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 9Worked for most · soon
ChromeDevToolsAGENTS.md

chrome-devtools-mcp

ChromeDevTools/chrome-devtools-mcp/AGENTS.md

implement upstream code in this repository. - [ ] Puppeteer internals are imported only through `src/third_party/index.ts`. - [ ] Repeated code is one helper. Extract a helper when the same block appears two or more times

Steady22 mentions in 2 weeks

No other project uses it yet

57k6mo agoReviewMountCreate a free account to mount
ayghriAGENTS.md

i-have-adhd

ayghri/i-have-adhd/AGENTS.md

Authorship, labels, safety, review, and PR requirements. | ## Runtime entry points When debugging or changing one integration, begin with its entry point: | Runtime | Read first | | --- | --- | | Claude Code | `.claude-plugin/plugin.json`, `hooks/hooks.json

Steady6 mentions in 2 weeks

1 project uses a version of this

57k5mo agoReviewMountCreate a free account to mount
BlockAGENTS.md

goose

block/goose/AGENTS.md

discussion instead. - Read the agreed design, constraints, non-goals, and verification plan before changing code. - Keep the implementation within the issue's agreed scope. - If implementation reveals a material design

1 project uses a version of this

57k4mo agoReviewMountCreate a free account to mount
HKUDSReads credentialsAGENTS.md

DeepTutor

HKUDS/DeepTutor/AGENTS.md

reporting | | `visualize` | analyzing → generating → reviewing (SVG / Chart.js / Mermaid / HTML; or routes to Manim sub-stages via `render_type`) | | `math_animator` | concept_analysis → concept_design → code_generation → code_retry → summary → render

Steady5 mentions in 2 weeks

No other project uses it yet

57k3mo agoReviewMountCreate a free account to mount
multica-aiReads credentialsAGENTS.md

multica

multica-ai/multica/AGENTS.md

keys, cascading deletes, or cascading updates. Validate relationships and clean up dependents in application code, using a transaction when the operation must be atomic. - Every migration-created index, including indexes

No other project uses it yet

56k19d agoReviewMountCreate a free account to mount
bmad-code-orgAGENTS.md

BMAD-METHOD

bmad-code-org/BMAD-METHOD/AGENTS.md

instructions for exotic cases — the model usually handles them from context, and the reviewing human can correct it when it does not. - Write template conditionals as block-level

Steady3 mentions in 2 weeks

No other project uses it yet

55k58d agoReviewMountCreate a free account to mount
ggml-orgAGENTS.md

whisper.cpp

ggml-org/whisper.cpp/AGENTS.md

used responsibly for: - **Learning and exploration**: Understanding codebase structure, techniques, and documentation - **Code review assistance**: Obtaining suggestions on human-written code - **Mechanical tasks**: Formatting, generating repetitive patterns from established designs

Steady12 mentions in 2 weeks

No other project uses it yet

55k6mo agoReviewMountCreate a free account to mount
JetBrainsAGENTS.md

kotlin / compiler

JetBrains/kotlin/compiler/AGENTS.md

Representation) Located in `compiler/ir/`. Backend IR is used by all targets for: - Lowering (transforming code to target-friendly form) - Optimization - Serialization to klibs Backend implementations: - `compiler/ir/backend.jvm/` - JVM backend - `compiler/ir/backend.js/` - JavaScript

No other project uses it yet

54k12d agoReviewMountCreate a free account to mount
expoAGENTS.md

expo

expo/expo/AGENTS.md

affects: Android, iOS, or web. An Android-only change needs Android screenshots. Shared code needs a pair for every platform that runs it. Do not use an iOS Simulator screenshot

No other project uses it yet

54k21d agoReviewMountCreate a free account to mount
dbeaverAGENTS.md

dbeaver

dbeaver/dbeaver/AGENTS.md

ensure each change is understood and reviewed by a human contributor. - AI tools disclosure: if AI tools were used to generate code, mention it in the PR description. Example: *This

