# sub-agents-mcp

> sub-agents-mcp — shinpr-sub-agents-mcp. Use this tool when you need to define and manage task-specific AI sub-agents for MCP-compatible tools, allowing for customized and modular AI workflows. It takes Markdown inputs and integrates with git for version control, enabling seamless collaboration and deployment. Ideal for use cases requiring flexible and scalable AI agent configurations.

Canonical page: https://skillsregistry.net/skills/shinpr-sub-agents-mcp  
JSON: https://api.skillsregistry.net/v1/skills/shinpr-sub-agents-mcp

## Description

Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-08-23

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** productivity
- **Updated:** 2026-09-20

## Source

- **Source listing:** [GitHub](https://github.com/shinpr/sub-agents-mcp)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "shinpr-sub-agents-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/shinpr-sub-agents-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/shinpr-sub-agents-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt