Run a single specialist reviewer of your choice against the codebase: pick one review agent (security, performance, unused code, and so on), optionally scope it to a path, and get its findings in the terminal.
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
# Audit
Run one specialist reviewer against this codebase: $ARGUMENTS
If the line above still shows a placeholder instead of a value, this platform does not pass arguments to skills: take the value from the user's message instead, and treat it as empty when the message gives none. Read every later mention of the placeholder as that value.
Use this instead of `/reviewcrew` when only one review angle matters. `/reviewcrew` runs all reviewers and writes a report file: this command runs exactly one and answers in the terminal.
## Step 1: Resolve the Reviewer
The first word of `$ARGUMENTS` names the reviewer. Everything after it is an optional path to scope the review to: a directory or file. When no path is given, review the whole project.
Available reviewers:
| Name | Covers |
|------|--------|
| `security` | Injection, XSS, auth, SSRF, JWT, secrets, supply chain |
| `code` | Correctness, style, anti-patterns, performance, memory, concurrency |
| `architecture` | Structure, coupling, cohesion, SOLID, duplication, observability |
| `performance` | Bottlenecks, complexity, queries, caching, scalability |
| `test` | Coverage, assertion quality, flakiness, mocking, test data |
…
The line at the top of this page pins the label git:20261014.5b60e38, 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.
GET https://markdownregistry.com/api/v1/artifacts/art_hbslfzlsggw4iqir
GET https://markdownregistry.com/api/v1/resolve?ref=rashadansari/myagents/audit
GET https://markdownregistry.com/api/v1/blob/2e715b618653f541d26503a332e5dcd12bb52dbd7fb7cabbf3bfb7d632cc1019
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.
rashadansari/myagents · plugins/albino/skills/agent-memory/SKILL.md · Use the agent-memory MCP server to retrieve, verify, and store durable project knowledge and global user knowledge…
rashadansari/myagents · plugins/albino/skills/commit-pr/SKILL.md · Create a git commit and open a pull request (creates a new branch first if on main/master)
rashadansari/myagents · plugins/albino/skills/eu-ai-act/SKILL.md · Reference knowledge on the EU AI Act (Regulation (EU) 2024/1689): risk tiers, obligations, compliance deadlines…
rashadansari/myagents · plugins/albino/skills/frontend-design/SKILL.md · Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to…
rashadansari/myagents · plugins/albino/skills/humanizer/SKILL.md · Remove signs of AI-generated writing from text. Use when editing or reviewing
text to make it sound more natural and…
rashadansari/myagents · plugins/albino/skills/markitdown/SKILL.md · Convert files, URLs, and documents to Markdown using the markitdown MCP server. Activate when the user asks to convert…
jeremylongshore/tons-of-skills-marketplace · plugins/ai-agency/hyperflow/skills/audit/SKILL.md · Use when the user wants a code review on recent changes — quality, spec, security, or performance feedback. Triggers a…
suboss87/fdeops · skills/audit/SKILL.md · Audit an inherited engagement or implementation against its evidence. Use when taking over work or joining mid-project…
oliver-kriska/claude-elixir-phoenix · plugins/elixir-phoenix/skills/audit/SKILL.md · Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when…
3x-haust/oh-my-design · skills/audit/SKILL.md · Audit current renders and stress coverage, repair real defects and stop under the bound refinement policy.
hainrixz/claude-seo-ai · skills/audit/SKILL.md · Audit a website or web codebase for SEO and AI-search (GEO/AEO) — produces two independent 0-100 scores (Search SEO +…
