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 18Worked for most · soon
bytedanceAGENTS.md

sonic

bytedance/sonic/AGENTS.md

tests or benchmark data for performance changes, and update user documentation when behavior changes. ## Security & Compatibility Notes Do not disclose security bugs in public issues; follow `CONTRIBUTING.md` and contact

No other project uses it yet

9.6k21mo agoReviewMountCreate a free account to mount
apacheAGENTS.md

jmeter

apache/jmeter/AGENTS.md

Security model: [SECURITY.md](./SECURITY.md) ## Building and testing JMeter builds with Gradle. Use `./gradlew --quiet ...` to reduce output verbosity. After modifying Java code, before reporting the change as done (handing control

9.6k3y agoReviewMountCreate a free account to mount
LearningCircuitAGENTS.md

local-deep-research

LearningCircuit/local-deep-research/AGENTS.md

src/local_deep_research/web/app.py`, `src/local_deep_research/web/fastapi_app.py`, `src/local_deep_research/web/routers/`, `src/local_deep_research/web/services/` | | Auth and sessions | `src/local_deep_research/web/auth/`, `src/local_deep_research/database/encrypted_db.py` | | Settings | `src/local_deep_research/settings/`, `src/local_deep_research/settings/env_definitions/`, `src/local_deep_research/web/routers/settings.py`, `src/local_deep_research/defaults/` | | Security and safe HTTP | `src/local_deep_research/security/` (`safe_requests.py`, `ssrf_validator.py`, `egress/`); policy in `SECURITY.md` | | LLM and embedding providers | `src/local_deep_research/llm/providers

9.6k6mo agoReviewMountCreate a free account to mount
FinbAGENTS.md

Bark

Finb/Bark/AGENTS.md

abstraction layer over Alamofire - **Material/SnapKit** - UI framework and Auto Layout DSL - **CryptoSwift** - Encryption for secure push notifications - **Kingfisher** - Image downloading and caching ### Data Flow 1. **Device Registration**: App requests APNs

9.5k59d agoReviewMountCreate a free account to mount
pocoprojectAGENTS.md

poco

pocoproject/poco/AGENTS.md

that specific action, as listed in [outward writes](ai-agents/git-and-pull-requests.md#outward-writes). 10. **Security.** Do not discuss an unpublished vulnerability in public issues, pull requests or commit messages

9.5k3y agoReviewMountCreate a free account to mount
WebGoatAGENTS.md

WebGoat

WebGoat/WebGoat/AGENTS.md

Gradle is not configured; Maven is the only supported build system. - Spring MVC, Thymeleaf, Security, Data JPA, Actuator, and OAuth2 Client. - HSQLDB persistence with Flyway-owned schemas; Hibernate

9.4k14mo agoReviewMountCreate a free account to mount
git-ecosystemAGENTS.md

git-credential-manager

git-ecosystem/git-credential-manager/AGENTS.md

index](docs/README.md): user-facing configuration and provider-specific guidance. - [SECURITY.md](SECURITY.md): private reporting of security vulnerabilities. ## Making changes - Inspect the affected implementation and tests before editing. Reuse existing helpers

Steady5 mentions in 2 weeks

No other project uses it yet

9.4k4y agoReviewMountCreate a free account to mount
apacheAGENTS.md

iceberg

apache/iceberg/AGENTS.md

below is ambiguous, pick the option that produces less for a reviewer to read. ## Security Model When assessing potential vulnerabilities or calibrating automated security findings, use [`SECURITY-THREAT-MODEL.md`](SECURITY-THREAT-MODEL.md

9.4k46d agoReviewMountCreate a free account to mount
wealthfolioAGENTS.md

wealthfolio

wealthfolio/wealthfolio/AGENTS.md

scroll handling; values via the formatting hooks. Details in `apps/frontend/src/i18n/README.md`. ## Persisted identifiers and security - Reuse named constants for secret-store keys and identifiers shared across code paths. Put shared constants

Steady5 mentions in 2 weeks

1 project uses a version of this

9.4k10mo agoReviewMountCreate a free account to mount
caorushiziAGENTS.md

mediago / vercel-react-best-practices

caorushizi/mediago/.agents/skills/vercel-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

