test | mark | keeper or reason | proposed proof |`), where the proposed proof names the class's proof kind and, for a mutation, the owner file, the exact find/replace, and the keeper to run. This worker applies `F` rows in the test file it owns and reports them in the ledger as applied; `D`/`C` rows are returned uncut; it never mutates any file to prove a test - the orchestrator runs the proofs in Phase 4b.
+ 221 
+ 222 Apply changes in this order (safest → riskiest): comments → dead code → defensive → duplication → complexity → abstraction/boundary → performance → tests (`F` rows; `D`/`C` wait for Phase 4b) → oversized-modules.
- 228 For each skipped issue, give reason.
+ 232 For each skipped issue, give reason. For a test file, end with the ledger rows.
+ 236 
+ 237 ### Phase 4b: Prove the test cuts, serially, then cut
+ 238 
+ 239 After the last batch finishes and no worker is running, the orchestrator takes the collected ledger rows. For each row whose proof is a mutation, run the `programming` skill's `bun run <programming skill dir>/scripts/typescript/mutation-proof.ts --file <owner> --find <text> --replace <text> --test 'candidate=<argv>' --test 'keeper=<argv>'` (add `--json` for the ledger; each `--test` value is split on spaces with no quoting, so a filter that contains a space needs a wrapper script or a file-path target instead): it applies the find/replace to the production owner, runs the candidate and the keeper on the unmodified test tree, records both verdicts, and restores the owner byte for byte (sha256-checked) before the next row. One mutation at a time, never while another worker or test run is live, and never two on the same file; a mutation touches a file outside the diff only transiently and is never committed. Rows proven per the table become the cuts; a D or C whose proof fails or was not run is an R. Non-mutation proofs (prose pin, change certificate, seam keeper, copied inventory, capability restatement, near-duplicate cases) are checked here too, from the row's evidence.
- 287   - Tests added: [M new regression tests at path/to/test_X.py]
- 288   - Baseline status: GREEN
+ 295   - Tests added: [M gate-passing tests at path/to/test_X.py, each naming its contract]
+ 296   - Baseline status: GREEN apart from the baseline-red list (recorded as bugs, excluded from proofs, not deleted): [none] OR [list]
+ 314 Tests Ledger (category 9; one row per test declaration marked D/C/F, proofs run in Phase 4b):
+ 315   | Test | Mark | Keeper / reason | Proof |
+ 316   |---|---|---|---|
+ 317   | `foo.test.ts > reads the source for "export"` | D | source grep; `foo.test.ts > exports parse()` owns the contract | mutation parse.ts `return tokens` -> `return []`: candidate green, keeper red; restored sha-equal |
+ 318   | `skill.test.ts > mentions the gate` | D | prose pin on SKILL.md | assertion line + repo prose rule (no mutation applies) |
+ 319 
- 358 - ALWAYS verify changes compile/parse and pass type-check.
- 359 - ALWAYS preserve test coverage; add tests rather than remove them.
- 360 - If uncertain about a change, err on the side of keeping the original code.
- 361 - The default action when in doubt is SKIP, not GUESS.
+ 372 - Preserve every proven contract: a test leaves only with its proof receipt (category 9), and a missing contract gets a gate-passing test, never a change certificate.
+ 373 - When in doubt, SKIP and keep the original; never GUESS.

Compare on GitHub

Before Not checked yet → After Instructions only

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Network or broad shell → After Network or broad shell

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Network or broad shell

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Instructions only → After Instructions only

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Instructions only

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Local scripts → After Network or broad shell

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Local scripts

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Network or broad shell → After Network or broad shell

75b017473c71 → 49104cf38aa1

- 41 # Core command — auto-detects WAF, runs the full fetch grid (run from the skill dir):
- 42 python3 -m engine "https://example.com/blocked-page"
+ 41 # Core command — auto-detects WAF, runs the full fetch grid (run from the skill dir).
+ 42 # Keep -B: this skill can live inside a signed app bundle, and bytecode caches written into engine/ break its signature.
+ 43 python3 -B -m engine "https://example.com/blocked-page"
- 122 python3 scripts/extract_cookies.py --browser chrome --domain youtube.com --output ~/.local/state/omo-cookies/youtube.cookies.json
+ 123 python3 -B scripts/extract_cookies.py --browser chrome --domain youtube.com --output ~/.local/state/omo-cookies/youtube.cookies.json
- 124 python3 scripts/extract_cookies.py --browser chrome --domain youtube.com --inject --cdp 9242
+ 125 python3 -B scripts/extract_cookies.py --browser chrome --domain youtube.com --inject --cdp 9242

