# Claude Code Agent

> Use this tool when you need to efficiently manage multiple tasks with specialized capabilities without tool overload. The Claude Code Agent solves the problem of context window bloat by dynamically spawning subagents with custom server configurations, taking in task-specific inputs and outputting isolated instances with relevant tools. It is ideal for use cases where users need to scale to hundreds of trusted MCP servers, providing a streamlined interface for subagent lifecycle management.

Canonical page: https://skillsregistry.net/skills/pulsemcp-claude-code-agent  
JSON: https://api.skillsregistry.net/v1/skills/pulsemcp-claude-code-agent

## Description

An agentic MCP configuration server that solves the tool overload problem by dynamically spawning Claude Code subagents with only task-relevant MCP servers installed. Built by Tadas Antanavicius, it analyzes trusted server lists to identify relevant capabilities for specific tasks, then creates isolated Claude Code instances with custom system prompts and selective server configurations. The implementation provides 7 tools for complete subagent lifecycle management including initialization, server discovery and installation, chat delegation, transcript inspection, and cleanup, enabling users to scale to hundreds of trusted MCP servers without context window bloat by using specialized subagents equipped with only the tools needed for each specific task.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-29

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/pulsemcp-claude-code-agent)
- **Repository:** <https://github.com/pulsemcp/mcp-servers/tree/HEAD/experimental/claude-code-agent>

## 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": "pulsemcp-claude-code-agent"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/pulsemcp-claude-code-agent` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/pulsemcp-claude-code-agent/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