AGENTS.md examples from real projects

morlutoAGENTS.md

rea

morluto/rea/AGENTS.md

REA is a local-only reverse-engineering tool with shared CLI/MCP workflows. Distinguish observations, derivations, inferences, and unknowns; preserve Evidence provenance and session semantics through both adapters. Provider support and setup live in README.md and its linked guides. Follow the contribution scope and fail-closed integration rule. Do not integrate capabilities while material scope, authority, side-effect, or required verification questions remain unresolved. For new providers or capabilities involving target execution, injection, mutation, or protection recovery, seek the required maintainer scope decision before substantial…

No other project uses it yet

moltbotAGENTS.md

clawdbot

moltbot/clawdbot/AGENTS.md

Keep this file under 20,000 characters, the size OpenClaw loads whole. Put long rules in the owning guide and leave a one-line pointer here. Design trades correctness against complexity and performance. Choose deliberately; never maximize one axis at others' expense. Task defines scope and authorization; chosen workflow owns execution, review, publication, recovery, and cleanup. Explicit user instructions override skill guidelines and workflow defaults; host limits and required authorization boundaries still apply. Read nearest scoped AGENTS.md and matching guides below in…

molt-botAGENTS.md

clawdbot

molt-bot/clawdbot/AGENTS.md

The task defines scope and authorization; its chosen workflow owns execution, review, publication, recovery, and cleanup. Explicit user instructions take precedence over skill guidelines and workflow defaults; host limits and required authorization boundaries still apply. Read the nearest scoped AGENTS.md and the matching references below, including when changing callers outside an owner's directory. Update instructions at their owner instead of adding competing rules here.

No other project uses it yet

vintaAGENTS.md

awesome-python

vinta/awesome-python/AGENTS.md

An opinionated guide to the best Python frameworks, libraries, and tools. README.md is the source of truth for entries, and website/data/category_intros/ holds the category page intros; website/ renders both into…

No other project uses it yet

obraAGENTS.md

superpowers

obra/superpowers/AGENTS.md

Stop. Read this section before doing anything. This repo has a 94% PR rejection rate. Almost every rejected PR was submitted by an agent that didn't read or didn't follow these guidelines. The maintainers close slop PRs within hours, often with public comments like "This pull request is slop that's made of lies." Your job is to protect your human partner from that outcome. Submitting a low-quality PR doesn't help them — it wastes the maintainers' time, burns your human…

No other project uses it yet

DeepSeekAGENTS.md

deepseek-harness / benchmarks

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

This tree owns required, repository-level performance gates whose measured user path crosses package ownership. Package-local diagnostics remain beside their owners and use the .perf.ts suffix instead of joining test:bench.

NousResearchAGENTS.md

hermes-agent / agent

NousResearch/hermes-agent/agent/AGENTS.md

Applies on top of the root AGENTS.md (prompt-caching invariant, facade + siblings rules). run_agent.py is the public facade: AIAgent is assembled from mixins (agent/turn_facade.py, client_lifecycle.py, stream_delivery.py, session_persistence.py, compression_facade.py, ...). Construction runs agent/agent_init.py::init_agent; a turn is agent/conversation_loop.py::run_conversation, which AIAgent.run_conversation forwards to after taking the session turn lease (turn_facade_lease.py). AIAgent.__init__ takes ~60 parameters (credentials, routing, callbacks, session context, budget, credential pool, ...) — read run_agent.py for the list; the subset you usually touch: base_url, api_key, provider, api_mode ("chat_completions" | "codex_responses" | ...),…

No other project uses it yet

affaan-mAGENTS.md

ECC

affaan-m/ECC/AGENTS.md

This is a production-ready AI coding plugin providing 68 specialized agents, 286 skills, 94 commands, and automated hook workflows for software development. Version: 2.2.1 Use agents proactively without user prompt: - Complex feature requests → planner - Code just written/modified → code-reviewer - Bug fix or new feature → tdd-guide - Architectural decision → architect - Security-sensitive code → security-reviewer - Brownfield project onboarding → spec-miner - Autonomous loops / loop monitoring → loop-operator - Harness config reliability and cost…

No other project uses it yet

TheAlgorithmsAGENTS.md

Python

TheAlgorithms/Python/AGENTS.md

Guidance for AI coding agents (and their humans) contributing to TheAlgorithms/Python. This complements — and never overrides — CONTRIBUTING.md. Read that first. This repository is educational: implementations should be clear and correct rather than maximally optimized. Every change goes through CI and the algorithms-keeper bot, both of which reject non-conforming PRs automatically. - Check at least one box in the PR description. The algorithms-keeper bot closes any PR whose "Describe your change" section has no checked box (* [x]). Fill…

No other project uses it yet

sstAGENTS.md

opencode

sst/opencode/AGENTS.md

Use a short branch name of at most three words, separated by hyphens. Do not use slashes or type prefixes such as feat/ or fix/. Examples: session-recovery, fix-scroll-state, regenerate-sdk. Use conventional commit-style messages and PR titles: type(scope): summary. Valid types are feat, fix, docs, chore, refactor, and test. Scopes are optional; use the affected package or area when helpful, e.g. core, opencode,

n8n-ioAGENTS.md

n8n / skills

n8n-io/n8n/.agents/skills/AGENTS.md

Shared n8n skills live in .agents/skills. These are the canonical source for skills that should work across Claude Code, OpenCode, and future agent harnesses. Claude plugin skills should usually be…

MicrosoftAGENTS.md

vscode

microsoft/vscode/AGENTS.md

This file provides instructions for AI coding agents working with the VS Code codebase. For detailed project overview, architecture, coding guidelines, and validation steps, see the Copilot Instructions.

instructkrAGENTS.md

claw-code / rust

instructkr/claw-code/rust/AGENTS.md

Virtual Cargo workspace (resolver 2, edition 2021) housing 11 crates that compose the claw CLI and supporting services. Dependency direction: rusty-claude-cli → tools/commands/runtime/api/plugins. tools → commands. Workspace lints (all crates opt in via [lints] workspace = true): - unsafe_code = forbid. No exceptions. - clippy all = warn, pedantic = allow. Explicitly allowed: module_name_repetitions, missing_panics_doc, missing_errors_doc. No rustfmt.toml or clippy.toml. Stock defaults only. TUI rule: formatting fns take &mut impl Write, never stdout directly. Never mix raw ANSI escapes with…