Agent skill · software engineering · bighardperson
claude-code-skill
Control Claude Code via MCP protocol. Execute commands, read/write files, search code, and use all Claude Code tools programmatically with agent team support.
Why this skill is useful
Adds executable commands for controlling Claude Code via MCP protocol, enabling advanced automation and tool integration.
What it needs
Requires node installed locally. About 6k tokens when loaded. Last updated 2026-04-26. 34 stars on the source repository.
What this skill does
Claude Code Skill Control Claude Code via MCP (Model Context Protocol). This skill unleashes the full power of Claude Code for openclaw agents, including persistent sessions, agent teams, and advanced tool control. ⚡ Quick Start 🎯 When to Use This Skill Use Persistent Sessions When: ✅ Multi-step tasks requiring multiple tool calls ✅ Iterative development (write code → test → fix → repeat) ✅ Long conversations needing full context ✅ Agent needs to work autonomously ✅ You want streaming real-time feedback Use Direct MCP Tools When: ✅ Single command execution ✅ Quick file read/write ✅ One-off searches ✅ No context needed between operations 📚 Command Reference Basic MCP Operations Persistent Sessions (Agent Loop) Starting Sessions Permission Modes: Mode Description ------ ------------- acceptEdits Auto-accept file edits (default) plan Preview changes before applying default Ask for each operation bypassPermissions Skip all prompts (dangerous!) delegate Delegate decisions to parent dontAsk Never ask, reject by default Sending Messages Managing Sessions Session History & Search Batch Operations 🤝 Agent Team Features Deploy multiple Claude agents working together on complex tasks. Basic Agent Team Pre-configured Team Templates 🔧 Advanced Features Tool Control System Prompts Session Management Multi-Model Support (Proxy) Use --base-url to route requests through a proxy, enabling other models (Gemini, GPT) to power Claude Code: Note: Requires claude-code-proxy running on port 8082 with proper API keys configured. 🎓 Best Practices For OpenClaw Agents 1. Always use persistent sessions for multi-step tasks 2. Use --stream for long-running tasks 3. Set budget limits for safety 4. Use plan mode for critical changes 5. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills bighardperson/openclaw-claude-code