/ Verzeichnis / Playground / agent-rules-skill
● Community netresearch ⚡ Sofort

agent-rules-skill

von netresearch · netresearch/agent-rules-skill

Generates AGENTS.md files following the agents.md convention — tells any coding agent (Claude Code, Cursor, Codex) how your repo works.

A small, focused Claude Code skill by Netresearch. It inspects a repository and drafts an AGENTS.md file following the agents.md convention — a growing standard for telling AI agents project conventions, build commands, testing approach, and contribution rules in one place.

Warum nutzen

Hauptfunktionen

Live-Demo

In der Praxis

agent-rules-skill.replay ▶ bereit
0/0

Installieren

Wählen Sie Ihren Client

~/Library/Application Support/Claude/claude_desktop_config.json  · Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "agent-rules-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/netresearch/agent-rules-skill",
        "~/.claude/skills/agent-rules-skill"
      ],
      "_inferred": true
    }
  }
}

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "agent-rules-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/netresearch/agent-rules-skill",
        "~/.claude/skills/agent-rules-skill"
      ],
      "_inferred": true
    }
  }
}

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "agent-rules-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/netresearch/agent-rules-skill",
        "~/.claude/skills/agent-rules-skill"
      ],
      "_inferred": true
    }
  }
}

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "agent-rules-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/netresearch/agent-rules-skill",
        "~/.claude/skills/agent-rules-skill"
      ],
      "_inferred": true
    }
  }
}

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "agent-rules-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/netresearch/agent-rules-skill",
        "~/.claude/skills/agent-rules-skill"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json
{
  "context_servers": {
    "agent-rules-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/netresearch/agent-rules-skill",
          "~/.claude/skills/agent-rules-skill"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add agent-rules-skill -- git clone https://github.com/netresearch/agent-rules-skill ~/.claude/skills/agent-rules-skill

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: agent-rules-skill

Generate an AGENTS.md for a repo that doesn't have one

👤 Teams introducing AI coding agents to an existing codebase ⏱ ~15 min beginner

Wann einsetzen: Your team just started using Claude Code / Cursor and nobody's written the orientation doc.

Voraussetzungen
  • Skill installed — git clone https://github.com/netresearch/agent-rules-skill ~/.claude/skills/agent-rules-skill
Ablauf
  1. Run it on your repo
    Use agent-rules-skill. Analyze this repo and draft an AGENTS.md following the convention.✓ Kopiert
    → Draft with build/test commands, lint config, style notes, gotchas
  2. Refine
    Add a section on where not to edit (generated files, vendor/).✓ Kopiert
    → Section added with explicit paths
  3. Commit
    Commit as docs/AGENTS.md.✓ Kopiert
    → File committed at repo root or in docs/

Ergebnis: A living AGENTS.md that makes future agent sessions start with context.

Fallstricke
  • AGENTS.md balloons into an everything-doc — Keep it focused on what an agent needs. Link to README for humans.
Kombinieren mit: filesystem · git

Generate per-package AGENTS.md files in a monorepo

👤 Monorepo maintainers ⏱ ~30 min intermediate

Wann einsetzen: Different packages have different conventions; a single root AGENTS.md isn't enough.

Ablauf
  1. Scan packages
    Use agent-rules-skill. For each package in packages/, generate a tailored AGENTS.md capturing its specifics.✓ Kopiert
    → One AGENTS.md per package
  2. Root summary
    Generate a root AGENTS.md that links to per-package files and lists shared rules.✓ Kopiert
    → Root file with pointers

Ergebnis: Agents pick up the right context based on which package they're working in.

Kombinieren mit: filesystem

Keep AGENTS.md in sync with an evolving repo

👤 Repos where AGENTS.md goes stale fast ⏱ ~10 min beginner

Wann einsetzen: You added new build commands or changed conventions and AGENTS.md lies about them.

Ablauf
  1. Diff
    Use agent-rules-skill. Compare current AGENTS.md to what the repo actually has now. What's stale?✓ Kopiert
    → List of drift items
  2. Update
    Update only the stale parts; leave human-written sections alone.✓ Kopiert
    → Minimal diff preserving human commentary

Ergebnis: AGENTS.md stays trustworthy.

Kombinieren mit: git

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

agent-rules-skill + filesystem

Apply generated files directly

Write the draft to AGENTS.md at repo root.✓ Kopiert
agent-rules-skill + git

Commit as a focused change

Commit the new AGENTS.md with a message describing what it covers.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

WerkzeugEingabenWann aufrufenKosten
scan_repo repo path First step on any repo 0
draft_agents_md scan output Drafting new file 0
diff_check existing AGENTS.md + current repo Staleness check 0

Kosten & Limits

Was der Betrieb kostet

API-Kontingent
None
Tokens pro Aufruf
Modest — repo scan + short output
Kosten in €
Free
Tipp
Run on focused directories in huge monorepos; whole-repo scans are token-heavy.

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: None
Datenabfluss: Repo contents go through Claude API during scan

Fehlerbehebung

Häufige Fehler und Lösungen

Generated commands don't match CI

Verify against actual CI config; skill infers from common files but not always correct

File is too long

Prompt for conciseness; agents.md is meant to be short

Alternativen

agent-rules-skill vs. andere

AlternativeWann stattdessenKompromiss
Manually writing AGENTS.mdSmall repo with clear conventionsWorks but drifts; need discipline to keep fresh
Cursor-specific .cursorrulesYou only use CursorNon-portable; AGENTS.md works across agents

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen