AGENTS.md examples from real projects

androidxAGENTS.md

androidx / camera

androidx/androidx/camera/AGENTS.md

Instructions for AI agents to perform strict CameraX code reviews.

moltbotAGENTS.md

moltbot

moltbot/moltbot/AGENTS.md

before merge or completion ([gate](.agents/skills/openclaw-pr-maintainer/references/media.md#screenshot-completion-gate)). - Before nontrivial code commit/landing: follow [fresh review](.agents/skills/openclaw-pr-maintainer/SKILL.md#review-and-publish). - **Make ClawSweeper happy.** It reviews each PR automatically once, when

moltbotAGENTS.md

moltbot / scripts

moltbot/moltbot/scripts/AGENTS.md

scope rules into hooks/CI snippets. - PR preparation: `pr` / `pr-lib` own source acquisition, correction reviews, gate bindings. Changing them: read [PR preparation](../docs/reference/scripts/pr-preparation.md). - PR wrapper lifecycle

moltbotAGENTS.md

moltbot / ui

moltbot/moltbot/ui/AGENTS.md

Control UI Guide ## Solid - Before writing, reviewing, or refactoring any Solid code here, read the [Solid skill](../.agents/skills/solid/SKILL.md) in full, the installed `node_modules/solid-js/CHEATSHEET.md` it points to, and the references

steipeteAGENTS.md

warelay

steipete/warelay/AGENTS.md

before merge or completion ([gate](.agents/skills/openclaw-pr-maintainer/references/media.md#screenshot-completion-gate)). - Before nontrivial code commit/landing: follow [fresh review](.agents/skills/openclaw-pr-maintainer/SKILL.md#review-and-publish). - ClawSweeper reviews each PR automatically once, when it opens

steipeteAGENTS.md

warelay / scripts

steipete/warelay/scripts/AGENTS.md

scope rules into hooks/CI snippets. - PR preparation: `pr` / `pr-lib` own source acquisition, correction reviews, gate bindings. Changing them: read [PR preparation](../docs/reference/scripts/pr-preparation.md). - PR wrapper lifecycle

steipeteAGENTS.md

warelay / ui

steipete/warelay/ui/AGENTS.md

repo-global architecture, proof, Git rules in root `AGENTS.md`. ## Solid - Before writing, reviewing, or refactoring any Solid code here, read the [Solid skill](../.agents/skills/solid/SKILL.md) in full, the installed `node_modules/solid-js/CHEATSHEET.md

molt-botAGENTS.md

clawdbot

molt-bot/clawdbot/AGENTS.md

merge or completion ([gate](.agents/skills/openclaw-pr-maintainer/references/media.md#screenshot-completion-gate)). - Before committing or landing nontrivial code, get fresh review through the permitted workflow and resolve actionable findings unless the user opts

molt-botReads credentialsAGENTS.md

clawdbot / scripts

molt-bot/clawdbot/scripts/AGENTS.md

Actions run URL land in `.local/gates.env` (`REMOTE_GATES_*`) and `.local/prep.md`. Use it for reviewed trusted code when a loaded host makes the local 88-shard run stall-kill; contributor/fork code

molt-botAGENTS.md

clawdbot / ui

molt-bot/clawdbot/ui/AGENTS.md

separate `control-ui-boot-*` groups in `ui/config/control-ui-chunking.ts`, reducing requests without pulling chat-only code into New Session. Its `entries` record contains the dynamic entry points actually requested by each route

morlutoAGENTS.md

rea

morluto/rea/AGENTS.md

silently expand scope for theoretical robustness. Assess brittleness in touched code during implementation, debugging, review, and maintenance. Fix the producing representation or ownership rule before adding downstream repairs. Normalize once

No other project uses it yet

morlutoAGENTS.md

rea / website

morluto/rea/website/AGENTS.md

translations extract` after changing source text, and review translated setup prompts, terminology and case-study reasoning for readability. Keep code, commands, URLs, paths and Evidence unchanged. Use inline `code

No other project uses it yet

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

No other project uses it yet

DeepSeekReads credentialsAGENTS.md

deepseek-harness

deepseek-ai/deepseek-harness/AGENTS.md

component or state, conversation or Session behavior, or lifecycle, concurrency, subprocess, and teardown code. Its [review principles](docs/defensive-patterns/README.md#why-these-rules) apply per artifact. ## Type safety and documentation Everything compiles

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

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

No other project uses it yet

DeepSeekReads credentialsAGENTS.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

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

No other project uses it yet

NousResearchReads credentialsAGENTS.md

hermes-agent

NousResearch/hermes-agent/AGENTS.md

Hermes Agent - Development Guide For AI coding assistants and developers working on hermes-agent. This root file is a hub: what applies everywhere, then a routing table. Each area

No other project uses it yet

NousResearchReads credentialsAGENTS.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

No other project uses it yet