# personal-agent

> personal-agent — huanggeyu717-beep-personal-agent. Use this tool when you need to execute tasks locally with controlled access, leveraging a desktop AI assistant that integrates with Codex and utilizes a local Runtime for model execution. It solves problems related to secure and efficient task management, providing a git-enabled interface for project modifications with human approval. Ideal for use cases requiring localized AI processing with strict permission controls.

Canonical page: https://skillsregistry.net/skills/huanggeyu717-beep-personal-agent  
JSON: https://api.skillsregistry.net/v1/skills/huanggeyu717-beep-personal-agent

## Description

本地优先的桌面 AI 助手，同时作为 Codex 的受控执行端：以 MCP Server 接入上游，委派任务由本地 Runtime 用自配模型执行；权限默认为空，项目改动先出 diff 并经人工批准。

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-22

## Source

- **Source listing:** [GitHub](https://github.com/huanggeyu717-beep/personal-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": "huanggeyu717-beep-personal-agent"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/huanggeyu717-beep-personal-agent` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/huanggeyu717-beep-personal-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