AGENTS.md — agents

Overview

Claude Code skill/plugin providing AI agent capabilities

Key Files

File	Purpose
skills/agent-rules/scripts/verify-commands.sh	!/usr/bin/env bash
skills/agent-rules/scripts/generate-file-map.sh	!/usr/bin/env bash
skills/agent-rules/scripts/analyze-git-history.sh	!/usr/bin/env bash
skills/agent-rules/scripts/detect-utilities.sh	!/usr/bin/env bash
skills/agent-rules/scripts/extract-platform-files.sh	!/usr/bin/env bash

Golden Samples (follow these patterns)

Pattern	Reference
Standard implementation	skills/agent-rules/SKILL.md

Setup & environment

• Plugin: agents v2.8.0
• Skills: 1 skill(s) in skills/
• Install: composer require netresearch/agent-rules-skill

Directory structure

.claude-plugin/
  plugin.json          → Plugin manifest (name, version, skills)
skills/
  <skill-name>/
    SKILL.md           → Skill definition and instructions
    assets/            → Templates, reference docs
    scripts/           → Shell scripts for automation
    references/        → Examples, golden samples

Build & tests

• Lint scripts: shellcheck skills/*/scripts/*.sh
• Validate plugin: jq . .claude-plugin/plugin.json

Code style & conventions

• SKILL.md: Clear, actionable instructions for AI agents
• Shell scripts: Follow ShellCheck recommendations
• Templates: Use `` syntax for variables
• Keep skills focused on one domain/task
• Include checkpoints for verification
• Provide golden samples for pattern demonstration

Skill design principles

• Actionable: Tell agents WHAT to do, not just WHAT things are
• Verifiable: Include checkpoints agents can run to verify work
• Scoped: One skill = one domain (don't mix concerns)
• Referenced: Point to golden samples, not generic examples
• Minimal: Include only what agents need; avoid documentation bloat

Security & safety

• Never include secrets or credentials in skills
• Validate all user inputs in scripts
• Use placeholder values in examples: your-api-key, example.com
• Review generated content for sensitive information

PR/commit checklist

• ShellCheck passes: shellcheck skills/*/scripts/*.sh
• SKILL.md instructions are clear and actionable
• Templates use whole-line placeholders (not inline)
• Golden samples exist for key patterns
• Checkpoints are verifiable
• plugin.json version updated if releasing

Patterns to Follow

Prefer looking at real code in this repo over generic examples. See Golden Samples section above for files that demonstrate correct patterns.

When stuck

• Check existing skills for patterns
• Review Claude Code documentation
• Test skills with claude --skill <name>
• Check root AGENTS.md for project conventions

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