Steady5 mentions in 2 weeks

No other project uses it yet

52k3mo agoReviewMountCreate a free account to mount
QuantumNousAGENTS.md

new-api

QuantumNous/new-api/AGENTS.md

tool — not a grep, a partial skim, memory, or a summary — before planning, coding, or reviewing, and then follow every rule in it. A task touches billing when it meets

Steady9 mentions in 2 weeks

No other project uses it yet

52k1d agoReviewMountCreate a free account to mount
alibabaAGENTS.md

open-code-review

alibaba/open-code-review/AGENTS.md

Agent Guidelines for open-code-review This file provides instructions for AI coding assistants working on this project. ## Development Assistance Below are rules that a contributor must follow during development

Steady13 mentions in 2 weeks

No other project uses it yet

52k3mo agoReviewMountCreate a free account to mount
roboflowAGENTS.md

supervision

roboflow/supervision/AGENTS.md

Confirm alignment with `src/supervision/` architecture. - For pull request reviews, follow [.github/skills/code-review/SKILL.md](.github/skills/code-review/SKILL.md). ______________________________________________________________________ ## 2. Repository Architecture **Package root**: `src/supervision/` — all library code. **Tests**: `tests/` — mirrors `src/supervision/`. **Public API**: `src/supervision/__init__.py`. ``` src/supervision/ ├── detection

Steady8 mentions in 2 weeks

No other project uses it yet

52k10mo agoReviewMountCreate a free account to mount
VercelAGENTS.md

agent-browser

vercel-labs/agent-browser/AGENTS.md

cli/src/color.rs`. This module respects the `NO_COLOR` environment variable. Never use hardcoded ANSI color codes. - CLI flags must always use kebab-case (e.g., `--auto-connect`, `--allow-file-access`). Never

Steady31 mentions in 2 weeks

No other project uses it yet

51k19d agoReviewMountCreate a free account to mount
moeru-aiAGENTS.md

airi

moeru-ai/airi/AGENTS.md

review UI appearance and interaction | [AIRI Design Guide](DESIGN.md) | | Write, refactor, or review TypeScript or Vue code, including date, time, and unit helpers | [`enforce-rules-for-typescript`](.agents/skills/enforce-rules-for-typescript/SKILL.md) | | Write

Steady5 mentions in 2 weeks

No other project uses it yet

51k2d agoReviewMountCreate a free account to mount
AstralAGENTS.md

ruff

astral-sh/ruff/AGENTS.md

Rooster configuration could not be inspected, say so when reporting the PR. ## Code Review Rules For security reviews of Ruff and ty runtime changes, use the [threat models](.agents/references/threat-models.md

Steady5 mentions in 2 weeks

No other project uses it yet

51k5d agoReviewMountCreate a free account to mount
cypress-ioAGENTS.md

cypress

cypress-io/cypress/AGENTS.md

Dependency Updates Whether you're bumping a dependency or reviewing a Renovate PR, follow [Code Review of Dependency Updates](./CONTRIBUTING.md#code-review-of-dependency-updates). Read the changelog for every

No other project uses it yet

51k2d agoReviewMountCreate a free account to mount
TanStackAGENTS.md

query

TanStack/query/AGENTS.md

supported environments. Do not add fallbacks for hypothetical callers. - Verify automated review findings against the code and the application path. Determine whether each finding is a regression, a pre-existing

No other project uses it yet

51k12mo agoReviewMountCreate a free account to mount
pandas-devAGENTS.md

pandas

pandas-dev/pandas/AGENTS.md

limited to, interactions such as pushing code, opening issues or pull requests, and replying to issues, pull requests, or reviews. - The user is required to disclose your agent information (harness

No other project uses it yet

51k2d agoReviewMountCreate a free account to mount
mudlerAGENTS.md

LocalAI

mudler/LocalAI/AGENTS.md

MODEL_VERSION [TOOL1] [TOOL2]`. - **The human submitter is responsible** for reviewing, testing, and understanding every line of generated code. ## Topics | File | When to read | |------|-------------| | [.agents/ai-coding-assistants.md](.agents/ai-coding-assistants.md) | Policy for AI-assisted

Steady3 mentions in 2 weeks

No other project uses it yet

50k3y 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.