AGENTS.md examples from real projects

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

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

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

No other project uses it yet

rust-langAGENTS.md

rust

rust-lang/rust/AGENTS.md

exemption, state once that the resulting code, comments, and documentation are LLM-generated and cannot later be contributed without arranging with a reviewer, and cite the gate(s) that prohibit

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

No other project uses it yet

immich-appAGENTS.md

immich

immich-app/immich/AGENTS.md

generated code; the human contributor must understand and be able to explain every change (see `CONTRIBUTING.md`). - Do not generate PR titles, descriptions, issue text, review comments or discussion answers. Translating

No other project uses it yet

SupabaseAGENTS.md

supabase

supabase/supabase/AGENTS.md

source of truth and the docs skills are the process that applies it. - [code-review](.agents/skills/code-review/SKILL.md) — read-only assessments and development-task readiness checks - `copywriting` — any user-facing text, anywhere

No other project uses it yet

SupabaseAGENTS.md

supabase / apps

supabase/supabase/apps/docs/AGENTS.md

style-guide/01-voice-and-tone.md` — person, tense, sentence length, brevity - `style-guide/02-elements.md` — admonitions, code blocks, procedures, tabs, images - `style-guide/03-page-structure.md` — document type, section grouping, chunking Load the file you need

No other project uses it yet

SupabaseAGENTS.md

supabase / studio

supabase/supabase/apps/studio/AGENTS.md

number inputs | `react-hook-form` | | Displaying API errors | `studio-error-handling` | | Tests (deciding, writing, reviewing) | `studio-testing`, then `studio-mock-api-tests` (component/MSW) or `studio-e2e-tests` (Playwright) | | PostHog event

No other project uses it yet

addyosmaniAGENTS.md

agent-skills

addyosmani/agent-skills/AGENTS.md

Planning / breakdown → `planning-and-task-breakdown` - Bug / failure / unexpected behavior → `debugging-and-error-recovery` - Code review → `code-review-and-quality` - Refactoring / simplification → `code-simplification` - API or interface design

addyosmaniAGENTS.md

agent-skills

addyosmani/agent-skills/docs/agents.md

system prompt by your harness (Claude Code, Cursor, Copilot, etc.). | Persona | Role | Best for | |---------|------|----------| | [code-reviewer](../agents/code-reviewer.md) | Senior Staff Engineer | Five-axis review before merge | | [security-auditor](../agents/security-auditor.md) | Security Engineer

axiosAGENTS.md

axios

axios/axios/AGENTS.md

Review security and hygiene.** Preserve the guards and architecture boundaries below. Inspect the final diff for unrelated dependency or workflow changes, generated bundles, version churn, secrets, debug code, focused tests

No other project uses it yet

MicrosoftAGENTS.md

terminal

microsoft/terminal/AGENTS.md

establish beyond reasonable doubt that a maintainer has permitted it. - Bug reports and code reviews, *IF* AI-use is disclosed *AND* a human has personally verified all findings and evidence

No other project uses it yet

MicrosoftAGENTS.md

playwright

microsoft/playwright/AGENTS.md

commit message: commit messages, PR titles and bodies, PR and issue comments, review comments, and code comments. There is no scope in which the footer is permitted — if you find

No other project uses it yet

vllm-projectPipes a download into a shellAGENTS.md

vllm

vllm-project/vllm/AGENTS.md

work. ### Accountability - Pure code-agent PRs are **not allowed**. A human submitter must understand and defend the change end-to-end. - The submitting human must review every changed line

nexu-ioAGENTS.md

open-design

nexu-io/open-design/.github/AGENTS.md

cross-workflow behavior, update the topology tests instead of relying only on workflow YAML review. ## Architecture GitHub automation uses two layers. Business layer: - Business workflows decide what happened and what

No other project uses it yet

zed-industriesAGENTS.md

zed

zed-industries/zed/docs/AGENTS.md

Summary ### Changes Made | File | Change | Related Code | | -------------- | ----------------- | ----------------- | | path/to/doc.md | Brief description | link to PR/commit | ### Rationale Brief explanation of why these updates were made. ### Review Notes Any items reviewers should pay special

infiniflowAGENTS.md

ragflow

infiniflow/ragflow/AGENTS.md

build.sh --test`; that is expected, not an external service. ## Working Rules - When reviewing documentation or code, inspect the full affected path and report all verifiable findings in one review

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