agentleFS

AGENTS.md examples from real projects

How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.

Best matches · from page 9Worked for most · soon
rapid7AGENTS.md

metasploit-framework

rapid7/metasploit-framework/AGENTS.md

available linked issues, module documentation, and review discussion alongside the diff. Prioritize correctness, security, regressions, compatibility, and reproducible validation of changed behavior. - Ground each finding in a concrete trigger, affected

39k2y agoReviewMountCreate a free account to mount
chatwootAGENTS.md

chatwoot

chatwoot/chatwoot/AGENTS.md

requirement. - Before adding a dependency, verify current upstream maintenance, release activity, community/support health, and security advisories and patch responsiveness. Do not introduce abandoned or unmaintained packages. Prefer a small, readable

Steady2 mentions in 2 weeks

No other project uses it yet

39k4y agoReviewMountCreate a free account to mount
AdguardTeamReads credentialsAGENTS.md

AdGuardHome / client_v2

AdguardTeam/AdGuardHome/client_v2/AGENTS.md

stable release rather than copying a stale version. **Rationale**: Fewer, well-vetted dependencies reduce security vulnerabilities, supply-chain risk, and long-term maintenance cost. **Known exclusions** (to be fixed): - Most

Steady6 mentions in 2 weeks

No other project uses it yet

38k3mo agoReviewMountCreate a free account to mount
keycloakAGENTS.md

keycloak

keycloak/keycloak/AGENTS.md

breaks. In Markdown files in the repository, put each sentence on its own line. ## Security vulnerabilities Do not create public issues for security vulnerabilities. Follow the process in [SECURITY.md](SECURITY.md

38k6mo agoReviewMountCreate a free account to mount
nextcloudAGENTS.md

server

nextcloud/server/AGENTS.md

github.com/nextcloud/.github/blob/master/AI_POLICY.md)** - the primary reference for AI-specific rules, covering disclosure, author accountability, communication, security, licensing, code quality, and autonomous agent behavior. - **[Contribution Guidelines](https://github.com/nextcloud/.github/blob/master/CONTRIBUTING.md)** - covering testing requirements

37k24d agoReviewMountCreate a free account to mount
markedjsAGENTS.md

marked

markedjs/marked/AGENTS.md

Open/Closed Principle: provide extension hooks rather than bloating core with endless configuration toggles. ### 3. Security & Scope Boundaries - **No Sanitization in Core**: Marked's single responsibility is translating Markdown into HTML

37k6y agoReviewMountCreate a free account to mount
virgiliojr94AGENTS.md

book-to-skill

virgiliojr94/book-to-skill/AGENTS.md

Preserve backwards compatibility unless the task explicitly authorizes a breaking change. - Do not weaken security checks, path hardening, sanitization, or generated-skill scanning to make an experiment pass. ## Execution loop

3 projects use a version of this

37k5mo agoReviewMountCreate a free account to mount
pnpmAGENTS.md

pnpm

pnpm/pnpm/AGENTS.md

lives in **[review-code review guide](./.agents/skills/review-code/references/REVIEW_GUIDE.md)** — how changes are accepted or rejected, the security-first / performance-second priorities, the security checklist and advisory regression themes, and the test/changeset/version-coverage expectations

37k9d agoReviewMountCreate a free account to mount
pnpmAGENTS.md

pnpm / pnpr

pnpm/pnpm/pnpr/AGENTS.md

pnpr/`. **Read [`../AGENTS.md`](../AGENTS.md) and [`../PHILOSOPHY.md`](../PHILOSOPHY.md) first.** They cover the monorepo-wide philosophy: security, performance, efficient disk usage, predictability, and feature consolidation. They also cover PR workflow, signing agent

37k9d agoReviewMountCreate a free account to mount
MicrosoftDeletes or force-pushesAGENTS.md

Data-Science-For-Beginners

microsoft/Data-Science-For-Beginners/AGENTS.md

server enables hot-reload for quick iteration - Production builds are optimized and minified ### Security Notes - No sensitive data or credentials should be committed - Use environment variables for any API keys

Steady49 mentions in 2 weeks

No other project uses it yet

37k14mo agoReviewMountCreate a free account to mount
MicrosoftDeletes or force-pushesAGENTS.md

