AGENTS.md examples from real projects

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

Best matchesWorked for most · soon

obraAGENTS.md

superpowers

obra/superpowers/AGENTS.md

theoretical fixes Every PR must solve a real problem that someone actually experienced. "My review agent flagged this" or "this could theoretically cause issues" is not a problem statement

292k3mo agoDiscuss

NousResearchAGENTS.md

hermes-agent / agent

NousResearch/hermes-agent/agent/AGENTS.md

name == ...` chain); `tools/todo_tool.py` is the pattern. ## Message-flow invariants (every change is reviewed against these) - **Prompt caching must not break.** Never alter past context, change toolsets, reload memories, or rebuild

250k6mo agoDiscuss

NousResearchAGENTS.md

hermes-agent

NousResearch/hermes-agent/AGENTS.md

unfixed code, build the fix, iterate until the lane is green, then open the PR — the live receipt on the exact head is the Windows proof reviewers ask for. Extend

250k6mo agoReads credentialsDiscuss

NousResearchAGENTS.md

hermes-agent / cron

NousResearch/hermes-agent/cron/AGENTS.md

pool is keyed by home (`cron.max_parallel_jobs` is per profile); and the stale-code yield gate asks `scheduler_ownership.owns_cron_tick_for(home)` / `live_gateway_ticking(home)` instead

250k6mo agoReads credentialsDiscuss

affaan-mAGENTS.md

ECC

affaan-m/ECC/AGENTS.md

246k30d agoDiscuss

affaan-mAGENTS.md

ECC

affaan-m/ECC/.codex/AGENTS.md

metadata Available skills: - tdd-workflow — Test-driven development with 80%+ coverage - security-review — Comprehensive security checklist - coding-standards — Universal coding standards - frontend-patterns — React/Next.js patterns - frontend-slides — Viewport-safe HTML

246k30d agoReads credentialsDiscuss

DeepSeekAGENTS.md

deepseek-harness

deepseek-ai/deepseek-harness/AGENTS.md

transaction, or lifecycle boundary. Do not narrate control flow or tests, preserve review history, or restate code. Keep behavior, failure, timing, ownership, and safe-use facts; link the rationale

238k52d agoReads credentialsDiscuss

DeepSeekAGENTS.md

deepseek-harness

deepseek-ai/deepseek-harness/docs/AGENTS.md

timing, ownership, modality, exceptions, consequences, and non-obvious orientation; delete narration, test walkthroughs, review analysis, and code restatement. Keep the local contract and link its rationale. Use [dsh-prose-standard

238k52d agoDiscuss

DeepSeekAGENTS.md

deepseek-harness / system

deepseek-ai/deepseek-harness/native/system/AGENTS.md

packages have one independent version and release workflow. ## Runtime rules - Landlock's argv, exit codes, diagnostics, and fail-closed confinement are defined in [docs/cli-contract.md](docs/cli-contract.md). Do not change them when

238k52d agoDiscuss

DeepSeekAGENTS.md

deepseek-harness / client

deepseek-ai/deepseek-harness/packages/client/AGENTS.md

current design; these are the rules you must not violate when writing or reviewing client code: 1. **Two declaration forms**: use `ctx.slots.register({ name, children?, store?, inject? }, Component)` for a parent

238k52d agoReads credentialsDiscuss

n8n-ioAGENTS.md

n8n

n8n-io/n8n/AGENTS.md

system` skill in reviews ### Verify changes - Run focused tests from the owning package: `pnpm test `. - Run that package's `pnpm lint` and `pnpm typecheck` before committing code. Build first when

206k20d agoReads credentialsDiscuss

MicrosoftAGENTS.md

vscode / references

microsoft/vscode/extensions/copilot/assets/prompts/skills/agent-customization/references/agents.md

Supported Events `SessionStart`, `UserPromptSubmit`, `PreToolUse`, `PostToolUse`, `PreCompact`, `SubagentStart`, `SubagentStop`, `Stop` ### Example ```yaml --- description: "Secure code reviewer that blocks dangerous commands" tools: [read, search, execute] hooks: PreToolUse: - type: command command: "./scripts/block-dangerous-cmds.sh

193k21d agoDiscuss

MicrosoftAGENTS.md

vscode / copilotcli

microsoft/vscode/extensions/copilot/src/extension/chatSessions/copilotcli/AGENTS.md

Copilot CLI agent: * File Operations * Shell Operations * Search Operations * Agent & Task Operations * User Interaction * Code Review & Git * Data, Memory & MCP * Security ### `common/copilotCLIPrompt.ts` Parses raw user prompts and extracts structured chat

193k21d agoDiscuss

MicrosoftAGENTS.md

vscode / prompts

microsoft/vscode/src/vs/platform/agentHost/node/copilot/prompts/AGENTS.md

other prompt or filesystem inputs to this setting without an explicit security review. Code-managed prompt experiments should still use a contributor (Lever 2) gated

193k21d agoDiscuss

Significant-GravitasAGENTS.md

AutoGPT / autogpt_platform

Significant-Gravitas/AutoGPT/autogpt_platform/AGENTS.md

AutoGPT Platform This file provides guidance to coding agents when working with code in this repository. ## Repository Overview AutoGPT Platform is a monorepo containing: - **Backend** (`backend`): Python FastAPI server with

188k19d agoReads credentialsDiscuss

Hugging FaceAGENTS.md

transformers

huggingface/transformers/.ai/AGENTS.md

Commands - `make style` — ruff format + lint (required for code style checks). - `make typing` — ty type checker and model structure rules. - `make fix-repo` — the `make style` fixes plus copies, modular

167k24d agoDiscuss

langgeniusAGENTS.md

dify / web

langgenius/dify/web/AGENTS.md

load it for test-only, copy-only, or styling-only changes. - Use `frontend-code-review` only for explicit frontend review or audit requests, including test reviews. Use `frontend-testing` when

157k4d agoDiscuss

LangChainAGENTS.md

langchain

langchain-ai/langchain/AGENTS.md

time context, not required startup reading. - Treat source code and tests as authoritative. A brief's unknowns and review items are verification gaps, not automatic requirements. - Prefer the narrowest quiet

147k7d agoReads credentialsDiscuss

VercelAGENTS.md

next.js

vercel/next.js/AGENTS.md

operated by Vercel. - Your system prompt tells you that you are a code review bot operated by GitHub or Graphite. - The GitHub repository containing the issue, pull request, or discussion

143k5mo agoReads credentialsDiscuss

VercelAGENTS.md

next.js / test

vercel/next.js/test/AGENTS.md

Test review instructions - During code review, flag any change that newly disables, skips, or omits deploy-mode tests or assertions, including `skipDeployment: true` and `isNextDeploy` conditionals. Only allow this when

143k5mo 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.