agent-rules-skill MCP — Cas d'usage, Installer & Démo en direct

Pourquoi l'utiliser

Fonctionnalités clés

Follows the agents.md convention
Detects build / test / lint commands automatically
Captures coding conventions from existing code
One file works across Claude Code, Cursor, Codex, etc.
Keeps the file short — agents.md is for orientation, not novels

Démo en direct

Aperçu en pratique

agent-rules-skill.replay ▶ prêt

0/0

Installer

Choisissez votre 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
    }
  }
}

Ouvrez Claude Desktop → Settings → Developer → Edit Config. Redémarrez après avoir enregistré.

~/.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 utilise le même schéma mcpServers que Claude Desktop. La config projet l'emporte sur la 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
    }
  }
}

Cliquez sur l'icône MCP Servers dans la barre latérale Cline, puis "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
    }
  }
}

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

~/.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 utilise un tableau d'objets serveur plutôt qu'une 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"
        ]
      }
    }
  }
}

Ajoutez dans context_servers. Zed recharge à chaud à la sauvegarde.

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

Une seule ligne. Vérifiez avec claude mcp list. Supprimez avec claude mcp remove.

Cas d'usage

Usages concrets : 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

Quand l'utiliser : Your team just started using Claude Code / Cursor and nobody's written the orientation doc.

Prérequis

Skill installed — git clone https://github.com/netresearch/agent-rules-skill ~/.claude/skills/agent-rules-skill

Déroulement

Run it on your repo

Use agent-rules-skill. Analyze this repo and draft an AGENTS.md following the convention.✓ Copié

→ Draft with build/test commands, lint config, style notes, gotchas
Refine

Add a section on where not to edit (generated files, vendor/).✓ Copié

→ Section added with explicit paths
Commit

Commit as docs/AGENTS.md.✓ Copié

→ File committed at repo root or in docs/

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

Pièges

AGENTS.md balloons into an everything-doc — Keep it focused on what an agent needs. Link to README for humans.

Combiner avec : filesystem · git

Generate per-package AGENTS.md files in a monorepo

👤 Monorepo maintainers ⏱ ~30 min intermediate

Quand l'utiliser : Different packages have different conventions; a single root AGENTS.md isn't enough.

Déroulement

Scan packages

Use agent-rules-skill. For each package in packages/, generate a tailored AGENTS.md capturing its specifics.✓ Copié

→ One AGENTS.md per package
Root summary

Generate a root AGENTS.md that links to per-package files and lists shared rules.✓ Copié

→ Root file with pointers

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

Combiner avec : filesystem

Keep AGENTS.md in sync with an evolving repo

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

Quand l'utiliser : You added new build commands or changed conventions and AGENTS.md lies about them.

Déroulement

Diff

Use agent-rules-skill. Compare current AGENTS.md to what the repo actually has now. What's stale?✓ Copié

→ List of drift items
Update

Update only the stale parts; leave human-written sections alone.✓ Copié

→ Minimal diff preserving human commentary

Résultat : AGENTS.md stays trustworthy.

Combiner avec : git

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

agent-rules-skill + filesystem

Apply generated files directly

Write the draft to AGENTS.md at repo root.✓ Copié

agent-rules-skill + git

Commit as a focused change

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

Outils

Ce que ce MCP expose

Outil	Entrées	Quand appeler
scan_repo	repo path	First step on any repo
draft_agents_md	scan output	Drafting new file
diff_check	existing AGENTS.md + current repo	Staleness check

Coût et limites

Coût d'exécution

Quota d'API: None
Tokens par appel: Modest — repo scan + short output
Monétaire: Free
Astuce: Run on focused directories in huge monorepos; whole-repo scans are token-heavy.

Sécurité

Permissions, secrets, portée

Stockage des identifiants : None

Sortie de données : Repo contents go through Claude API during scan

Dépannage

Erreurs courantes et correctifs

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

Alternatives

agent-rules-skill vs autres

Alternative	Quand l'utiliser	Compromis
Manually writing AGENTS.md	Small repo with clear conventions	Works but drifts; need discipline to keep fresh
Cursor-specific .cursorrules	You only use Cursor	Non-portable; AGENTS.md works across agents

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills