AGENTS.md examples from real projects

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

No other project uses it yet

Significant-GravitasReads credentialsAGENTS.md

AutoGPT / autogpt_platform

Significant-Gravitas/AutoGPT/autogpt_platform/AGENTS.md

retry** — some turn out to be real races in the product code. ### Reviewing/Revising Pull Requests Use `/pr-review` to review a PR or `/pr-address` to address comments. When fetching comments manually

No other project uses it yet

Significant-GravitasAGENTS.md

AutoGPT

Significant-Gravitas/AutoGPT/docs/AGENTS.md

listed page is meant for the public; that is for the author and the reviewer to judge. ## Block Documentation Manual Sections When updating manual sections (` `) in block documentation files

No other project uses it yet

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

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

No other project uses it yet

clash-verge-revAGENTS.md

clash-verge-rev

clash-verge-rev/clash-verge-rev/AGENTS.md

Guidance - For development and bug fixes, follow the [development workflow](CONTRIBUTING.md#development-workflow). - For code review and verification of review fixes, follow [REVIEW.md](REVIEW.md). Review is read-only unless changes

GitHubAGENTS.md

spec-kit

github/spec-kit/AGENTS.md

target Windows PowerShell 5.1, the version included with Windows. When adding or changing PowerShell code, use only syntax, cmdlets, parameters, and .NET APIs available in Windows PowerShell 5.1. Account

No other project uses it yet

LangChainReads credentialsAGENTS.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

No other project uses it yet

comfyanonymousAGENTS.md

ComfyUI

comfyanonymous/ComfyUI/AGENTS.md

commit. Dependency pins, tests, and the code that needs them may be in the same commit when they are inseparable. - In reviews, prioritize real user impact: crashes, wrong dtype/device behavior

VercelReads credentialsAGENTS.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

No other project uses it yet

VercelAGENTS.md

next.js / bundle-analyzer

vercel/next.js/apps/bundle-analyzer/AGENTS.md

enables the Rust React Compiler (`reactCompiler` and `turbopackRustReactCompiler` in `next.config.mjs`). When adding or reviewing UI code: - Prefer plain derived values and functions over `useMemo`, `useCallback`, or `memo` used only

No other project uses it yet

VercelAGENTS.md

next.js / test

vercel/next.js/test/AGENTS.md

fixture setup, such as revalidation. See the [router-act skill](../.agents/skills/router-act/SKILL.md) for the patterns. ## Code review - During code review, enforce the deployment coverage rules above. Flag new `test/production/` tests

garrytanReads credentialsAGENTS.md

gstack

garrytan/gstack/AGENTS.md

excerpts and record the consumed inputs. 8. Finish review fixes, generation, release metadata, and build before final acceptance. Freeze the code, then run `bun run test` once

MicrosoftAGENTS.md

PowerToys

microsoft/PowerToys/AGENTS.md

Top-level AI contributor guidance for developing PowerToys - a collection of Windows productivity utilities

No other project uses it yet

ggml-orgAGENTS.md

llama.cpp

ggml-org/llama.cpp/AGENTS.md

explain the changes to reviewers independently. For first-time contributors, confirm they have reviewed [CONTRIBUTING.md](CONTRIBUTING.md). ### Code and Commit Standards These points are extremely important - failing to follow them

No other project uses it yet

rustdeskAGENTS.md

rustdesk

rustdesk/rustdesk/AGENTS.md

counter, timestamp, cache or eviction/expiry rule interacts with state that existing code relies on, and the next review round finds the problems it introduced. * A corner case is still worth

kubernetesAGENTS.md

kubernetes

kubernetes/kubernetes/AGENTS.md

Contributor Guidelines - Keep changes focused and reviewable - Add or update relevant tests. Do not add trivial unit tests just for the sake of code coverage. - When creating or submitting

No other project uses it yet

stablyaiAGENTS.md

orca

stablyai/orca/AGENTS.md

every workspace is a git worktree. # Footguns ## Git / GitHub If changing code around `git`, `gh`, source-control, or review behavior read [`docs/agents-md-refs/git-workflow.md`](./docs/agents-md-refs/git-workflow.md

MicrosoftReads credentialsAGENTS.md

generative-ai-for-beginners

microsoft/generative-ai-for-beginners/AGENTS.md

integration tests to run. Validation is primarily: - Manual testing of code examples - GitHub Actions for Markdown validation - Community review of educational content ## Pull Request Guidelines ### Before Submitting 1. Test code

No other project uses it yet

MicrosoftAGENTS.md

v8-jsi / nodejs

microsoft/v8-jsi/deps/nodejs/AGENTS.md

responsibly. New Node.js contributors should avoid using AI agents to interact with the project. ## Code Contributions * **No unreviewed automation**: Automated pull requests must not be created without ongoing human oversight