Compare on GitHub

Before Not checked yet → After Network or broad shell

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Network or broad shell → After Network or broad shell

75b017473c71 → 49104cf38aa1

+ 486 - A permission denial or a refusal by the user is not a blocker to work
+ 487   around: it is final for what that call was meant to do. Never reach that
+ 488   result with another tool, command, path or host; ask the user.

Compare on GitHub

Before Not checked yet → After Network or broad shell

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Network or broad shell → After Network or broad shell

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Network or broad shell

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Network or broad shell → After Network or broad shell

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Network or broad shell

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Local scripts → After Network or broad shell

75b017473c71 → 49104cf38aa1

Compare on GitHub

Before Not checked yet → After Local scripts

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Network or broad shell → After Network or broad shell

75b017473c71 → 49104cf38aa1

- 120 ## Phase 0 — Decompose and open the journal
+ 120 ## Execution references
- 122 Before spawning anything, decompose the query. Start from "what must be true if the user's intent/spec is true?", not "what looks broken?" Seed `intent-diff.md` with those expected truths before treating code, current docs, or web results as the source of truth:
+ 122 Read [research-collection.md](references/research-collection.md) before scoping or collecting sources, then [research-delivery.md](references/research-delivery.md) before verification, synthesis, and delivery. These references continue this skill in phase order; their requirements remain binding.
- 124 ```
- 125 <analysis>
- 126 Core question: <the actual information need>
- 127 Axes (3+ orthogonal): <axis — what to search, where, why> ...
- 128 Codebase relevant: <yes/no> · External: <yes/no> · Collection: <search-only | browser> · Verification likely: <yes/no>
- 129 Scale: <axis count, source territories, target document length> · Precision demand: <what a wrong claim costs here> → lifecycle: <single team | research team then refinement team>
- 130 </analysis>
- 131 ```
- 132 
- 133 `Collection` is `search-only` only when a result snippet settles every axis (a date, a version, a spec value); anything that needs reading a source is `browser`.
- 134 
- 135 Then create the session directory:
- 136 
- 137 ```bash
- 138 mkdir -p .omo/ulw-research/$(date +%Y%m%d-%H%M%S)
- 139 ```
- 140 
- 141 This is `$SESSION_DIR`. The orchestrator owns the journal: you write every file in it; workers never do (a mass-research dag node writes only its own `waves/<run-key>/<node-id>.md` handoff file, which carries its EXPAND tail and claim candidates; you journal from it). Maintain:
- 142 
- 143 - `brief.md` — the analysis block, the axis list, the expected truths, and the `## Deliverable` record from the interview below (lane, state, formats, each field with `answered_by`).
- 144 - `sources-ledger.md` — one line per source the moment it is read: `[S<n>] <url> — <what it is>`. The closing briefing counts sources and domains from this file.
- 145 - `sources/` and `fact-ledger.json` — the source snapshots and the verbatim fact ledger ([references/fact-ledger.md](references/fact-ledger.md)). Every number and every direct quotation in the report comes from a ledger row through a `{{F<n>:label}}` or `{{Q<n>:label}}` placeholder; nobody types a value into a report or into `SYNTHESIS.md`.
- 146 - `wave-<N>-<kind>-<axis>.md` — your digest of each worker return: key findings, sources with URLs, and the worker's EXPAND markers verbatim.
- 147 - `expansion-log.md` — per wave: workers spawned, markers gained, leads opened and closed.
- 148 - `excursion-log.md` — one ENTER row and one EXIT row per excursion: `excursion_id`, parent claim or axis, ENTER trigger, depth, workers spent, the EXIT rule that closed it, what it changed in the top-level answer (`none` is a valid, required answer), and the ulw-loop steer/evidence id it was mirrored into.
- 149 - `intent-diff.md` — orchestrator-owned expected-truth ledger comparing intent/spec/history to observed reality.
- 150 - `claim-graph.md` — orchestrator-owned claim graph linking every final assertion to observations, counterevidence, dependencies, and verdict.
- 151 - `observation-manifest.md` — orchestrator-owned observation manifest with `observed_at`, temporal validity, artifact paths, and contamination notes.
- 152 - `verification-economics.md` — proof-cost ledger mapping claim risk to verification path, deferral decisions, and residual risk.
- 153 - `cause-disappearance.md` — cause ledger tracking expected truth, previous observation, `last_seen`, disconfirming observation, and whether the violation is no longer observed.
