Borrowing it
Nothing to install: this file belongs to baz-scm/awesome-reviewers. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/baz-scm/awesome-reviewers/main/CLAUDE.mdgit clone --depth 1 https://github.com/baz-scm/awesome-reviewersWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/baz-scm/awesome-reviewers/claude-md)<a href="https://agentmods.dev/instructions/baz-scm/awesome-reviewers/claude-md"><img src="https://agentmods.dev/badge/instructions/baz-scm/awesome-reviewers/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/baz-scm/awesome-reviewers/claude-md"><img src="https://agentmods.dev/badge/instructions/baz-scm/awesome-reviewers/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01008 | $0.01008 |
| Opus 5 | $0.00504 | $0.00504 |
| Sonnet 5 | $0.00202 | $0.00202 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
awesome-reviewers CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Awesome Reviewers — repository guidelines
What this project is
A library of expert engineering instructions for AI and infrastructure domains, distilled from code review discussions in production open-source repositories. Consumers are people and agents that need raw, copy-ready expertise: agents, review harnesses, context brokers.
It is a Jekyll site on GitHub Pages. Keep it that way — static, dependency-light, no build step beyond Jekyll and one Python script.
Source of truth
_reviewers/ only:
<slug>.md— front matter (title,description,repository,label,language,comments_count,repository_stars) plus the instruction body in markdown.<slug>.json— the review discussions the instruction was derived from.
Everything else is derived by build_data.py and is not committed: _data/api.json,
_data/domains.json, _data/entries.json, _data/meta.json, _data/sources.json,
assets/data/search.json, domains/*.html, raw/**, llms.txt, openapi.json. Re-run
python build_data.py after touching _reviewers/, and before the first local Jekyll build.
Dates are derived from discussion timestamps, never declared in front matter. Domain is derived from
the source repository via the explicit map in build_data.py.
Site layer
_layouts/base.html— chrome for every page._layouts/domain.html— one page per domain, renders all its instructions from_data/entries.json._layouts/reviewer.html— instruction detail page, metadata from_data/meta.json[page.slug]._includes/row.html— the one row component shared by the homepage, search results and domain pages.assets/css/site.scss— the only stylesheet. No webfonts, no CSS framework.assets/js/site.js— the only script. No dependencies.
Machine interface
openapi.json(OpenAPI 3.1), the/api/page,llms.txt,robots.txtandREADME.mdall describe the same endpoints.DEV_RESOURCESinbuild_data.pyis the single source of truth; add an endpoint there rather than in five places.- Errors follow RFC 9457 problem details.
PROBLEM_TYPESinbuild_data.pydefines them; everytypeURI must resolve to an#error-<code>anchor on the/api/page. 404.htmlis what GitHub Pages serves for every missing path. It carries the recovery links, a markdown recovery block and the same problem details in a<script type="application/problem+json">, because a static host cannot return a JSON body with a 404 status.edge/is an optional CDN worker that addsAcceptnegotiation and real JSON errors. It is excluded from the Jekyll build and the site does not depend on it.- Tests:
python -m unittest discover -s tests -t .andnode --test tests/worker.test.mjs. Both run in CI beforejekyll build.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 73 lines · 1,008 tokens per session scan A 917be7b1825d
awesome-reviewers CLAUDE.md is an instructions file published in the GitHub repository baz-scm/awesome-reviewers (145 stars, last pushed 20d ago), licensed Apache-2.0. It adds 1,008 tokens to every session, about $0.0050 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).