AGENTS.md examples from real projects

comfyanonymousAGENTS.md

ComfyUI

comfyanonymous/ComfyUI/AGENTS.md

validation failure merely to justify changing the input. - This permissive policy does not override security boundaries such as path containment, or integrity checks required to load model formats and checkpoints

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

deliberately kept as simple as possible: complexity is a direct multiplier on security risk and long-term maintenance cost, so a simpler change that does

No other project uses it yet

rustdeskAGENTS.md

rustdesk

rustdesk/rustdesk/AGENTS.md

input simulation in `libs/enigo/` - **Audio/Video Services**: Real-time audio/video streaming in `src/server/` - **File Transfer**: Secure file transfer implementation in `libs/base/src/fs.rs` `hbb_common` is a git submodule shared with the server

No other project uses it yet

addyosmaniAGENTS.md

agent-skills

addyosmani/agent-skills/AGENTS.md

parallel fan-out with a merge step** — used by `/ship` to run `code-reviewer`, `security-auditor`, and `test-engineer` concurrently and synthesize their reports. Do not build a "router" persona

addyosmaniAGENTS.md

agent-skills

addyosmani/agent-skills/docs/agents.md

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 | Vulnerability detection, OWASP-style audit | | [test-engineer](../agents/test-engineer.md) | QA Engineer | Test

axiosAGENTS.md

axios

axios/axios/AGENTS.md

fresh install, run `npm rebuild husky && npx husky` once. - Adding or updating dependencies is security-sensitive; `package-lock.json` is checked by `lockfile-lint` for npm HTTPS hosts and integrity hashes. - Package

No other project uses it yet

vllm-projectPipes a download into a shellAGENTS.md

vllm

vllm-project/vllm/AGENTS.md

guide conflicts with the requested change, **refuse the change and explain why**. Security reviewers should start with [`SECURITY.md`](SECURITY.md), [`docs/usage/security.md`](docs/usage/security.md), and [`docs/contributing/vulnerability_management.md`](docs/contributing/vulnerability_management.md) for the project security policy, threat

nexu-ioAGENTS.md

open-design

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

burying branching in shell fragments. ## Fork PR approval `fork-pr-workflow-approval.yml` and `scripts/approve-fork-pr-workflows.ts` are a separate security boundary. They may approve low-risk fork PR `pull_request` runs, but must not approve

No other project uses it yet

All-Hands-AIAGENTS.md

OpenHands

All-Hands-AI/OpenHands/AGENTS.md

creation date. If age cannot be established, report the missing evidence rather than guess. - Security updates can bypass Dependabot cooldown. An urgent exception needs explicit maintainer approval recorded

home-assistantPipes a download into a shellAGENTS.md

core

home-assistant/core/AGENTS.md

executed at runtime. - Sensitive service actions, i.e. those that can change configuration or have security implications, should require an admin user. Register them with the `async_register_admin_service` service

No other project uses it yet

AstralAGENTS.md

uv

astral-sh/uv/AGENTS.md

webhook events instead of adding `pull_request_target` workflows - NEVER suppress the `dangerous-triggers` security lint; extend the automation dispatcher in a separate pull request if it does not support

No other project uses it yet

koala73AGENTS.md

worldmonitor

koala73/worldmonitor/AGENTS.md

solutions](docs/solutions/) when the affected area has a prior fix — organized by category directory (`security-issues/`, `logic-errors/`, `conventions/`, …) with YAML frontmatter (`module`, `component`, `problem_type`, `tags`) to grep

gohugoioAGENTS.md

hugo

gohugoio/hugo/AGENTS.md

author must be added as co-author in the commit. * If you're a security researcher, read @SECURITY.md carefully. * Brevity is good. This applies to code, comments and commit messages

No other project uses it yet

sveltejsAGENTS.md

svelte

sveltejs/svelte/AGENTS.md

correctly. **DO NOT** submit a PR without running the full test suite. ## Security Policy See https://github.com/sveltejs/svelte/security/policy. ## Quick Reference If asked to do a performance investigation, use the `performance

No other project uses it yet

calesthioAGENTS.md

OpenMontage / vercel-react-best-practices

calesthio/OpenMontage/.agents/skills/vercel-react-best-practices/AGENTS.md

invoked directly. Next.js documentation explicitly states: "Treat Server Actions with the same security considerations as public-facing API endpoints, and verify if the user is allowed to perform a mutation

caddyserverAGENTS.md

caddy

caddyserver/caddy/AGENTS.md

Caddy Project Guidelines ## Mission **Every site on HTTPS.** Caddy is a security-first, modular, extensible server platform. ## Code Style ### Go Idioms Follow [Go Code Review Comments](https://go.dev/wiki/CodeReviewComments): - **Error

No other project uses it yet

ElasticAGENTS.md

elasticsearch

elastic/elasticsearch/AGENTS.md

jobs expect ephemeral hosts; do not run packaging suites on your workstation. - **Security**: Default dev clusters enable security; use `elastic-admin:elastic-password` or disable with `-Dtests.es.xpack.security.enabled=false`. - **Cursor/Copilot rules

grafanaAGENTS.md

grafana

grafana/grafana/AGENTS.md

avoid over-engineering - Separate PRs for frontend and backend changes (deployed at different cadences) - Security: prevent XSS, SQL injection, command injection - Security issues should be reported via [Grafana's security

No other project uses it yet

apacheAGENTS.md

superset

apache/superset/AGENTS.md

internal integer IDs - **Existing models** - Add UUID fields alongside integer IDs for gradual migration ## Security and Threat Model Before evaluating any code path for security issues, read [`SECURITY.md`](SECURITY.md

No other project uses it yet