netresearch/agent-rules-skill / skills/agent-rules
agent-rules
FlaggedUse when creating or updating AGENTS.md files, .github/copilot-instructions.md, or other AI agent rule files, onboarding AI agents to a project, standardizing agent documentation, or when anyone mentions AGENTS.md, agent rules, project onboarding, or codebase documentation for AI agents.
references/git-hooks-setup.md
View on GitHub<!-- SPDX-License-Identifier: CC-BY-SA-4.0 -->
<!-- SPDX-FileCopyrightText: Netresearch DTT GmbH -->
# Git Hooks Setup for Autonomous Agents
## Why Hooks Matter
Git hooks catch formatting errors, lint violations, and test failures **before commit** -- not minutes later in CI. For autonomous agents, this is critical: a failed CI run wastes time, tokens, and creates noisy fix-up commits. Hooks provide immediate feedback in the local loop.
## Detecting the Hook Framework
Check for these files in the repository root:
| File | Framework | Language ecosystem |
|------|-----------|-------------------|
| `lefthook.yml` or `.lefthook.yml` | [Lefthook](https://github.com/evilmartians/lefthook) | Any (Go binary) |
| `captainhook.json` | [CaptainHook](https://github.com/captainhookphp/captainhook) | PHP / Composer |
| `.husky/` directory | [Husky](https://github.com/typicode/husky) | Node.js / npm |
| `.pre-commit-config.yaml` | [pre-commit](https://pre-commit.com/) | Python / Any |
## Setup Commands
### Lefthook
```bash
# If a Makefile target exists (preferred)
make setup
# Otherwise install directly
go install github.com/evilmartians/lefthook@latest
lefthook install
```
### CaptainHook (PHP)
```bash
# Hooks install automatically via Composer plugin
composer install
```
CaptainHook registers itself as a Composer plugin. Running `composer install` triggers the post-install hook that sets up git hooks. No extra step needed.
### Husky (Node.js)
```bash
# Hooks install automatically via npm prepare script
npm install
```
Husky uses the `prepare` lifecycle script in `package.json`. Running `npm install` (or `yarn install`) automatically runs `husky install`.
### pre-commit (Python)
```bash
pip install pre-commit
pre-commit install
```
Or if the project uses a virtual environment:
```bash
# Inside activated venv
pre-commit install
```
## When No Hooks Exist
If no hook framework is detected:
1. **Do not skip this step.** The absence of hooks is a gap worth flagging.
2. Suggest adding hooks to the project -- recommend Lefthook for polyglot repos, or the ecosystem-native tool (Husky for JS, CaptainHook for PHP, pre-commit for Python).
3. See the `git-workflow` skill for hook framework setup guidance.
## Never Skip Hooks
**NEVER** use `--no-verify` to bypass hooks. If a hook fails:
1. Read the hook output to understand the failure.
2. Fix the underlying issue (formatting, lint error, failing test).
3. Stage the fix and commit again.
Skipping hooks defeats their purpose and pushes problems to CI where they are more expensive to fix.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 467k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 196k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |