AGENTS.md examples from real projects

molt-botAGENTS.md

clawdbot / ui

molt-bot/clawdbot/ui/AGENTS.md

separate `control-ui-boot-*` groups in `ui/config/control-ui-chunking.ts`, reducing requests without pulling chat-only code into New Session. Its `entries` record contains the dynamic entry points actually requested by each route

obraAGENTS.md

superpowers

obra/superpowers/AGENTS.md

theoretical fixes Every PR must solve a real problem that someone actually experienced. "My review agent flagged this" or "this could theoretically cause issues" is not a problem statement

No other project uses it yet

DeepSeekAGENTS.md

deepseek-harness

deepseek-ai/deepseek-harness/docs/AGENTS.md

timing, ownership, modality, exceptions, consequences, and non-obvious orientation; delete narration, test walkthroughs, review analysis, and code restatement. Keep the local contract and link its rationale. Use [dsh-prose-standard

No other project uses it yet

DeepSeekAGENTS.md

deepseek-harness / system

deepseek-ai/deepseek-harness/native/system/AGENTS.md

packages have one independent version and release workflow. ## Runtime rules - Landlock's argv, exit codes, diagnostics, and fail-closed confinement are defined in [docs/cli-contract.md](docs/cli-contract.md). Do not change them when

No other project uses it yet

NousResearchAGENTS.md

hermes-agent / agent

NousResearch/hermes-agent/agent/AGENTS.md

name == ...` chain); `tools/todo_tool.py` is the pattern. ## Message-flow invariants (every change is reviewed against these) - **Prompt caching must not break.** Never alter past context, change toolsets, reload memories, or rebuild

No other project uses it yet

NousResearchAGENTS.md

hermes-agent / tests

NousResearch/hermes-agent/tests/AGENTS.md

keep it. Reviewers reject new change-detectors; authors convert them before re-review. ## Never read source code in tests A test that reads a `.py`/`.ts`/`.tsx` file's text

affaan-mAGENTS.md

ECC

affaan-m/ECC/AGENTS.md

design and scalability | Architectural decisions | | tdd-guide | Test-driven development | New features, bug fixes | | code-reviewer | Code quality and maintainability | After writing/modifying code | | security-reviewer | Vulnerability detection | Before commits, sensitive

No other project uses it yet

TheAlgorithmsAGENTS.md

Python

TheAlgorithms/Python/AGENTS.md

algorithm file per PR.** Split unrelated changes into separate PRs to keep review focused. - **Don't change code and its doctests in the same PR.** If you're only updating

No other project uses it yet

MicrosoftAGENTS.md

vscode / references

microsoft/vscode/extensions/copilot/assets/prompts/skills/agent-customization/references/agents.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: "./scripts/block-dangerous-cmds.sh

No other project uses it yet

MicrosoftAGENTS.md

vscode / copilotcli

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

Copilot CLI agent: * File Operations * Shell 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

No other project uses it yet

MicrosoftAGENTS.md

vscode / agentHost

microsoft/vscode/src/vs/platform/agentHost/AGENTS.md

exports the public provider types from `agent.ts` for call-site compatibility; new provider code should import directly from `agent.ts`. ### Customization installation (Skills, MCP servers, catalog plugins) Installation is local-only

No other project uses it yet

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-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

No other project uses it yet

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

No other project uses it yet

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

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

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

reference](lib/gate/README.md) and `$gate-tests` for directive selection, build-skipping limitations, and verification guidance. ## Code review - During code review, flag any change that newly disables, skips, or omits deploy-mode

No other project uses it yet