AGENTS.md examples from real projects

morlutoAGENTS.md

rea

morluto/rea/AGENTS.md

cover finalization. Before adding complexity for a speculative or vanishingly unlikely race or security edge case, explain the concrete failure mode, likelihood, and complexity cost to the user

No other project uses it yet

moltbotAGENTS.md

clawdbot

moltbot/clawdbot/AGENTS.md

incidents. No engineering for millisecond races, theoretical interleavings, or adversarial timing unless user data, security, or money at risk, or a real incident shows them. - Prefer cheap mechanisms: idempotency keys

molt-botAGENTS.md

clawdbot

molt-bot/clawdbot/AGENTS.md

live authority. - Core owns shared message tools, action vocabulary, and dispatch; channels own account, security, conversation, and transport contracts. Keep typed command/approval/URL/action distinctions until encoding; never infer commands from

No other project uses it yet

DeepSeekAGENTS.md

deepseek-harness / experimental

deepseek-ai/deepseek-harness/packages/experimental/AGENTS.md

packages through `devDependencies`; examples may load them explicitly. - Experimental status does not relax engineering, security, documentation, lifecycle, testing, or snapshot requirements. - Publishing an experimental package does not promote

No other project uses it yet

affaan-mAGENTS.md

ECC

affaan-m/ECC/AGENTS.md

domain tasks 2. **Test-Driven** — Write tests before implementation, 80%+ coverage required 3. **Security-First** — Never compromise on security; validate all inputs 4. **Immutability** — Always create new objects, never mutate

No other project uses it yet

sstAGENTS.md

opencode

sst/opencode/AGENTS.md

improves the caller. - Before adding complexity for a speculative or vanishingly unlikely race or security edge case, explain the concrete failure mode, likelihood, and complexity cost to the user

MicrosoftAGENTS.md

vscode / references

microsoft/vscode/extensions/copilot/assets/prompts/skills/agent-customization/references/agents.md

/hooks.md)). ### Supported Events `SessionStart`, `UserPromptSubmit`, `PreToolUse`, `PostToolUse`, `PreCompact`, `SubagentStart`, `SubagentStop`, `Stop` ### Example ```yaml --- description: "Secure code reviewer that blocks dangerous commands" tools: [read, search, execute] hooks: PreToolUse: - type: command command

No other project uses it yet

MicrosoftAGENTS.md

vscode / copilotcli

microsoft/vscode/extensions/copilot/src/extension/chatSessions/copilotcli/AGENTS.md

Operations * Search Operations * Agent & Task Operations * User Interaction * Code Review & Git * Data, Memory & MCP * Security ### `common/copilotCLIPrompt.ts` Parses raw user prompts and extracts structured chat prompt references (files, locations, diagnostics) ### `node/copilotcliPromptResolver.ts

No other project uses it yet

MicrosoftAGENTS.md

vscode / prompts

microsoft/vscode/src/vs/platform/agentHost/node/copilot/prompts/AGENTS.md

FAMILY`, which is process-scoped and would leak across every session in the window. > **Security note.** The setting is application-scoped (not workspace-configurable) and forwarded to the agent host

No other project uses it yet

DietrichGebertAGENTS.md

ponytail

DietrichGebert/ponytail/AGENTS.md

unfinished: new non-trivial logic (a branch, a loop, a parser, money or security, or a whole new script or app) leaves one small test or an assert-based self

No other project uses it yet

clash-verge-revAGENTS.md

clash-verge-rev

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

required issue is missing, ask maintainers to open or approve one before implementing. For security-sensitive fixes that cannot be tracked publicly, follow maintainer-approved private tracking. 2. **Scope discipline

No other project uses it yet

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