---
title: "clawd-hq"
url: "https://claudemods.dev/zh-tw/builds/clawd-hq-0299b6"
source: "https://github.com/vedant-shah/clawd-hq/tree/main/plugins/clawd-hq"
source_type: "github"
repo: "https://github.com/vedant-shah/clawd-hq/tree/main/plugins/clawd-hq"
author: "vedant-shah"
author_handle: "vedant-shah"
stars: 6
category: "多代理與協作"
categories: ["agents"]
tags: ["background-agents", "chief-of-staff", "delegation", "hooks", "orchestration", "pixel-art", "subagents", "workflow"]
permission_level: 3
scan_complete: false
install: "claude plugin marketplace add vedant-shah/clawd-hq\nclaude plugin install clawd-hq@clawd-hq"
added: "2026-11-09T06:09:24.522Z"
updated: "2026-11-11T03:38:56.293Z"
locale: "zh-tw"
content_locale: "zh-tw"
---

# clawd-hq

把你的 Claude Code 聊天變成一位幕僚長：你可以一直說話，而他會把工作交給你已安裝的幫手中的專家，並在後台執行這些工作，還有一個即時像素風辦公室面板。

## Description

當 Claude 在你主要對話中處理長時間工作時，新請求會堆在它後面，而要更改指示就代表得停止工作並再說一次。

Clawd HQ 把你主要聊天變成 Clawd，一位幕僚長。你只要向他簡報一次。Clawd 會從你已安裝的幫手中為每項工作挑選合適的專家（ECC、另一個套件，或你自己的 agent），在後台執行獨立工作，並帶回一份淺顯報告。你全程可以繼續說話，而且可以在不重新啟動的情況下中途更改正在執行專家的任務。

- 使用你自己的套件：一個專案會得到一支由它真正需要的 5 到 10 個幫手組成的小團隊。
- 合適規模的模型：每項工作可選用 Haiku、Sonnet 或 Opus。
- 配對：兩位專家互相檢查彼此的工作，並帶回一個結論。
- 安靜的聊天：工具列與交回內容會被折疊起來，讓對話保持易讀。
- 即時辦公室面板會顯示誰正在處理什麼，並為每位專家顯示進度條。

權限，用白話說：此外掛使用 hooks 來監看工具呼叫並繪製面板，讀取你電腦上的過往工作階段，以找出你使用了哪些幫手，並向 Claude 模型詢問幾個小問題（每個都列在 README 的 Privacy 區段）。除了這些模型呼叫之外，它不會開啟任何網路連線，也不會啟動任何處理程序。只有當你按下「Add to CLAUDE.md」時，它才會寫入你專案的 CLAUDE.md。

免費、MIT 授權、非官方。需要 Claude Code v2.1.287 或更新版本。輸入 /office-demo 可觀看 90 秒導覽。

## Install

```
claude plugin marketplace add vedant-shah/clawd-hq
claude plugin install clawd-hq@clawd-hq
```

## Original README

When Claude is doing a long job in your main conversation, new requests pile up behind it, and changing an instruction means stopping the job and saying it again.

Clawd HQ turns your main chat into Clawd, a chief of staff. You brief him once. He picks the right specialist for each job from the helpers you already have installed (ECC, another kit, or your own agents), runs independent work in the background, and brings back one plain report. You keep talking the whole time, and you can change a running specialist's task midway without a restart.

- Uses your own kit: a project gets a small team of the 5 to 10 helpers it actually needs.
- Right-sized models: Haiku, Sonnet or Opus per job.
- Pair-ups: two specialists check each other's work and come back with one conclusion.
- Quiet chat: tool rows and hand-backs are folded away, so the conversation stays readable.
- A live office panel shows who is working on what, with a progress bar for each specialist.

Permissions, in plain words: the plugin uses hooks to watch tool calls and draw the panel, reads past sessions on your machine to find which helpers you use, and asks Claude models a few small questions (each is listed in the README's Privacy section). Apart from those model calls, it opens no network connections and starts no processes. It writes to your project's CLAUDE.md only when you press "Add to CLAUDE.md".

Free, MIT licensed, unofficial. Needs Claude Code v2.1.287 or later. Type /office-demo for a 90-second tour.