Sub Agents MCP — AI skill for Claude Code
Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.
How to install Sub Agents MCP
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open shinpr/sub-agents-mcp and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Sub Agents MCP does
Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.
Alternatives in AI
- AIHawk — Open-source AI browser agent: describe any task in plain language and it autonomously browses, clicks, types a 30.3k ★
- Define — Definition phase - Clarify and scope problems with multi-AI consensus 2.8k ★
- Vllm Mlx — High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon 1.5k ★
README
Sub-Agents MCP Server
[](https://www.npmjs.com/package/sub-agents-mcp) [](https://opensource.org/licenses/MIT)
Run reusable coding agents from any MCP-compatible client.
Write a reviewer, test writer, or investigator in Markdown, then ask your assistant to use it. The MCP server runs that agent with the coding CLI you choose and returns the result to the same conversation.
What You Can Do
- Delegate code review, test writing, investigation, and documentation to focused agents
- Reuse the same agent definitions across MCP clients with one shared backend and model configuration
- Continue the same agent across multiple calls for longer work
Quick Start
You need Node.js 22 or later, an MCP-compatible client, and one supported coding CLI installed and signed in. This example uses Codex.
1. Create an Agent
Create an agents folder anywhere on your machine, then add `code-reviewer.md`:
# Code Reviewer
Review code for bugs and maintainability issues.
## Task
- Find concrete problems in the requested changes
- Explain why each problem matters
- Point to the affected code
## Done When
- All requested files have been reviewed
- Findings include evidence and suggested next steps
The filename becomes the agent name: `code-reviewer.md` becomes `code-reviewer`.
2. Add the MCP Server
Add the server to your client's MCP configuration. Replace `AGENTS_DIR` with the absolute path to the folder you created.
{
"mcpServers": {
"sub-agents": {
"command": "npx",
"args": ["-y", "sub-agents-mcp"],
"env": {
"AGENTS_DIR": "/absolute/path/to/agents",
"AGENT_TYPE": "codex"
}
}
}
}
Restart or reconnect your MCP client after saving the configuration.
3. Run the Agent
Ask your assistant:
Use the code-reviewer agent to review the authenticati
Related Skills
Xu Maestro
XuMaestro is a powerful and flexible workflow orchestrator for AI agents (Gemini & Claude). it allows you to d
Agent Nexus
A service-boundary-aware document exchange center for coordinating heterogeneous LLM code agents via MCP. Impl
Vectora
Local-first AI assistant that runs as a sub-agent inside Claude Code, Paperclip, and any MCP-compatible orches
Harness
Define and control AI agents in markdown with full prompt transparency, persistent memory, and integrated tool
Thio AI Skills
Task-specific AI instructions I've created. Aka "Skills" for Claude, "Gems" for Gemini, and "Custom GPTs" for
System Ir
System Context Compiler — compile code, config, infra, runtime, and intent into an evidence-backed machine mod
Related Agents
Docs Maker
Expert documentation writer specializing in GitHub-compatible markdown and Diátaxis framework. Use when creati
Timps Ab Testing Agent
Design A/B tests with Welch's t-test power analysis and GrowthBook configuration. Use the timps_ab_testing_age
Karo
Task decomposition, progress management, and multi-perspective analysis specialist. Deployed by the leader for