- 154 - `verify-<slug>.md`, `SYNTHESIS.md`, `REPORT.*` from later phases.
- 155 
- 156 Append each digest the moment its worker returns, not in a batch at the end — the journal is your recovery point after context loss and the user's audit trail.
- 157 
- 158 ### Run it as a loop, and journal in real time
- 159 
- 160 ulw-loop is ON by default for this mode: when the `ulw-loop` skill is available, register the research axes as loop goals so the run has durable state and survives a compaction. The session directory's timestamp is the run's start clock — the closing briefing is computed from it, so create it once and never rename it. From that point every finding, source, quote, number, and lead is written into `$SESSION_DIR` **the instant it lands** — never held in the conversation for an end-of-run dump. After any context loss, re-read the brief and the journal before doing anything else, then resume from the open wave.
- 161 
- 162 ### Deliverable lane, format, and the empty-info interview
- 163 
- 164 Never block collection on the shape of the deliverable, and never guess it either. Read [references/deliverable-phase.md](references/deliverable-phase.md) sections 1-6 before writing the brief, then:
- 165 
- 166 1. **Derive first.** Name the lane (`template-strict`, `template-vibe`, `no-format`, `edit-existing`) and the promised formats from the request and its destination (the reference's section 3). When the request refers to an existing deliverable, decide its state with `node "$SKILL_DIR/scripts/report-tools.mjs" outcome state --deliverable <path> --session-dir "$SESSION_DIR"`: `partial` resumes the skeleton on disk, `complete` means edit-existing and never a regenerated report. `$SKILL_DIR` is this skill's own directory, the folder containing this SKILL.md.
- 167 2. **Read the requester's format memory** with the memory tool when the harness exposes one: the pointer `system/human/report-style.md`, then `reference/human-report-style.md`; take the choice recorded for the most similar context (same destination kind and audience) as the first option.
- 168 3. **Ask only what is still missing**: at most the reference's three questions (destination and format, audience and length, template lineage) in one call to the harness question tool (`ask_user_question` or `request_user_input`), non-blocking where the harness supports it, each with its default first, a free-text "describe the format" path, and "don't care, you decide". Collection starts without waiting; a late answer is folded in until the assembly worker starts, and after that it becomes a re-render request.
- 169 4. **Settle source fidelity in the same step.** Seven fields under `## Fidelity` in `brief.md` say what the report must stay faithful to; the reference's section 4 lists each field's values and default. Infer every field before asking anything; an explicit word in the request decides a field (`answered_by: request`), the destination, the sources, and the Phase 0 axes supply the rest (`answered_by: default`):
- 170    - `as of`: a version, release, tag, commit, date, quarter, "as of", "current", or "latest" in the request decides it; a pointed-at repository anchors on its HEAD or tag at run start, pointed-at documents on their own revisions, and a comparison of two anchors records `multiple: <a>, <b>; rows tagged`. Default `latest at run start, <run date>`, the date of the `$SESSION_DIR` timestamp. Ask when the topic is version-bound or time-sensitive (software, APIs, standards, prices, rates, rankings, laws, programs, schedules) and nothing names an anchor; a stable topic takes the default silently.
- 171    - `meaning check`: the QA tier decides (full: `on`, light: `off`); a chat answer on a legal, medical, financial, procurement, or public-facing question with no speed word is `on`. Ask when two explicit signals disagree: a document deliverable under a literal "quick" or "fast", or a light-tier answer that carries both a speed word and a precision demand; `on` goes first.
- 172    - `source floor`: "official docs only", "peer-reviewed only", "SEC filings" give `primary only` or `classes: <host suffixes>`; "from these only" gives `pointed only: <source ids, URLs, or paths>`; pointed-at sources with no restricting word are seeds, not a floor. Default `standard`. Ask when a restricting phrase sits beside an open-ended question whose answer lives outside that floor. Declare each source's provenance when you snapshot it (`source snapshot --provenance primary|secondary`, by the Phase 3b primary-source rule); `primary only` refuses every source not declared `primary`.
