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 10Worked for most · soon
nettyAGENTS.md

netty

netty/netty/AGENTS.md

github/workflows/autoport-*.yml`). When a cherry-pick conflicts, the port must be done manually. ## Security Netty parses untrusted network input (HTTP/1.x, HTTP/2, HTTP/3, and more), implements TLS on top of BoringSSL/OpenSSL

35k9d agoReviewMountCreate a free account to mount
backstageAGENTS.md

backstage

backstage/backstage/AGENTS.md

code style. - `/REVIEWING.md`: guidelines for pull requests and writing changesets. - `/SECURITY.md`: guidelines for security. - `/docs/architecture-decisions/`: contains the architecture decisions for the project. All new source files

35k4d agoReviewMountCreate a free account to mount
apacheAGENTS.md

kafka

apache/kafka/AGENTS.md

Agent Guide for Apache Kafka This file is read by automated agents (security scanners, code analyzers, AI assistants) operating on this repository. ## Project overview Apache Kafka is a distributed event

34k3mo agoReviewMountCreate a free account to mount
hiddifyAGENTS.md

hiddify-app

hiddify/hiddify-app/AGENTS.md

migration, or API change. **Complex**: several areas, native code, connection/core logic, DB migrations, or security-relevant code. - If the change spans repos (e.g. hiddify-core), link the related PR. ## Opening

Steady4 mentions in 2 weeks

No other project uses it yet

34k2d agoReviewMountCreate a free account to mount
OWASPAGENTS.md

CheatSheetSeries

OWASP/CheatSheetSeries/AGENTS.md

tools most often break. > The audience for every cheat sheet is **developers, not security experts**. Content must be accurate, practical, concise, and opinionated. We would rather have _good_ advice

34k44d agoReviewMountCreate a free account to mount
Yeachan-HeoAGENTS.md

oh-my-codex / templates

Yeachan-Heo/oh-my-codex/templates/AGENTS.md

missing authority, or an irreversible/destructive branch. - Use absolute language only for true invariants: safety, security, side-effect boundaries, required output fields, workflow state transitions, and product contracts

Steady23 mentions in 2 weeks

No other project uses it yet

34k7mo agoReviewMountCreate a free account to mount
gethomepageAGENTS.md

homepage

gethomepage/homepage/AGENTS.md

preparing a PR, especially for anything large or involving AI-generated code. ## Issue and security reports - Issue reports must describe observed behavior only: what happened, how to reproduce

34k6d agoReviewMountCreate a free account to mount
telegramdesktopDeletes or force-pushesAGENTS.md

tdesktop

telegramdesktop/tdesktop/AGENTS.md

change, one whose correctness needs a real testing campaign, or one that is safety-, security- or data-safety-critical. Make the offer in one line, say why, and route

34k5d agoReviewMountCreate a free account to mount
alibabaAGENTS.md

nacos

alibaba/nacos/AGENTS.md

Distributed Lock Spec](./specs/en/lock/lock-spec.md) - Extension model: [Integration And Adapter Spec](./specs/en/integration/integration-adapter-spec.md), [Plugin Specs](./specs/en/plugin/README.md) - Security model: [Auth And Permission Spec](./specs/en/auth/auth-permission-spec.md), [Auth Plugin Spec](./specs/en/auth/auth-plugin-spec.md), [RAM Auth Plugin Spec](./specs/en/auth/ram-auth-plugin-spec.md

Steady29 mentions in 2 weeks

No other project uses it yet

34k10mo agoReviewMountCreate a free account to mount
onyx-dot-appReads credentialsAGENTS.md

onyx

onyx-dot-app/onyx/AGENTS.md

server, web_server, celery_X) will be tailing their logs to this file. ## Security Considerations - Never commit API keys or secrets to the repository - Use the encrypted credential storage