Data-Science-For-Beginners / en

microsoft/Data-Science-For-Beginners/translations/en/AGENTS.md

server enables hot-reload for quick iteration - Production builds are optimized and minified ### Security Notes - No sensitive data or credentials should be committed - Use environment variables for any API keys

Steady49 mentions in 2 weeks

No other project uses it yet

37k14mo agoReviewMountCreate a free account to mount
MicrosoftDeletes or force-pushesAGENTS.md

Data-Science-For-Beginners / my

microsoft/Data-Science-For-Beginners/translations/my/AGENTS.md

server သည် hot-reload ကို enable လုပ်သည် - Production builds များသည် optimized နှင့် minified ဖြစ်သည် ### Security Notes - Sensitive data သို့မဟုတ် credentials များကို commit မလုပ်ပါနှင့် - Cloud lessons များတွင် API keys အတွက် environment

Steady49 mentions in 2 weeks

No other project uses it yet

37k14mo agoReviewMountCreate a free account to mount
MicrosoftDeletes or force-pushesAGENTS.md

Data-Science-For-Beginners / pcm

microsoft/Data-Science-For-Beginners/translations/pcm/AGENTS.md

server dey enable hot-reload for quick iteration - Production builds dey optimized and minified ### Security Notes - No sensitive data or credentials suppose dey committed - Use environment variables

Steady49 mentions in 2 weeks

No other project uses it yet

37k14mo agoReviewMountCreate a free account to mount
MicrosoftDeletes or force-pushesAGENTS.md

Data-Science-For-Beginners / tl

microsoft/Data-Science-For-Beginners/translations/tl/AGENTS.md

kredensyal ng Azure account - Panatilihing updated ang mga dependencies para sa mga security patch ## Pag-aambag sa Mga Pagsasalin - Ang mga automated na pagsasalin ay pinamamahalaan sa pamamagitan ng GitHub

Steady49 mentions in 2 weeks

No other project uses it yet

37k14mo agoReviewMountCreate a free account to mount
wailsappAGENTS.md

wails

wailsapp/wails/AGENTS.md

that summary. Conventional title types choose the category; `changelog:added|changed|fixed|deprecated|removed|security` labels override it, and `skip-changelog` excludes a PR. Internal-only title types are excluded

No other project uses it yet

37k17d agoReviewMountCreate a free account to mount
BlockReads credentialsAGENTS.md

sprout

block/sprout/AGENTS.md

names the concrete defect and the fix. - Recommend blocking only for concrete correctness, security, or agreed-contract defects with a realistic failure scenario: state the defect, how it fails

37k7d agoReviewMountCreate a free account to mount
TencentAGENTS.md

WeKnora / cli

Tencent/WeKnora/cli/AGENTS.md

headers. `_notice` is reserved — open-map infrastructure is in place for deprecation / version_skew / security notices; the field is omitted until a producer is wired in v0.8. `profile` echoes

No other project uses it yet

37k49d agoReviewMountCreate a free account to mount
utmappAGENTS.md

UTM

utmapp/UTM/AGENTS.md

QEMU out-of-process** (XPC: `QEMUHelper`→`QEMULauncher`); host files reach it only through a security-scoped-bookmark dance — respect it for anything touching disk images, shared dirs, or file handles

No other project uses it yet

37k5d agoReviewMountCreate a free account to mount
gchqAGENTS.md

CyberChef

gchq/CyberChef/AGENTS.md

live under `tests/browser/` and are run with `npm run testui` or `npm run testuidev`. ## Security - Avoid prototype pollution. Utilise `Object.create(null)`, `Map`, and `Object.prototype.hasOwnProperty.call(...)`. - Avoid XSS. Escape strings before rendering

36k8mo agoReviewMountCreate a free account to mount
alan2207AGENTS.md

bulletproof-react

alan2207/bulletproof-react/AGENTS.md

HTTP requests with MSW instead of mocking fetch - Focus on user interactions and outcomes ## Security Considerations ### Authentication - **JWT tokens** stored in HttpOnly cookies (preferred) or localStorage - **React Query Auth

No other project uses it yet

36k2y agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

About AGENTS.md

What is AGENTS.md?

An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.

Where does it go?

At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.

What should it contain?

Setup and test commands, code style, and the rules a new contributor would need to know.

Does Claude Code read it?

Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.