- 173    - `derived numbers`: "compare", "growth", "share", "estimate" give `allowed`; "only the sources' own numbers", "no estimates" give `none`. Default `allowed`. Ask when both kinds of phrase share one request. Record only `allowed` or `none` (any other value stops `fact fill` and `fact verify` with a usage error); a partial or free-text answer records `none`.
- 174    - `languages` (never asked): the report in the user's language or the one they named; sources `en`, plus the user's language for a local topic, plus the pointed-at documents' languages; quotes `original` when every source language equals the report language, else `original with translation beside`.
- 175    - `identifier classes` (never asked): from the Phase 0 axes' domain (software: version strings, package names, commit ids; finance: tickers, filing ids, fiscal periods; law: statute, article, and case numbers; science: gene names, DOIs, trial ids), else `none`. It is recorded only; no gate enforces it yet.
- 176    - `fallback` (never asked): `block-quote`, or `omit` on "drop anything you cannot verify"; no other value is accepted.
- 177 
- 178    Ask nothing when the request, the destination, and the sources decide every field. Otherwise ask only the fields whose trigger fired, in the same question-tool call as the format questions (`ask_user_question` or `request_user_input`), non-blocking where the harness supports it, each with its default first, a free-text path, and "don't care, you decide" (it resolves to the first option, recorded `answered_by: user`). At most four questions ride in that call: `pending` fidelity fields first, then format Q1, Q2, Q3, then `as of`, `meaning check`, `source floor`, `derived numbers`; a question that loses its slot runs on its default and is named, with that default, in the reply that opens collection. When each reading of a field would make part of the request undeliverable, record it `pending` with no default. Collection starts regardless: `source snapshot`, `fact add`, `fact quote`, `fact derive`, `fact retract`, and `fact export` keep working while answers are pending; only the six reader-facing commands (`fact fill`, `fact verify`, `fact pairs`, `fact meaning-check`, `fact polish-apply`, `fact polish-diff`) and the assembly lane wait for the lock, and those commands exit 1 with `fidelity_interview_incomplete` while a field is `pending` or missing. When the assembly lane is about to start, a field still awaiting its answer keeps its default; a `pending` field is asked once more, blocking this time.
- 179 5. **Record it.** Write `## Deliverable` into `brief.md` (lane, state, formats, destination, audience, template, format description, each with `answered_by: user|default|request`) plus `## Fidelity` (the block below), and open the manifest in the same step: `node "$SKILL_DIR/scripts/report-tools.mjs" outcome init --promised <formats> --lane <lane> --session-dir "$SESSION_DIR"`. When the ask is to recreate, reproduce, or rebuild something visual, add `Reference compare: required` with the source (URL or file) and the moments to compare; the comparison runs on every round of the build, not only at the end.
- 180 
- 181 #### The fidelity questions
- 182 
- 183 Ask them in the user's language, translating these English texts faithfully and keeping the option order; `<run date>` is the `$SESSION_DIR` date.
- 184 
- 185 - **`as of`**, header `As of`: "Which version or date must the facts hold for? Sources are snapshotted and quoted against that anchor."
- 186   1. `Latest as of today, <run date>` - The state published at the run's start; anything older is flagged as stale.
- 187   2. `Other: a named version, release, or date` - Type it (v3.2, 2026-Q3, a commit or tag). Every quote and number is checked against sources valid at that anchor.
- 188   3. `Don't care, you decide` - Resolves to option 1.
- 189 - **`meaning check`**, header `Drift check`: "Numbers and quotes are always script-checked against source snapshots. Should every explanatory sentence also be read against its source quote by a separate reader? Slower and more tokens; it catches widened scope and dropped hedges."
- 190   1. `On` - Every sentence is paired with its source and read; confirmed drift is rewritten from the quote or listed in the briefing.
- 191   2. `Off (faster)` - Script checks only: numbers, units, quotes, qualifiers, bindings. A paraphrase that shifts meaning is not read.
- 192   3. `Other: where to focus` - Type it ("the financial sections", "anything about the competitor"); those pairs go to the strongest reader.
- 193   4. `Don't care, you decide` - Resolves to option 1.
- 194 - **`source floor`**, header `Sources`: "Which sources may back a statement of fact?"
- 195   1. `Standard: primary source required for high-risk claims` - Numeric, legal, financial, dated, and causal claims need a primary source plus two independent domains; other claims may cite attributed secondary sources.
- 196   2. `Primary only` - Every fact traces to a first-party source (standard, filing, dataset, official doc); commentary appears only as attributed opinion.