33k1d agoReviewMountCreate a free account to mount
onyx-dot-appAGENTS.md

onyx / mobile

onyx-dot-app/onyx/mobile/AGENTS.md

mock; this also satisfies `import/first`). - Native mocks are centralized: MMKV self-mocks, `expo-secure-store` manual mock in `__mocks__/`, resets in `jest.setup.ts`. - A generic fn like `apiFetch ` makes `jest.mocked()` infer

33k1d agoReviewMountCreate a free account to mount
zeroclaw-labsAGENTS.md

zeroclaw

zeroclaw-labs/zeroclaw/AGENTS.md

module, factory wiring, adjacent tests, and relevant docs before editing. 2. For architecture, config, security, workflow, governance, CI, release, or agent-assisted changes, start with `docs/book/src/contributing/architecture-map.md`. 3. Name the source

33k51d agoReviewMountCreate a free account to mount
VercelAGENTS.md

agent-skills / react-best-practices

vercel-labs/agent-skills/skills/react-best-practices/AGENTS.md

invoked directly. Next.js documentation explicitly states: "Treat Server Actions with the same security considerations as public-facing API endpoints, and verify if the user is allowed to perform a mutation

33k6mo agoReviewMountCreate a free account to mount
containersAGENTS.md

podman

containers/podman/AGENTS.md

Makefile** (`make help`, `make binaries`, `make validatepr`); match the **Go** version in `go.mod`. **Security** issues use the private process linked from CONTRIBUTING, not public GitHub. AI-assisted contributions must follow

1 project uses a version of this

33k6mo agoReviewMountCreate a free account to mount
garrytanPipes a download into a shellAGENTS.md

gbrain

garrytan/gbrain/AGENTS.md

false`, set by `src/cli.ts`) from **untrusted agent-facing callers** (`remote = true`, set by `src/mcp/server.ts`). Security-sensitive operations like `file_upload` tighten filesystem confinement when `remote = true` and default to strict

Steady41 mentions in 2 weeks

No other project uses it yet

33k3mo agoReviewMountCreate a free account to mount
conductor-ossAGENTS.md

conductor

conductor-oss/conductor/AGENTS.md

higher versions are always welcome — use one of two lowercase prefixes instead: ```groovy // Security: CVE-2025-12183 — lz4-java minimum patched version // Compat: commons-lang3 3.18.0+ required by Testcontainers/commons-compress ``` - `// Security

32k11mo agoReviewMountCreate a free account to mount
OpenAIAGENTS.md

openai-python

openai/openai-python/AGENTS.md

handwritten policy, automation, tests, and examples small; alter exported APIs only when explicitly required. ## Security requirements for coding agents Read and apply [contributor security requirements](CONTRIBUTING.md#security-requirements-for-contributions

Steady3 mentions in 2 weeks

No other project uses it yet

32k9d agoReviewMountCreate a free account to mount
FujiwaraChokiReads credentialsAGENTS.md

MoneyPrinterV2

FujiwaraChoki/MoneyPrinterV2/AGENTS.md

description. - Mark not-ready PRs with `WIP` and remove it when ready for review. ## Security & Configuration Tips - Treat `config.json` as environment-specific; do not commit real API keys or private

32k9mo agoReviewMountCreate a free account to mount
dragonflydbAGENTS.md

dragonfly

dragonflydb/dragonfly/AGENTS.md

basic), < 5.1 (epoll fallback) - Check: `uname -r` - Force epoll: `--proactor_type=epoll` - Docker: `--security-opt seccomp=unconfined` **FreeBSD**: Supported (kqueue backend) **macOS**: Not supported for production (use Docker/Linux) **For complete

Steady2 mentions in 2 weeks

No other project uses it yet

32k9mo agoReviewMountCreate a free account to mount
LangChainAGENTS.md

deepagents

langchain-ai/deepagents/AGENTS.md

labels, and troubleshooting. - [LangChain contributing guide](https://docs.langchain.com/oss/python/contributing/overview) — general contribution policy. ## Corridor security analysis When Corridor's `analyzePlan` tool is available, create a plan and use the tool

Steady4 mentions in 2 weeks

No other project uses it yet

31k3mo 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.