agent-rules-skill MCP — Use Cases, Install & Live Demo

Why use it

Key features

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

Live Demo

What it looks like in practice

agent-rules-skill.replay ▶ ready

0/0

Install

Pick your 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
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.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 uses the same mcpServers schema as Claude Desktop. Project config wins over global.

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
    }
  }
}

Click the MCP Servers icon in the Cline sidebar, then "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
    }
  }
}

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.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 uses an array of server objects rather than a 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"
        ]
      }
    }
  }
}

Add to context_servers. Zed hot-reloads on save.

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

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use 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

When to use: Your team just started using Claude Code / Cursor and nobody's written the orientation doc.

Prerequisites

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

Flow

Run it on your repo

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

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

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

→ Section added with explicit paths
Commit

Commit as docs/AGENTS.md.✓ Copied

→ File committed at repo root or in docs/

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

Pitfalls

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

Combine with: filesystem · git

Generate per-package AGENTS.md files in a monorepo

👤 Monorepo maintainers ⏱ ~30 min intermediate

When to use: Different packages have different conventions; a single root AGENTS.md isn't enough.

Flow

Scan packages

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

→ One AGENTS.md per package
Root summary

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

→ Root file with pointers

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

Combine with: filesystem

Keep AGENTS.md in sync with an evolving repo

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

When to use: You added new build commands or changed conventions and AGENTS.md lies about them.

Flow

Diff

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

→ List of drift items
Update

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

→ Minimal diff preserving human commentary

Outcome: AGENTS.md stays trustworthy.

Combine with: git

Combinations

Pair with other MCPs for X10 leverage

agent-rules-skill + filesystem

Apply generated files directly

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

agent-rules-skill + git

Commit as a focused change

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

Tools

What this MCP exposes

Tool	Inputs	When to call
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

Cost & Limits

What this costs to run

API quota: None
Tokens per call: Modest — repo scan + short output
Monetary: Free
Tip: Run on focused directories in huge monorepos; whole-repo scans are token-heavy.

Security

Permissions, secrets, blast radius

Credential storage: None

Data egress: Repo contents go through Claude API during scan

Troubleshooting

Common errors and fixes

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 others

Alternative	When to use it instead	Tradeoff
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

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills