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 20Worked for most · soon
playcanvasAGENTS.md

engine

playcanvas/engine/AGENTS.md

Questions? When in doubt: 1. Look at similar existing code in the codebase 2. Check the ESLint configuration 3. Review recent commits for patterns 4. If unclear or multiple valid

No other project uses it yet

17k11d agoReviewMountCreate a free account to mount
ipfsAGENTS.md

kubo

ipfs/kubo/AGENTS.md

minimum bar, not a courtesy. ## Go Style Follow these Go style references: - [Go Code Review Comments](https://go.dev/wiki/CodeReviewComments) - [Google Go Style Decisions](https://google.github.io/styleguide/go/decisions) Specific conventions for this

17k3mo agoReviewMountCreate a free account to mount
opfAGENTS.md

openproject

opf/openproject/AGENTS.md

linters and tests relevant to the changed files: - Ruby and ERB: follow the [code review guidelines](docs/development/code-review-guidelines/README.md#coding-style); use [lefthook.yml](lefthook.yml) for the configured checks. - JavaScript and TypeScript: follow

17k5y agoReviewMountCreate a free account to mount
argoprojAGENTS.md

argo-workflows

argoproj/argo-workflows/docs/AGENTS.md

features/` notes become release notes: write for users, not reviewers, and remember featuregen drops blank lines, so no indented code blocks, unindented lists or separate paragraphs. - Use Argo's terms

17k12mo agoReviewMountCreate a free account to mount
zephyrproject-rtosAGENTS.md

zephyr

zephyrproject-rtos/zephyr/AGENTS.md

implying it was done. - Review comments written with AI help are verified by the human before posting; never post raw model output (`doc/contribute/reviewer_expectations.rst`). - Commit messages, code comments, Kconfig help texts

17k6mo agoReviewMountCreate a free account to mount
a2ui-projectAGENTS.md

a2ui

a2ui-project/a2ui/AGENTS.md

tasks, load and read the respective skill recipe file in full: - **For authoring code, refactoring, addressing review feedback, or reviewing PR diffs across any language:** Read [.agents/skills/coding-principles/SKILL.md](.agents/skills/coding-principles/SKILL.md) (progressively activates

17k6d agoReviewMountCreate a free account to mount
GoogleAGENTS.md

A2UI

google/A2UI/AGENTS.md

tasks, load and read the respective skill recipe file in full: - **For authoring code, refactoring, addressing review feedback, or reviewing PR diffs across any language:** Read [.agents/skills/coding-principles/SKILL.md](.agents/skills/coding-principles/SKILL.md) (progressively activates

17k9d agoReviewMountCreate a free account to mount
systemdAGENTS.md

systemd

systemd/systemd/AGENTS.md

style guide (must-read before writing code) - `docs/CONTRIBUTING.md` — contribution guidelines and PR workflow - `docs/VARLINK.md` — Varlink API guidelines. Read in full before writing or reviewing changes to Varlink APIs, and apply

17k9d agoReviewMountCreate a free account to mount
tikvAGENTS.md

tikv

tikv/tikv/AGENTS.md

make test # Using nextest (faster) env EXTRA_CARGO_ARGS=$TESTNAME make test_with_nextest ``` ### Code Quality ```bash # Run formatter make format # Run clippy linter (use this instead of cargo clippy

17k5mo agoReviewMountCreate a free account to mount
emqxAGENTS.md

emqx

emqx/emqx/AGENTS.md

post GitHub comments or review replies** unless you were asked to. Address review feedback in code and commits, and report the comment-to-commit mapping to the person

Steady6 mentions in 2 weeks

No other project uses it yet

17k3y agoReviewMountCreate a free account to mount
AppleAGENTS.md

foundationdb

apple/foundationdb/AGENTS.md

year from now? Is it genuinely essential and **non-obvious from the code itself**? ## Code Review When reviewing, state explicitly: what the change is for, whether it is correct, bugs

No other project uses it yet

17k6mo agoReviewMountCreate a free account to mount
FlashML-orgAGENTS.md

FreeToken

FlashML-org/FreeToken/AGENTS.md

comment`, or `gh issue create` on the user's behalf. - Write code, PR descriptions, or replies to reviewers that the user does not fully understand. The user must be able

17k10d agoReviewMountCreate a free account to mount
ipythonAGENTS.md

ipython

ipython/ipython/AGENTS.md

frequent requests. Pull requests for edge cases that code analysis found, and that users are unlikely to hit, may wait for review until all higher-priority pull requests are merged

17k13d agoReviewMountCreate a free account to mount
kubernetesAGENTS.md

kops

kubernetes/kops/AGENTS.md

bash make gofmt make goimports ``` ### Linting The project uses `golangci-lint` to lint the code. You can run the linter by running the following command: ```bash make verify-golangci-lint

17k5y agoReviewMountCreate a free account to mount
opensandbox-groupAGENTS.md

OpenSandbox

opensandbox-group/OpenSandbox/AGENTS.md

backslash) are only for intentional rendering, never for prose wrapping. Keep verbatim blocks untouched: code blocks, tables, YAML frontmatter, HTML blocks, ASCII diagrams. Never reflow generated markdown (e.g., helm-docs

1 project uses a version of this

17k11d agoReviewMountCreate a free account to mount
triggerdotdevAGENTS.md

trigger.dev

triggerdotdev/trigger.dev/AGENTS.md

namespace catalog, running crumbs init" load: "node_modules/agentcrumbs/skills/agentcrumbs/init/SKILL.md" ## agentcrumbs Add crumbs as you write code — not just when debugging. Mark lines with `// @crumbs` or wrap blocks in `// #region @crumbs`. They

Steady7 mentions in 2 weeks

No other project uses it yet

17k3mo agoReviewMountCreate a free account to mount
aio-libsAGENTS.md

aiohttp

aio-libs/aiohttp/AGENTS.md

Sphinx; `make doc` builds locally. - No docstrings or comments that just restate the code. ## Changelog - Fragments in `CHANGES/{pr_or_issue}.{type}.rst` (valid types are defined in `pyproject.toml` under

No other project uses it yet

17k6mo agoReviewMountCreate a free account to mount
Lakr233AGENTS.md

vphone-cli

Lakr233/vphone-cli/AGENTS.md

launcher. - `VPhoneExecutable/VPhoneCommand`: `vphone-cli`, firmware patcher, signer, and command tests. - `VPhoneExecutable/VPhoneCommand/VPhoneRestore`: native restore code and tests. - `VPhoneExecutable/VPhoneEscalator`: the AMFI allowlist program, built for arm64e. It is not a general privilege

17k7d agoReviewMountCreate a free account to mount
FreshRSSAGENTS.md

FreshRSS

FreshRSS/FreshRSS/AGENTS.md

FreshRSS introduction and conventions for AI agents and human contributors

17k19d agoReviewMountCreate a free account to mount
ai-shifuAGENTS.md

ChatALL

ai-shifu/ChatALL/AGENTS.md

alias (configured in `jsconfig.json`) instead of deep relative paths when importing from `src/`. - Keep code comments and implementation notes in English, and add concise comments only when logic

17k21mo 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.