# agent-tree

> agent-tree — lifrary-agent-tree. Use this tool when you need to navigate and manage complex Claude Code sessions as a visual file-tree in your terminal. It solves problems of disorganization and difficulty in resuming sessions by allowing users to browse and resume from any node. The agent-tree tool takes CLI inputs and provides a numbered tree output, making it ideal for use cases involving git version control and session management.

Canonical page: https://skillsregistry.net/skills/lifrary-agent-tree  
JSON: https://api.skillsregistry.net/v1/skills/lifrary-agent-tree

## Description

Navigate any Claude Code session as a numbered file-tree in your terminal — and resume from any node. CLI + MCP plugin.

## Trust

- **Trust score (0–1):** 0.89
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** file-system
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/lifrary/agent-tree)

## 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": "lifrary-agent-tree"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/lifrary-agent-tree` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/lifrary-agent-tree/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