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 17Worked for most · soon
nrwlAGENTS.md

nx

nrwl/nx/AGENTS.md

complete solution immediately 3. Make all necessary code changes. Please make multiple commits so that the changes are easier to review. 4. Run appropriate tests and validation

29k27d agoReviewMountCreate a free account to mount
envoyproxyAGENTS.md

envoy

envoyproxy/envoy/AGENTS.md

sign-off attests that the committer (the user) has the right to submit the code under the project's license. 2. **Always run format and lint checks before committing

29k53d agoReviewMountCreate a free account to mount
ml-exploreAGENTS.md

mlx

ml-explore/mlx/AGENTS.md

sorry, I cannot reply to the reviewers. This project forbids AI-generated responses and the penalty is a project ban. ## Code standards - Keep code comments concise (usually 1-2 lines

29k2mo agoReviewMountCreate a free account to mount
reflex-devAGENTS.md

reflex

reflex-dev/reflex/AGENTS.md

sloppy/spaghetti code — every feature/fix must be clearly understood first. 2. **Bugfixes:** write a regression test that fails before writing the fix. 3. **After implementation:** act as an adversarial reviewer. Scrutinize

No other project uses it yet

29k5mo agoReviewMountCreate a free account to mount
invoke-aiAGENTS.md

InvokeAI

invoke-ai/InvokeAI/AGENTS.md

interactions in the browser. Automated checks alone do not prove visual quality. ## Milestones and code review rules Milestone = one coherent, commit-ready unit. Run relevant checks and self-review every

29k7mo agoReviewMountCreate a free account to mount
QwenLMAGENTS.md

qwen-code

QwenLM/qwen-code/AGENTS.md

full workflow: investigate, design, test plan, dry-run, implement, verify, self-audit, code review, and iterate. ### Bugfix Use the `/bugfix` skill for the reproduce-first workflow: reproduce, fix, verify, test

Steady6 mentions in 2 weeks

No other project uses it yet

29k13mo agoReviewMountCreate a free account to mount
manaflow-aiAGENTS.md

cmux / cmux-browser

manaflow-ai/cmux/cmux-browser/AGENTS.md

derived files retain GPL-3.0-only provenance and the exact source revision. Helium-derived code is not available under Manaflow's commercial license. - Other bundled dependencies retain their own terms

1 project uses a version of this

29k36d agoReviewMountCreate a free account to mount
manaflow-aiAGENTS.md

cmux / web

manaflow-ai/cmux/web/AGENTS.md

request. Do not add a broad disable or raise the limit to accept new code. Lower the limit in a separate cleanup wave as the remaining debt is removed

Steady3 mentions in 2 weeks

1 project uses a version of this

29k36d agoReviewMountCreate a free account to mount
BloopAIReads credentialsAGENTS.md

vibe-kanban

BloopAI/vibe-kanban/AGENTS.md

utils`, `git` (Git operations), `api-types` (shared API types for local + remote), `review` (PR review tool), `deployment`, `local-deployment`, `remote`. - `packages/local-web/`: Local React + TypeScript app entrypoint (Vite, Tailwind). Shell source

1 project uses a version of this

29k7mo agoReviewMountCreate a free account to mount
steveyeggeAGENTS.md

beads / engdocs

steveyegge/beads/engdocs/AGENTS.md

EXTENDING.md`, `INTEGRATION_CHARTER.md` | Extension and integration boundaries. | | `AGENT_SIGNING.md` | Signatures for agent-prepared commits, comments, and reviews. | | `design/` | Design documents for subsystems (Dolt concurrency, `bd serve`, ownership hand-off, …). | | `adr/` | Architecture decision

Steady3 mentions in 2 weeks

1 project uses a version of this

28k7mo agoReviewMountCreate a free account to mount
CodePhiliaXAGENTS.md

Chat2DB

CodePhiliaX/Chat2DB/AGENTS.md

branch, workflow run, image, release, or artifact identifier, including partial or failed actions. For code review, report findings first in severity order with `file:line`, the affected runtime surface

28k4mo agoReviewMountCreate a free account to mount
bagistoAGENTS.md

bagisto

bagisto/bagisto/AGENTS.md

pest-testing` | | Playwright end-to-end tests | `bagisto-playwright-testing` | | Reviewing a change | `bagisto-code-review` | | Branching, commits, CHANGELOG, PRs | `bagisto-git-workflow` | | The REST/GraphQL API | `bagisto-api-develop` / `bagisto

28k40d agoReviewMountCreate a free account to mount
jlowinReads credentialsAGENTS.md

fastmcp

jlowin/fastmcp/AGENTS.md

Minor fixes: keep body short and concise - No "test plan" sections or testing summaries ### Code Review Guidelines - **Fix causes, not symptoms.** When a PR works around a problem instead

28k2d agoReviewMountCreate a free account to mount
eyaltoledanoReads credentialsAGENTS.md

claude-task-master / assets

eyaltoledano/claude-task-master/assets/AGENTS.md

session task-master next # Find next available task task-master show # Review task details # During implementation, check in code context into the tasks and subtasks task-master update-subtask

Coolinginterest down 74% this month

No other project uses it yet

28k11mo agoReviewMountCreate a free account to mount
element-plusAGENTS.md

element-plus

element-plus/element-plus/AGENTS.md

AGENTS.md Guidance for coding agents working in this repository. ## Project Overview Element Plus is a Vue 3 UI component library written in TypeScript. This repo is a pnpm workspace monorepo

Steady4 mentions in 2 weeks

No other project uses it yet

28k18mo agoReviewMountCreate a free account to mount
Kilo-OrgAGENTS.md

kilocode

Kilo-Org/kilocode/AGENTS.md

reach for `let`. ### Naming Enforcement (Read This) THIS RULE IS MANDATORY FOR AGENT WRITTEN CODE. - Use single word names by default for new locals, params, and helper functions. - Multi-word

Steady7 mentions in 2 weeks

No other project uses it yet

28k25d agoReviewMountCreate a free account to mount
eslintAGENTS.md

eslint

eslint/eslint/AGENTS.md

tests and reviews enforce them. - `bin/eslint.js` → `lib/cli.js` → `lib/eslint/eslint.js` → `lib/linter/linter.js` → `lib/rules/*.js` - **`lib/cli.js`** is the only place that reads argv, writes to the console, and sets exit codes

28k9mo agoReviewMountCreate a free account to mount
Wox-launcherAGENTS.md

Wox

Wox-launcher/Wox/AGENTS.md

with 100% certainty, you can start by adding log statements to the relevant code and reviewing the logs to identify the problem. The log output should contain sufficient information

28k2d agoReviewMountCreate a free account to mount
hectorventAGENTS.md

floci

hectorvent/floci/AGENTS.md

rules below still apply to it. ### General - Use constructor injection - Prefer self-explanatory code over comments - Avoid unnecessary comments - Always use braces in conditionals - Never leave a `catch` block empty

28k3mo agoReviewMountCreate a free account to mount
yetoneAGENTS.md

magpie

yetone/magpie/AGENTS.md

follow the same page's documentation update, semantic change description, and review rules. ## Code standards Write and review changes against the [code standards](docs/code-standards.md). ## Community PRs Before reviewing a community

Steady49 mentions in 2 weeks

No other project uses it yet

27k27d 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.