AGENTS.md examples from real projects

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

Best matches · from page 3Worked for most · soon

MicrosoftAGENTS.md

ML-For-Beginners / ml

microsoft/ML-For-Beginners/translations/ml/AGENTS.md

മോഡൽ ഡിപ്ലോയ്മെന്റിനുള്ള വെബ് ആപ്പ് ഫ്രെയിംവർക്ക് - **Docsify**: ഡോക്യുമെന്റേഷൻ സൈറ്റ് ജനറേറ്റർ - **GitHub Actions**: CI/CD, സ്വയം വിവർത്തനങ്ങൾ ## Security Considerations - **കോഡിൽ രഹസ്യങ്ങൾ ഇല്ല**: API കീകൾ അല്ലെങ്കിൽ ക്രെഡൻഷ്യലുകൾ ഒരിക്കലും കമ്മിറ്റ് ചെയ്യരുത് - **ഡിപ്പെൻഡൻസികൾ**: npm, pip പാക്കേജുകൾ

91k12mo agoDeletes or force-pushesDiscuss

MicrosoftAGENTS.md

ML-For-Beginners / pcm

microsoft/ML-For-Beginners/translations/pcm/AGENTS.md

model deployment - **Docsify**: Documentation site generator - **GitHub Actions**: CI/CD and automated translations ## Security Considerations - **No secrets for code**: No ever commit API keys or credentials - **Dependencies**: Keep

91k12mo agoDeletes or force-pushesDiscuss

MicrosoftAGENTS.md

ML-For-Beginners / te

microsoft/ML-For-Beginners/translations/te/AGENTS.md

కోసం వెబ్ అప్లికేషన్ ఫ్రేమ్‌వర్క్ - **Docsify**: డాక్యుమెంటేషన్ సైట్ జనరేటర్ - **GitHub Actions**: CI/CD మరియు ఆటోమేటెడ్ అనువాదాలు ## Security Considerations - **కోడ్‌లో రహస్యాలు లేవు**: API కీలు లేదా క్రెడెన్షియల్స్ ఎప్పుడూ కమిట్ చేయవద్దు - **డిపెండెన్సీలు**: npm మరియు

91k12mo agoDeletes or force-pushesDiscuss

AstralAGENTS.md

uv

astral-sh/uv/AGENTS.md

webhook events instead of adding `pull_request_target` workflows - NEVER suppress the `dangerous-triggers` security lint; extend the automation dispatcher in a separate pull request if it does not support

90k2mo agoDiscuss

koala73AGENTS.md

worldmonitor

koala73/worldmonitor/AGENTS.md

solutions](docs/solutions/) when the affected area has a prior fix — organized by category directory (`security-issues/`, `logic-errors/`, `conventions/`, …) with YAML frontmatter (`module`, `component`, `problem_type`, `tags`) to grep

87k18d agoDiscuss

bytedanceAGENTS.md

deer-flow

bytedance/deer-flow/AGENTS.md

Install.md](Install.md)**, **[CONTRIBUTING.md](CONTRIBUTING.md)** - Project overview & usage → **[README.md](README.md)** (translations: `README_zh.md`, `README_ja.md`, `README_fr.md`, `README_ru.md`) - Security policy → **[SECURITY.md](SECURITY.md)** - Changes → **[CHANGELOG.md](CHANGELOG.md)** - Cutting a release → **[RELEASING.md](RELEASING.md)** ## Cross-Cutting Conventions These

83k3mo agoReads credentialsDiscuss

ElasticAGENTS.md

elasticsearch

elastic/elasticsearch/AGENTS.md

jobs expect ephemeral hosts; do not run packaging suites on your workstation. - **Security**: Default dev clusters enable security; use `elastic-admin:elastic-password` or disable with `-Dtests.es.xpack.security.enabled=false`. - **Cursor/Copilot rules

78k5mo agoDiscuss

MicrosoftAGENTS.md

ai-agents-for-beginners

microsoft/ai-agents-for-beginners/AGENTS.md

lessons (numbered 00-18) covering fundamentals, design patterns, frameworks, production deployment, local/on-device agents, and security of AI agents. **Key Technologies:** - Python 3.12+ - Jupyter Notebooks for interactive learning - AI Frameworks: Microsoft

