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 15Worked for most · soon
Hugging FaceAGENTS.md

diffusers

huggingface/diffusers/.ai/AGENTS.md

post to GitHub directly** — no comments, reviews, or replies. Draft when asked and hand the text to the user. ## Code formatting - `make style` and `make fix-copies` should

35k2mo agoReviewMountCreate a free account to mount
SeleniumHQAGENTS.md

selenium

SeleniumHQ/selenium/AGENTS.md

Grid routing/distributor/queue logic ## After making code changes - Call out any high risk areas touched - Note cross-binding impact and any follow-up issues needed ## Reviewing pull requests See `.github/pr_review.md

No other project uses it yet

35k14d agoReviewMountCreate a free account to mount
k3s-ioAGENTS.md

k3s

k3s-io/k3s/.agents/AGENTS.md

Use when: browsing or selecting local k3s agentic workflows from this folder. Catalog of workflow folders and contract for cross-tool compatibility.

Steady3 mentions in 2 weeks

No other project uses it yet

34k5mo agoReviewMountCreate a free account to mount
GitlawbAGENTS.md

openclaude

Gitlawb/openclaude/AGENTS.md

working in the OpenClaude repository. Read it before changing code, and also follow [CONTRIBUTING.md](CONTRIBUTING.md) for contributor policy, PR expectations, review follow-up, and project scope. ## Project Snapshot OpenClaude

34k32d agoReviewMountCreate a free account to mount
swc-projectAGENTS.md

swc

swc-project/swc/AGENTS.md

continue. ## Code style - Write comments and documentations in English. - Write documentation for your code. - When introducing a workaround, leave sufficient comments explaining why it is needed and any known limitations

34k51d agoReviewMountCreate a free account to mount
apacheAGENTS.md

kafka

apache/kafka/AGENTS.md

checkstyleMain checkstyleTest spotlessCheck ./gradlew spotbugsMain spotbugsTest -x test # optional static analysis ``` Checkstyle reports: ` /build/reports/checkstyle/`. ## Coding conventions - **Commits / PR titles**: Start with `KAFKA-XXXXX`, `MINOR`, or `HOTFIX`. Use `KAFKA-XXXXX` only

34k3mo agoReviewMountCreate a free account to mount
iOfficeAIAGENTS.md

AionUi

iOfficeAI/AionUi/AGENTS.md

path aliases: `@/*`, `@process/*`, `@renderer/*` - Prefer `type` over `interface` (per Oxlint config) - English for code comments; JSDoc for public functions ### Internationalization (i18n) New or changed user-facing text must use i18n

Steady5 mentions in 2 weeks

No other project uses it yet

34k8mo agoReviewMountCreate a free account to mount
OWASPAGENTS.md

CheatSheetSeries

OWASP/CheatSheetSeries/AGENTS.md

security review and testing. Illustrative status does not excuse incorrect or insecure guidance. - When reviewing code-heavy contributions, request a shorter conceptual revision with upstream implementation links. Successful execution

34k41d agoReviewMountCreate a free account to mount
hiddifyAGENTS.md

hiddify-app

hiddify/hiddify-app/AGENTS.md

data or migration risk. Otherwise **Needs review**, saying what to look at. - **Complexity Simple**: small, one area, no native code, migration, or API change. **Complex**: several areas, native code, connection/core

34k9mo agoReviewMountCreate a free account to mount
Yeachan-HeoAGENTS.md

oh-my-codex / templates

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

still marks that skill active. Use explicit team orchestration for feature development, bug investigation, code review, UX audit, and similar multi-lane work when coordination value outweighs overhead. Team mode

Steady24 mentions in 2 weeks

No other project uses it yet

34k7mo agoReviewMountCreate a free account to mount
alibabaAGENTS.md

nacos

alibaba/nacos/AGENTS.md

intended behavior differs from the existing spec, do not silently implement the code first: discuss the change with maintainers and update the affected specs as part of the design

Steady5 mentions in 2 weeks

No other project uses it yet

34k10mo agoReviewMountCreate a free account to mount
telegramdesktopDeletes or force-pushesAGENTS.md

tdesktop

telegramdesktop/tdesktop/AGENTS.md

Agent Guide for Telegram Desktop This guide defines repository-wide instructions for coding agents working with the Telegram Desktop codebase. ## AI Tasks In this repository "task" is a specific term

33k14d agoReviewMountCreate a free account to mount
remix-runAGENTS.md

remix

remix-run/remix/AGENTS.md

review focused UI library examples, including an adversarial product UX review. ## App And Demo Skills For working on Remix code in demos or writing Remix app code, use the root

33k7d agoReviewMountCreate a free account to mount
VercelAGENTS.md

agent-skills / vercel-optimize

vercel-labs/agent-skills/skills/vercel-optimize/AGENTS.md

projects that are not deployed on Vercel, greenfield projects with no traffic, or general code review. ## Requirements - Node.js 20+ - Vercel CLI with `vercel metrics`, `vercel usage`, `vercel contract`, and `vercel

Steady4 mentions in 2 weeks

18 projects use a version of this

33k6mo agoReviewMountCreate a free account to mount
onyx-dot-appReads credentialsAGENTS.md

onyx

onyx-dot-app/onyx/AGENTS.md

Common tasks table in `.agents/feature-map/INDEX.md`. - Look up a code path in `.agents/feature-map/PATHS.md` to find its component. - The step-by-step review procedure is `.agents/feature-map/VERIFYING.md`. - Onyx overloads words such as Persona

33k5d agoReviewMountCreate a free account to mount
zeroclaw-labsAGENTS.md

zeroclaw

zeroclaw-labs/zeroclaw/AGENTS.md

panic impossible. - Do not suppress unused production code with underscore names or `#[allow(dead_code)]`; remove it, connect it, or track it. Underscore names remain valid for required but intentionally

No other project uses it yet

33k47d agoReviewMountCreate a free account to mount
podman-container-toolsAGENTS.md

podman

podman-container-tools/podman/AGENTS.md

Podman Development ![PODMAN logo](https://raw.githubusercontent.com/containers/common/main/logos/podman-logo-full-vert.png) ## Persona This guide is for AI coding assistants (for example Claude, ChatGPT, Copilot). Use it for context on codebase layout, development patterns, testing

Steady11 mentions in 2 weeks

1 project uses a version of this

33k5mo agoReviewMountCreate a free account to mount
lbjlaqAGENTS.md

Antigravity-Manager

lbjlaq/Antigravity-Manager/AGENTS.md

Checks**: Execute only when tagging final releases; should not be executed during daily tasks, code reviews, simple edits, simple debugging, or trivial hardcoded changes. Run on demand before releasing

33k22d agoReviewMountCreate a free account to mount
tirth8205Deletes or force-pushesAGENTS.md

code-review-graph

tirth8205/code-review-graph/AGENTS.md

must push - If push fails, resolve and retry until it succeeds ## MCP Tools: code-review-graph **This project has a knowledge graph. Start with the code-review-graph MCP tools

No other project uses it yet

33k5mo agoReviewMountCreate a free account to mount
SigNozAGENTS.md

signoz / frontend

SigNoz/signoz/frontend/AGENTS.md

implement structural fixes. Ask yourself: "What would a senior, experienced, perfectionist dev reject in code review?" Fix all of it. 2. REVIEWABLE FILES: When creating new code, follow the rules

33k10d 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.