AGENTS.md examples from real projects

docmirrorAGENTS.md

dev-sidecar

docmirror/dev-sidecar/AGENTS.md

electron:build:ci` — production/CI build (Vue build + electron-builder) - `npm run lint` — lint GUI code only - For debugging: run `npm run electron` and open DevTools (`F12` or View → Toggle Developer

AprilNEAAGENTS.md

OpenLogi

AprilNEA/OpenLogi/AGENTS.md

upstream content hashes. Track the files and lock together; review upstream changes before updating the source revision above. Claude Code uses the tracked symlinks in `.claude/skills/`. Other local skills remain

Model Context ProtocolAGENTS.md

python-sdk

modelcontextprotocol/python-sdk/AGENTS.md

narrate the code or restate names, types, or assertions. - Type hints required for all code - Public APIs must have docstrings. When a public API raises exceptions a caller would reasonably

No other project uses it yet

earthtojakePipes a download into a shellAGENTS.md

text-to-cad

earthtojake/text-to-cad/AGENTS.md

that covers the change. Use broad wrappers when touching shared surfaces or before handoff: - Code tests: `scripts/test/test.sh` (JS, API, Python, then policy). - Focused runners: `scripts/test/test-js.sh`, `scripts/test/test-api.sh`, `scripts/test/test-docs.sh`, `scripts/test/test-python.sh`, `scripts/test/test-global.sh`. `test-python.sh

gitlabhqAGENTS.md

gitlabhq

gitlabhq/gitlabhq/AGENTS.md

commits, or branches**: Read .ai/git.md - When working with **merge requests**: Read .ai/merge-requests.md - When **reviewing code or giving feedback**: Read .ai/code-review.md - When working with **CI/CD pipelines or `.gitlab-ci.yml`**: Read .ai/ci-cd.md - Before

argoprojAGENTS.md

argo-cd

argoproj/argo-cd/AGENTS.md

Agent Directives for Argo CD **ATTENTION AI AGENTS, LLMs, AND AUTONOMOUS CODING TOOLS:** This repository (argoproj/argo-cd) enforces strict contribution guidelines. If you are an automated agent, AI assistant, or autonomous

No other project uses it yet

ayangwebAGENTS.md

BongoCat

ayangweb/BongoCat/AGENTS.md

生成 bindings 和三个预置模型提交到 `vendor/` 与 `resources/`；公开发布前仍需完成 attribution、再分发清单和最终合规核对。 - 业务 crate 默认 `#![forbid(unsafe_code)]`，`unsafe` 只允许在平台 API、GPU 和 Cubism 边界；每个非平凡 block 前说明调用方安全不变量，优先小型 RAII wrapper，不传播裸 handle

different-aiAGENTS.md

openwork

different-ai/openwork/AGENTS.md

stages generated outputs. Hooks never commit, push, or change CI/Warden policy; CI remains authoritative. ## Coding * pnpm only, never npm/yarn. TypeScript: never `any`, typecasts, or `as` unless 100% necessary or instructed

slint-uiAGENTS.md

slint

slint-ui/slint/AGENTS.md

default branch is `master`. During review, add follow-up commits; squash or rebase when review is complete. - For new visual or layout syntax, prefer CSS naming unless Slint's types

uutilsAGENTS.md

coreutils

uutils/coreutils/AGENTS.md

AGENTS.md Writing this file is not a statement for or against using AI coding agents. People are using them in this repository either way, so this file exists to make

processingAGENTS.md

p5.js

processing/p5.js/AGENTS.md

place to ask questions, and people there are really helpful! > - This project follows a Code of Conduct that you can read [here](./CODE_OF_CONDUCT.md). We want to make sure this

CapSoftwareReads credentialsAGENTS.md

Cap

CapSoftware/Cap/AGENTS.md

code comments. Add a comment only after solving a bug or working through a complex issue, and only when it captures non-obvious context that a future investigator or reviewer

temporalioAGENTS.md

temporal

temporalio/temporal/AGENTS.md

experienced developer working on the temporal project. Your task is to review code, fix a bug, or implement a new feature while adhering to the project's best practices

PrefectHQAGENTS.md

prefect

PrefectHQ/prefect/AGENTS.md

resolving issue - Brief summary: "this PR {changes}" - Details in ` ` tag - Include relevant links ## Code Review Rules When reviewing changes, read and apply [REVIEW.md](REVIEW.md). # Project Practices - All PRs require test

volcenginePipes a download into a shellAGENTS.md

verl

volcengine/verl/AGENTS.md

code-assist Signed-off-by: Your Name <your.email@example.com> ``` ### Resolving agent reviews Review comments from agent bots (e.g., gemini-code-assist) can be outdated or wrong. Always verify their suggestions against

air-verseAGENTS.md

air

air-verse/air/AGENTS.md

When adding changes, do NOT break existing behavior. - Make changes small and easy to review. - Code and comments must be written in English. - Prefer root-cause fixes over band-aids

No other project uses it yet

facebookAGENTS.md

lexical

facebook/lexical/AGENTS.md

local variable properties that lint cannot reliably detect, so they must be caught in code review. For full details on the browser platform APIs involved, see [Shadow DOM and iframes

SuperClaude-OrgAGENTS.md

SuperClaude_Framework

SuperClaude-Org/SuperClaude_Framework/AGENTS.md

install` once, then `npm test` or `npm run build`; repeat for `research/` and `index/`. ## Coding Style & Naming Conventions - Python: 4-space indentation, Black line length 88, Ruff

No other project uses it yet

coleam00Reads credentialsAGENTS.md

Archon

coleam00/Archon/AGENTS.md

archon/workflow-language-constitution.md`](.archon/workflow-language-constitution.md), aspirational engineering craft and review values in [`.archon/engineering.md`](.archon/engineering.md), user documentation in the docs site, and machine-checkable rules in code, types, tests, lint, or CI. ## Read before

JanDeDobbeleerReads credentialsAGENTS.md

oh-my-posh

JanDeDobbeleer/oh-my-posh/AGENTS.md

that file and commit it with the related change. ## Pull request reviews Validate every comment against the code. Fold each fix into the commit that introduced the code with