Use when reviewing a staged diff or a commit range for soundness against the project's taste rules, including a pre-commit pass or an explicit "sound review".
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
# sound:review
## What to read
- **No argument** → `git diff --cached`.
- **A range** (e.g. `main..HEAD`) → its commits and the whole `git diff <range>`.
## How to review
The project's taste rules live under `.claude/sound/`. Read the ones that bear on the code the diff touches, and apply each rule's `Detect:` and `Not-when:` **verbatim** — never from memory. If `.claude/sound/` is absent, say so and stop.
Review deeply: surface every rule the changes violate, and the enhancements that genuinely matter for this diff's kind. Ground every finding in the diff and the intent behind it — never rule from the text alone. Stay silent where a rule's `Not-when:` applies.
Report most-consequential first: `- <file>: <rule or enhancement> — <anchor>`. If nothing stands, say `CLEAN`.
The line at the top of this page pins the label git:20260724.e9c349c, 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 (991 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
saadshahd/moo.md · 38 stars · license MIT · pushed 2026-11-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_mrpg5otxssxp5hvs
GET https://markdownregistry.com/api/v1/resolve?ref=saadshahd/moo.md/review
GET https://markdownregistry.com/api/v1/blob/43df2c70cd6653428554251fd3bfff0ea51f49566dbbd58e86308ab0fa378beb
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.
saadshahd/moo.md · .claude/skills/moo-authoring/SKILL.md · Use when adding or changing a skill, hook, or runtime file in this repo — including deciding which unit a new…
saadshahd/moo.md · factory/skills/setup/SKILL.md · Set the factory up on the current repo — its GitHub login, rules file, labels, auto-merge, and the worker.
saadshahd/moo.md · hold/skills/grasp/SKILL.md · Build a walkthrough the user works through until they can pass a quiz on it. Use when the user needs to understand…
saadshahd/moo.md · hold/skills/land/SKILL.md · Build a stepped deck an audience works through until one thing of it stays with them. Use when the user needs an…
saadshahd/moo.md · hold/skills/learn/SKILL.md · Help the user understand something well enough to explain it. Use when the user needs to understand something and it is…
saadshahd/moo.md · hold/skills/toy/SKILL.md · Build a world the human drives until how a thing behaves is intuitive. Use when the user needs to hold how something…
saadshahd/moo.md · hope/skills/anchor/SKILL.md · Rewrite a rule so anyone applies it the same way. Use when a stated rule or claim takes the reader's judgment to apply.
saadshahd/moo.md · hope/skills/clarify/SKILL.md · Turn words with two readings into one confirmed ask. Use when the user's words admit two readings that would build…
saadshahd/moo.md · hope/skills/compose/SKILL.md · Plan the skills an ask needs, invoke each as its condition arrives. Use when the ask has multiple aspects that…
saadshahd/moo.md · hope/skills/consult/SKILL.md · Bring how named experts would think about the question. Use when the user wants expert thinking on a tradeoff, choice…
saadshahd/moo.md · hope/skills/deepen/SKILL.md · Hold an ask to the bar a top professional in its field would set — a deeper ask, never a bigger one. Use when an ask is…
qwenlm/qwen-code · packages/core/src/skills/bundled/review/SKILL.md · Review changed code for correctness, security, code quality, and performance. Use when the user asks to review code…
suboss87/fdeops · skills/review/SKILL.md · Review a proposed customer code change against its intended outcome and operational risks. Use for a diff or PR review…
snowflake-labs/cocoplus · .cortex/skills/cocobrew/review/SKILL.md · Enter the Review phase of CocoBrew. Aggregates findings from Code Quality Advisor, CocoCupper intelligence, spec…
dcouple/pane · main/src/services/paneChatBundle/skills/review/SKILL.md · Review a PR against its linked issue, repository checks, correctness, architecture, and applicable conventions. Post…
