AGENTS.md

Precedence: the closest AGENTS.md to the files you're changing wins. Root holds global defaults only.

Commands (unverified)

Source: CI (github-actions) — CI-sourced commands are most reliable

Task	Command	~Time
Lint	bash -n skills/agent-rules/scripts/*.sh	~5s
Validate	skills/agent-rules/scripts/validate-structure.sh .	~10s

If commands fail, verify against Makefile/package.json/composer.json or ask user to update.

Workflow

1. Before coding: Read nearest AGENTS.md + check Golden Samples for the area you're touching
2. After each change: Run the smallest relevant check (lint → typecheck → single test)
3. Before committing: Run full test suite if changes affect >2 files or touch shared code

File Map

skills/          → project files
assets/          → static assets (images, fonts)
LICENSE/         → project files

Heuristics (quick decisions)

When	Do
Committing	Use Conventional Commits (feat:, fix:, docs:, etc.)
Merging PRs	Squash and merge
Adding dependency	Ask first - we minimize deps
Unsure about pattern	Check Golden Samples above

Repository Settings

• Default branch: main
• Merge strategy: squash, merge, rebase

Boundaries

Always Do

• Run pre-commit checks before committing
• Add tests for new code paths
• Use conventional commit format: type(scope): subject

Ask First

• Adding new dependencies
• Modifying CI/CD configuration
• Changing public API signatures
• Running full e2e test suites
• Repo-wide refactoring or rewrites

Never Do

• Commit secrets, credentials, or sensitive data
• Modify vendor/, node_modules/, or generated files
• Push directly to main/master branch
• Delete migration files or schema changes

Index of scoped AGENTS.md

• ./skills/agent-rules/AGENTS.md — Claude Code skill/plugin providing AI agent capabilities
• ./.github/workflows/AGENTS.md — GitHub Actions workflows and CI/CD automation

When instructions conflict

The nearest AGENTS.md wins. Explicit user prompts override files.

AGENTS.md Generator Skill

Netresearch AI skill for generating and maintaining AGENTS.md files following the agents.md specification.

What is AGENTS.md? A context file written for AI coding agents, not humans. Human readability is a side effect, not a goal. Adopted by 60,000+ open-source projects. See the official specification and best practices from 2,500+ repositories.

Standards Compliance

This skill implements two complementary standards:

1. agents.md - The file format this skill generates. A simple Markdown convention for guiding AI coding agents, supported by Claude Code, GitHub Copilot, Cursor, and 60,000+ open-source projects.

2. Agent Skills - How this skill is packaged and distributed. A portable format for procedural knowledge that works across AI agents.

Supported Platforms:

• ✅ Claude Code (Anthropic)
• ✅ Cursor
• ✅ GitHub Copilot
• ✅ Other skills-compatible AI agents

Features

• Thin Root Files - ~30 lines with precedence rules and global defaults
• Scoped Files - Automatic subsystem detection (backend/, frontend/, internal/, cmd/)
• Auto-Extraction - Commands from Makefile, package.json, composer.json, go.mod
• Multi-Language - Templates for Go, PHP, TypeScript, Python, and hybrid projects
• Idempotent Updates - Preserve existing structure while refreshing content
• Managed Headers - Mark files as agent-maintained with timestamps

Installation

Marketplace (Recommended)

Add the Netresearch marketplace once, then browse and install skills:

# Claude Code
/plugin marketplace add netresearch/claude-code-marketplace

npx (skills.sh)

Install with any Agent Skills-compatible agent:

npx skills add https://github.com/netresearch/agent-rules-skill --skill agent-rules

Download Release

Download the latest release and extract to your agent's skills directory.

Git Clone

git clone https://github.com/netresearch/agent-rules-skill.git

Composer (PHP Projects)

composer require netresearch/agent-rules-skill

Requires netresearch/composer-agent-skill-plugin.

npm (Node Projects)

npm install --save-dev \
  @netresearch/agent-skill-coordinator \
  github:netresearch/agent-rules-skill

Requires @netresearch/agent-skill-coordinator, which discovers the skill in node_modules and registers it in AGENTS.md via a postinstall hook. For pnpm, also allowlist the coordinator's postinstall:

{
  "pnpm": {
    "onlyBuiltDependencies": ["@netresearch/agent-skill-coordinator"]
  }
}

Usage

The skill triggers on keywords like:

• "AGENTS.md", "agents file"
• "agent documentation", "AI onboarding"
• "project context for AI"

Example Prompts

"Generate AGENTS.md for this project"
"Update the agents documentation"
"Create scoped AGENTS.md files for each subsystem"
"Validate AGENTS.md structure"

Supported Projects

Type	Detection	Features
Go	go.mod	Version extraction, CLI tool detection
PHP	composer.json	TYPO3/Laravel/Symfony detection
TypeScript	package.json	React/Next.js/Vue/Express detection
Python	pyproject.toml	Poetry/Ruff/Django/Flask detection
Hybrid	Multiple markers	Auto-creates scoped files per stack

Structure

agents/
├── SKILL.md              # AI instructions
├── README.md             # This file
├── LICENSE-MIT           # Code license (MIT)
├── LICENSE-CC-BY-SA-4.0  # Content license (CC-BY-SA-4.0)
├── composer.json         # PHP distribution
├── references/           # Convention documentation
├── scripts/              # Generator scripts
│   ├── generate-agents.sh
│   ├── validate-structure.sh
│   └── detect-scopes.sh
└── templates/            # Language-specific templates
    ├── go/
    ├── php/
    ├── typescript/
    └── python/

Contributing

Contributions welcome! Please submit PRs for:

• Additional language templates
• Detection signal improvements
• Script enhancements
• Documentation updates

License

This project uses split licensing:

• Code (scripts, workflows, configs): MIT
• Content (skill definitions, documentation, references): CC-BY-SA-4.0

See the individual license files for full terms.

Credits

Developed and maintained by Netresearch DTT GmbH.

---

Made with ❤️ for Open Source by Netresearch