75k3mo agoReads credentialsDiscuss

MicrosoftAGENTS.md

ai-agents-for-beginners / en

microsoft/ai-agents-for-beginners/translations/en/AGENTS.md

75k3mo agoReads credentialsDiscuss

MicrosoftAGENTS.md

ai-agents-for-beginners / pcm

microsoft/ai-agents-for-beginners/translations/pcm/AGENTS.md

number 00-18) wey cover fundamentals, design patterns, frameworks, production deployment, local/on-device agents, plus security for AI agents. **Key Technologies:** - Python 3.12+ - Jupyter Notebooks for interactive learning - AI Frameworks: Microsoft

75k3mo agoReads credentialsDiscuss

ruvnetAGENTS.md

ruflo

ruvnet/ruflo/AGENTS.md

scopes; Ruflo records coordination. 6. Test focused, regression, and failure paths. 7. Validate types, security, policy, compatibility, and artifact integrity. 8. Benchmark a source-bound candidate against a source-bound

73k21d agoReads credentialsDiscuss

colbymchenryAGENTS.md

codegraph

colbymchenry/codegraph/AGENTS.md

calling codegraph entirely (maintainer-observed, repeatedly). `isError` is reserved for genuine "stop trying" cases: security refusals (`PathRefusalError`) and real malfunctions (which carry a retry-once note). Every expected/recoverable condition — project

72k57d agoDeletes or force-pushesDiscuss

diegosouzapwAGENTS.md

OmniRoute

diegosouzapw/OmniRoute/AGENTS.md

streams — use abort signals for cleanup - Return proper HTTP status codes (4xx/5xx) ### Security - **Never** use `eval()`, `new Function()`, or implied eval - Validate all inputs with Zod schemas - Encrypt credentials

71k12d agoReads credentialsDiscuss

code-yeongyuAGENTS.md

oh-my-openagent

code-yeongyu/oh-my-openagent/.agents/AGENTS.md

70k11d agoDiscuss

code-yeongyuAGENTS.md

oh-my-openagent

code-yeongyu/oh-my-openagent/AGENTS.md

when sidebar is disabled ├─→ initLiveServerRoute() + setLiveParentWakeRoutingDisabled() + warmLiveServerProbe() # live-listener wake routing ├─→ selectRuntimeSecuritySkills() + createRuntimeSkillSourceServer() # runtime security-skill source ├─→ initI18n() # load locale strings (packages/omo-opencode/src/locales/) ├─→ setAgentSortOrder() # apply configured agent_order ├─→ initializeOpenClaw() # if openclaw

70k11d agoReads credentialsDiscuss

code-yeongyuAGENTS.md

oh-my-openagent

code-yeongyu/oh-my-openagent/.opencode/AGENTS.md

Remove unused code with LSP-verified safety + atomic commits. | | `/security-research` | Run the Team Mode security-research audit with 3 vulnerability hunters and 2 PoC engineers. | ## OTHER CONTENTS - `background-tasks.json` — Runtime state

70k11d agoDiscuss

code-yeongyuAGENTS.md

oh-my-openagent / tests

code-yeongyu/oh-my-openagent/tests/AGENTS.md

equality between real artifacts, and observable runtime behavior such as parsing, routing, dispatch, state, security, and dynamic input propagation. - Treat `tests/hashline/` as its own Bun package. Preserve its lockfile

70k11d agoReads credentialsDiscuss

mem0aiAGENTS.md

mem0

mem0ai/mem0/AGENTS.md

bend. ### Reference | Topic | File | |-------|------| | Contributor guide | [`CONTRIBUTING.md`](CONTRIBUTING.md) | | Code of conduct | [`CODE_OF_CONDUCT.md`](CODE_OF_CONDUCT.md) | | Security reports | [`SECURITY.md`](SECURITY.md) | | Development setup | `docs/contributing/development.mdx` | | Documentation contributions | `docs/contributing/documentation.mdx` | | PR template | `.github/PULL_REQUEST_TEMPLATE.md` | | Issue forms | `.github/ISSUE_TEMPLATE/` | | Contribution

66k22d agoReads credentialsDiscuss

gsd-buildAGENTS.md

get-shit-done

gsd-build/get-shit-done/AGENTS.md

relevant, test evidence, affected platforms/runtimes, and update `CHANGELOG.md` or docs for user-facing changes. ## Security & Configuration Tips Do not commit secrets, local config, or generated worktree artifacts. Before release-facing

65k4mo agoDiscuss

gsd-buildAGENTS.md

get-shit-done

gsd-build/get-shit-done/docs/AGENTS.md

65k4mo agoDiscuss

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.