Use when writing or reviewing code, comments, tests, or docs.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Code quality
1. **Enforce, don't instruct.** If a machine can check a rule, add the check.
Apply these rules to code you change; fix old code in its own PR.
2. **Comments: none by default.** Keep one only for behavior we cannot change
(vendor, platform, protocol) or a public contract. A reason worth keeping
moves to a test, the docs, or the commit message.
3. **Tests must be able to fail.** Test behavior through the real entry point;
if a test still passes with every dependency returning None, it is fake.
Break the behavior, show the failing run, then land it. Never turn CI
green by skipping, retrying, sleeping, or loosening an assertion.
4. **Docs say only what code cannot.** Keep a sentence only if, without it,
the next person would change the code wrongly. Each fact once, where it
belongs; when docs and code disagree, fix the doc.
The line at the top of this page pins the label git:20261015.d4c34b8, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (1072 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
superdesigndev/treg · 5,899 stars · license a license file GitHub does not identify · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_yaomgbyjaehpv6rm
GET https://markdownregistry.com/api/v1/resolve?ref=superdesigndev/treg/code-quality
GET https://markdownregistry.com/api/v1/blob/a617abdd2941e1edda9dd6e38cf13a30098beb318de3d27374c53c89575f5f2e
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
superdesigndev/treg · .agents/skills/add-oauth-provider/SKILL.md · Add a provider to treg's OAuth registry (the ones treg holds its own approved app for). Use when asked to "add…
superdesigndev/treg · .agents/skills/dev-local/SKILL.md · One-command local dev stack for tools-registry. Use when asked to "start the dev server", "run treg locally", "test…
superdesigndev/treg · .agents/skills/google-ads/SKILL.md · Traps when running Google Ads through treg — the API requirements and cleanup semantics that cost round-trips or money…
superdesigndev/treg · .agents/skills/google-analytics/SKILL.md · Traps to avoid when querying Google Analytics 4 through treg — cases where the GA4 Data API returns a confident wrong…
superdesigndev/treg · .agents/skills/google-search-console/SKILL.md · Traps to avoid when querying Google Search Console through treg — cases where the API returns a confident wrong answer…
superdesigndev/treg · .agents/skills/portrait-clone/SKILL.md · Turn any n reference images (with at least one person) into one exhaustively locked, always de-slopped, JSON-only AIGC…
superdesigndev/treg · .agents/skills/tools-registry-context/SKILL.md · tools-registry context + doc upkeep. Use to warm up a fresh session (orient on the architecture + recent commits) or…
superdesigndev/treg · .agents/skills/ugc-talking-head-video/SKILL.md · Turn a locked character image (from portrait-clone) into a UGC-style 9:16 talking-head video: pick a voice-reference…
superdesigndev/treg · .agents/skills/vendor-listing/SKILL.md · Onboard a vendor who wants their API listed in the treg catalog. Use whenever someone asks "how do we get listed on…
superdesigndev/treg · .agents/skills/write-provider-skill/SKILL.md · Build a treg provider skill — the endpoint map + mistake map that lets an agent do real work on a platform API through…
seedcord/seedcord · .agents/skills/code-quality/SKILL.md · Use this when asked to write code, or audit, sweep, or fix code quality across the seedcord monorepo. Covers the React…
cooneycw/claude-power-pack · .claude/skills/code-quality/SKILL.md · Code review, testing and quality patterns. Use when reviewing code, deciding what testing a change needs, or judging…
smixs/code-quality-skill · skills/code-quality/SKILL.md · Code quality advisor for a repo: one bun script behind git hooks and Claude Code, Codex, Grok, pi, omp, and OpenCode…