- 197   3. `Only the sources I pointed at` - Ledger rows come from the named files and URLs only; anything else is context, not evidence.
- 198   4. `Other: name the source classes` - Type it ("peer-reviewed only", "no vendor blogs").
- 199   5. `Don't care, you decide` - Resolves to option 1.
- 200 - **`derived numbers`**, header `Derived`: "May the report state numbers no source states (sums, growth rates, shares, unit conversions, estimates)?"
- 201   1. `Yes, computed by script and labeled DERIVED` - Each one names its operation and input rows; inputs are checked for unit, period, and population compatibility; an estimate carries its assumptions.
- 202   2. `No, sourced numbers only` - Every number is a MEASURED ledger value; comparisons are stated in words or shown side by side.
- 203   3. `Other: describe` - Type it ("growth rates yes, estimates no"). A partial allowance is recorded as `none`, and the reply that opens collection says so.
- 204   4. `Don't care, you decide` - Resolves to option 1.
- 205 
- 206 #### The `## Fidelity` block
- 207 
- 208 Write it in the same step as `## Deliverable`, provisional defaults included, one line per field with its `answered_by`, plus an `asked:` line naming the fidelity questions sent:
- 209 
- 210 ```text
- 211 ## Fidelity
- 212 as of: latest at run start, 2026-10-23 (answered_by: default)
- 213 meaning check: on (answered_by: default)
- 214 source floor: standard (answered_by: default)
- 215 derived numbers: pending (answered_by: pending)
- 216 languages: report en; sources en; quotes original (answered_by: default)
- 217 identifier classes: version strings, package names, commit ids (answered_by: default)
- 218 fallback: block-quote (answered_by: default)
- 219 asked: derived numbers
- 220 ```
- 221 
- 222 Values carry no parentheses; `pending` goes only with `answered_by: pending`. When an answer lands, rewrite that one line with `answered_by: user` and leave `asked:` as history; a late answer after `fact fill` is a re-render: fill again, then verify.
- 223 
- 224 **Re-entry.** An `edit-existing` session, or any session created before this block existed, has no `## Fidelity`. Before any `fact` command, run the inference step above and write the block with `answered_by: default` on every field. `claims index` on a free-form `claim-graph.md` (no claim table) returns `{claims: [], errors: [...]}`, exits 2, and writes no `claims.json`; run `fact verify` without it, and the gate reports each unbound sentence as `unbound_sentence` (major) instead of blocking.
- 225 
- 226 **Calibration.** `fact meaning-check` appends one line per flagged pair to `--calibration` (default `$SESSION_DIR/fidelity-calibration.jsonl`). After each run, also append that run's new lines to the workspace-level `.omo/ulw-research/fidelity-calibration.jsonl`; promotion of `meaning_drift_confirmed` is decided from that log.
- 227 
- 228 Phase 5 opens by turning the recorded fields into `design-spec.md`.
- 229 
- 230 ## Phase 1 — Saturation wave
- 231 
- 232 **When the user asked for MASS research, the wave is sized by the topic's angles, not by the roster ceiling.** "mass ulw research", "mulw research", "ulw mass research" — in any language — order over-collection that a team of 8 cannot produce. Where the harness has a dependency-graph surface (the `mass-ulw` skill and its `references/planning.md`), run collection through it instead: 60+ angles covering every angle the topic has, routed across the whole difficulty ladder — mechanical sweeps and per-item harvest batches on the cheapest tier, judgment-shaped angles a step up, cross-territory angles a step above that, and the deepest tier reserved for genuinely hairy contradictions. Define each angle as a harvest -> expand -> verify chain before the run starts, each stage reading the previous stage's handoff file; open leads re-enter as new chains in each cluster of angles the moment that cluster settles, and the synthesis reduces through per-cluster architect-tier slice reducers into ONE architect-tier reducer (the strongest reasoning tier substitutes wherever no architect tier exists). Absent that surface, run the same per-angle chains with background workers, pasting each worker's reply into its angle's next-stage prompt the moment it reports. Everything else in this skill still binds: the deliverable interview, the journal, the claim graph, the convergence rules, and the delivery gates.
- 233 
- 234 Otherwise launch the entire first wave in one turn — every axis at once, as team members if you formed a team, else as background workers. Sequential launches and "start with one and see" defeat the mode.
- 235 
- 236 Scaling floor — more angles always justify more workers:
- 237 
- 238 | Query scope | explore | web | repo-dive | floor |
- 239 |---|---|---|---|---|