9.3k3mo agoReviewMountCreate a free account to mount
databasusAGENTS.md

databasus / frontend

databasus/databasus/frontend/AGENTS.md

call `navigator.clipboard` directly. - **Copy:** `BrowserClipboard.copyToClipboard(text)` — uses `navigator.clipboard` with `execCommand('copy')` fallback for non-secure contexts (HTTP). - **Paste:** Check `BrowserClipboard.isClipboardApiAvailable()` first. If available, use `BrowserClipboard.readFromClipboard()`. If not, show `ClipboardPasteModalComponent` (`shared/ui

9.3k3d agoReviewMountCreate a free account to mount
Jigsaw-CodeAGENTS.md

outline-apps / server_manager

Jigsaw-Code/outline-apps/server_manager/AGENTS.md

macOS**: `.dmg` and `.zip` (both required for auto-update). You may need to run `security unlock-keychain login.keychain` so electron-builder has access to your certificates. ## Debugging

9.3k10mo agoReviewMountCreate a free account to mount
bigbluebuttonAGENTS.md

bigbluebutton

bigbluebutton/bigbluebutton/AGENTS.md

duplicate the full agent policy. **Canonical instructions:** see `CLAUDE.md`. In particular, follow the security-reporting guidance in `CLAUDE.md` and do not open public PRs for suspected vulnerabilities

9.3k6mo agoReviewMountCreate a free account to mount
golang-jwtAGENTS.md

jwt

golang-jwt/jwt/AGENTS.md

Instructions for AI agents and AI-assisted contributors This is `golang-jwt/jwt`, a security-sensitive library used by a very large number of projects. It is maintained

No other project uses it yet

9.3k12d agoReviewMountCreate a free account to mount
CloudflareAGENTS.md

workerd

cloudflare/workerd/AGENTS.md

translated (`src/workerd/server/cli/wrangler.rs`) - Main schema: `src/workerd/server/workerd.capnp` - Sample configurations in `samples/` directory - Configuration uses capability-based security model ### Where to Look | Task | Location | Notes | | ---------------------- | ------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------ | | Add/modify JS API | `src/workerd/api/` | C++ with JSG macros

9.2k8mo agoReviewMountCreate a free account to mount
CloudflareAGENTS.md

workerd / per_isolate

cloudflare/workerd/src/per_isolate/AGENTS.md

guarantee — and what they do not.** Primordials are an **internal correctness** mechanism, not a security sandbox. The hard security boundary is the V8 isolate: separate address spaces, no shared mutable

9.2k8mo agoReviewMountCreate a free account to mount
CloudflareAGENTS.md

workerd / events

cloudflare/workerd/src/tests/events/AGENTS.md

half is unit tested in `src/workerd/api/event-target-bootstrap-test.c++`. ## Tests that live elsewhere (by design) - `src/workerd/api/tests/messageport-postmessage-uaf-test.js`: a security regression single, deliberately not merged into the suite. - `messagePortLegacyRedispatch` and `eventSourceLegacyError` in `src/workerd/api/tests/legacy-dispatch-exceptions-test.js`, which pins

9.2k8mo agoReviewMountCreate a free account to mount
CloudflareAGENTS.md

workerd / streams

cloudflare/workerd/src/tests/streams/AGENTS.md

src/workerd/api/tests/ts-webstreams-test.js` — TypeScript-impl internals (native/buffer/iterable bodies ARE ts streams, pumpTo); single-implementation by nature. - Security regression singles in `src/workerd/api/tests/` (streams-byob-close-reentry, streams-byob-concurrent-readatleast, streams-byte-cancel

9.2k8mo agoReviewMountCreate a free account to mount
CloudflareAGENTS.md

workerd / htmlrewriter

cloudflare/workerd/src/tests/streams/htmlrewriter/AGENTS.md

api/tests htmlrewriter-transform-cancel-test.js (cancel-before-read ×50 UAF regression) stays where it is, per the security-regression policy

9.2k8mo agoReviewMountCreate a free account to mount
VercelAGENTS.md

agent-eval / vercel-react-best-practices

vercel-labs/agent-eval/packages/playground/.agents/skills/vercel-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

Rising+2 new adopters in 4 weeks

54 projects use a version of this

2789mo 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.