AGENTS.md examples from real projects

How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.

Best matches · from page 14Worked for most · soon

“code review” 1k+ stars

DicklesworthstoneAGENTS.md

destructive_command_guard

Dicklesworthstone/destructive_command_guard/AGENTS.md

# AGENTS.md — dcg (Destructive Command Guard) > Guidelines for AI coding agents working in this Rust

6.1k36d agoDeletes or force-pushesDiscuss

DicklesworthstoneAGENTS.md

destructive_command_guard

Dicklesworthstone/destructive_command_guard/docs/agents.md

allowed, warned about, sent for review, or denied. The exit status changes only when a blocking verdict could not be delivered: | Code | Constant | Meaning | |------|----------|---------| | 0 | `EXIT_SUCCESS` | Verdict delivered

6.1k36d agoDeletes or force-pushesDiscuss

Microsoft AzureAGENTS.md

azure-sdk-for-net

Azure/azure-sdk-for-net/AGENTS.md

integration tests following existing patterns - **Bug Fixes**: Identifying and fixing issues in SDK code - **API Review**: Preparing code for API reviews and ensuring adherence to design guidelines #### Documentation - **README Updates

6.1k6mo agoDiscuss

FlorianBruniauxAGENTS.md

claude-code-ultimate-guide

FlorianBruniaux/claude-code-ultimate-guide/AGENTS.md

audits, and codebase reviews. ### Public content must be portable Apply this rule to guides, evaluations, examples, changelogs, indexes, exports, and landing content, including code blocks, tables, captions, and link targets

6k19d agoDiscuss

kenn-ioAGENTS.md

agentsview

kenn-io/agentsview/AGENTS.md

Tests, Testing, Verification, or Test plan. - Explain what the code does now, why it changed, tradeoffs, limits, and where reviewers should look

6k10d agoDiscuss

jacklandrinAGENTS.md

OnlySwitch

jacklandrin/OnlySwitch/AGENTS.md

applicable Context Routing guidance and the saved plan when one exists. 7. **Review the code — subagent: 5.6 Terra.** Review the implementation and tests for correctness, architecture compliance, edge cases, concurrency

6k5y agoDiscuss

oomol-labAGENTS.md

open-connector

oomol-lab/open-connector/AGENTS.md

idiomatic for this repo, and leave a brief reason when responding in review. - Do not manually wrap code to 80 columns. Let `oxfmt` decide formatting. ## Runtime API - Keep `/v1` response

5.9k29d agoDiscuss

generalactionAGENTS.md

emdash

generalaction/emdash/AGENTS.md

Overview Emdash is a local-first, cross-platform Electron app for running multiple AI coding agents in parallel. Each task is isolated in its own Git worktree

5.9k7mo agoDiscuss

lemonade-sdkAGENTS.md

lemonade

lemonade-sdk/lemonade/AGENTS.md

AGENTS.md This file provides guidance to agent driven code reviews when working with this repository. ## Project Overview Lemonade is a local LLM server providing GPU and NPU acceleration for running

5.8k21d agoReads credentialsDiscuss

Galaxy-DawnAGENTS.md

claude-scholar / rules

Galaxy-Dawn/claude-scholar/rules/agents.md

Kaggle solutions | Learning competition strategies and pipelines | ### Development Workflow | Agent | Purpose | When to Use | |-------|---------|-------------| | code-reviewer | Code quality, security, and maintainability review | After writing or modifying code | | tdd-guide | Test

5.6k6mo agoDiscuss

Microsoft AzureAGENTS.md

azure-sdk-for-python

Azure/azure-sdk-for-python/AGENTS.md

draft mode ✅ Run existing test suites ✅ Validate CODEOWNERS entries #### Restricted Operations ⚠️ Modifying generated code (requires review) ⚠️ Adding new dependencies (requires justification) ⚠️ Changing API signatures (requires design review) ⚠️ Disabling or removing

5.6k19mo agoDiscuss

GargantuaXAGENTS.md

gemini-watermark-remover

GargantuaX/gemini-watermark-remover/AGENTS.md

alone is not enough. - Treat `texture.hardReject`, `visibleDarkHole`, and selection-stage damage warnings as noisy review signals, not independent cleanliness truth. Confirmed clean exact-48 rescues can trigger them, while visible

5.6k3mo agoReads credentialsDiscuss

21st-devAGENTS.md

1code / openspec

21st-dev/1code/openspec/AGENTS.md

OpenSpec Instructions Instructions for AI coding assistants using OpenSpec for spec-driven development. ## TL;DR Quick Checklist - Search existing work: `openspec spec list --long`, `openspec list` (use `rg` only

5.6k8mo agoDiscuss

junhoyeoAGENTS.md

tokscale

junhoyeo/tokscale/AGENTS.md

title and does not contain worker/agent/internal review jargon. ## Commit Message Convention ``` : [optional body] ``` ### Types | Type | Description | |------|-------------| | `feat` | New feature | | `fix` | Bug fix | | `refactor` | Code refactoring (no behavior change) | | `docs` | Documentation

5.6k10d agoDiscuss

maziyarpanahiAGENTS.md

openmed

maziyarpanahi/openmed/AGENTS.md

change should explain the local command, the CI gate, and the expected developer workflow. ## Coding Style & Architecture Rules Use Python 3.10+, 4-space indentation, and 88-character lines. Prefer `snake

5.4k47d agoDiscuss

VercelAGENTS.md

eve

vercel/eve/AGENTS.md

AGENTS.md Guidance for coding agents (and humans) working in this repository. For setup, PR workflow, and release process, see [CONTRIBUTING.md](./CONTRIBUTING.md). ## About eve eve is a filesystem-first framework

5.4k28d agoDiscuss

weave-osAGENTS.md

router

weave-os/router/AGENTS.md

write. - **Non-tautological tests** — every test must assert behavior that breaks if prod code deleted. ## Layer model and import rules Three concentric layers. Imports flow inward only. ``` +-------------------------------------------------------------------+ | cmd/router/main.go (composition root

5.4k16d agoDiscuss

metalbear-coAGENTS.md

mirrord

metalbear-co/mirrord/AGENTS.md

tricky or non-obvious behavior clearly. Write comments for readers of the resulting code, not reviewers of the patch. Comments must stand alone after merge and describe the current behavior

5.3k3mo agoDiscuss

magnitudedevAGENTS.md

magnitude / design

magnitudedev/magnitude/design/AGENTS.md

document merely to rationalize accidental implementation behavior. ## Maintenance and enforcement Changes to governed code should be reviewed for both implementation correctness and design conformance. Reviewers and agents must check that

5.3k56d agoDiscuss

magnitudedevAGENTS.md

magnitude / inference-v3

magnitudedev/magnitude/inference-v3/AGENTS.md

branch is the only pre-review signal. Bot feedback (CodeRabbit, pre-commit.ci) is triaged, not obeyed: verify each item against the code, reproduce it before adopting a suggested fix (its proposed

5.3k56d agoDiscuss

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.