This preview is limited. See the complete change on GitHub.

Compare on GitHub

Before Not checked yet → After Network or broad shell

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub

Before Network or broad shell → After Network or broad shell

75b017473c71 → 49104cf38aa1

+ 69 ### Machine pre-check - the detect SDK before any reviewer
+ 70 
+ 71 On a web surface, run the `frontend` skill's detect SDK on every enumerated page before capturing for reviewers (`frontend/references/perfection/detect.md`: `detectPage({ kind: "url", url }, { reflow: true })`, or `bun <frontend skill dir>/scripts/detect/cli.ts --reflow --json <url>`). It reads the rendered page and reports contrast against the painted background, the type scale and heading order, overflow at 320-1440 px under an unbroken stress string, and decoration and copy tells. An error or warning is a FAIL on the matching checklist item (E2 contrast, B8 type scale, A9 or A13 layout, F8/F9 surfaces and scaffolds, C4 wrapping) before either reviewer looks; fix it and rerun. Keep the JSON beside the captures and hand it to both reviewers as evidence. Advisories go to the verdict's taste findings.
+ 72 
- 143 - A3 Margins are symmetric; prose sits in a 45-75 character measure.
+ 147 - A3 Margins are symmetric; prose sits in a 65-75 character measure on desktop and at least 45 on a phone.
+ 157 - A13 Spacing rhythm, read from computed values: the space above a section heading is at least 1.5x the space below it, and the gap between groups is at least 2x the gap inside a group (the `frontend` skill's `references/perfection/craft-floor.md`).
+ 167 - B8 Type scale floor, read from computed values: each heading step in use (display to h3, and the smallest heading to body) differs by at least 1.25x in size, and body-family roles (lead, body, small, caption, label) that sit closer also differ by weight, colour or case, a display heading stays at or under 6rem, and letter spacing never goes below -0.04em, unless the brief's chosen style route sets its own display scale or tracking (then that value is the check).
+ 192 - E7 Secondary text on a tinted or coloured surface is a shade of that hue or the foreground at reduced alpha, never neutral gray; a shadow carries a y-offset and a soft blur, never a zero-offset coloured glow unless the brief asked for glowing-border cards (the `frontend` skill's ambience route).
+ 202 - F8 Browser surfaces carry the palette in both themes: text selection, caret, visible scrollbars, focus ring, link underline offset, and tabular numerals in changing or aligned numbers; none shows the browser default (select text and focus a field in the capture to prove it).
+ 203 - F9 None of the generated scaffolds: a kicker label above a heading, an icon tile stacked over a heading in a grid of same-size cards, a hero metric with no decision behind it, a card nested in a card, monospace used as a "technical" costume. One the brief or its chosen route asked for, recorded as such, passes.
+ 204 
+ 205 A13, B8, E7, F8 and F9 are adapted from the craft floor of [pbakaus/impeccable](https://github.com/pbakaus/impeccable) (Apache-2.0, Copyright 2025 Paul Bakaus); the license and the list of changes are in the `frontend` skill's `ATTRIBUTION.md` section 6.

Compare on GitHub

Before Not checked yet → After Network or broad shell

First observation → 75b017473c71

No earlier version was observed for comparison.

Compare on GitHub