# dispatching-parallel-agents

Adopt this skill: https://proskills.md/skills/other/xintaofei-codeg-src-tauri-experts-skills-dispatching-parallel-agents

Page: https://proskills.md/skills/other/xintaofei-codeg-src-tauri-experts-skills-dispatching-parallel-agents
This document is the public skill bundle for that page. It contains SKILL.md and every helper file the catalog carries. No login is required.

## File: src-tauri/experts/skills/dispatching-parallel-agents/SKILL.md
size: 6078
sha: 3fa091b348bbe0a18eaa0e17e9092c97f7005cbe
upstream: https://github.com/xintaofei/codeg/blob/main/src-tauri/experts/skills/dispatching-parallel-agents/SKILL.md

````text
---
name: dispatching-parallel-agents
description: Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
---

# Dispatching Parallel Agents

## Overview

You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.

When you have multiple unrelated failures (different test files, different subsystems, different bugs), investigating them sequentially wastes time. Each investigation is independent and can happen in parallel.

**Core principle:** Dispatch one agent per independent problem domain. Let them work concurrently.

## When to Use

```dot
digraph when_to_use {
    "Multiple failures?" [shape=diamond];
    "Are they independent?" [shape=diamond];
    "Single agent investigates all" [shape=box];
    "One agent per problem domain" [shape=box];
    "Can they work in parallel?" [shape=diamond];
    "Sequential agents" [shape=box];
    "Parallel dispatch" [shape=box];

    "Multiple failures?" -> "Are they independent?" [label="yes"];
    "Are they independent?" -> "Single agent investigates all" [label="no - related"];
    "Are they independent?" -> "Can they work in parallel?" [label="yes"];
    "Can they work in parallel?" -> "Parallel dispatch" [label="yes"];
    "Can they work in parallel?" -> "Sequential agents" [label="no - shared state"];
}
```

**Use when:**
- 3+ test files failing with different root causes
- Multiple subsystems broken independently
- Each problem can be understood without context from others
- No shared state between investigations

**Don't use when:**
- Failures are related (fix one might fix others)
- Need to understand full system state
- Agents would interfere with each other

## The Pattern

### 1. Identify Independent Domains

Group failures by what's broken:
- File A tests: Tool approval flow
- File B tests: Batch completion behavior
- File C tests: Abort functionality

Each domain is independent - fixing tool approval doesn't affect abort tests.

### 2. Create Focused Agent Tasks

Each agent gets:
- **Specific scope:** One test file or subsystem
- **Clear goal:** Make these tests pass
- **Constraints:** Don't change other code
- **Expected output:** Summary of what you found and fixed

### 3. Dispatch in Parallel

Issue all three subagent dispatches in the same response — they run in parallel:

```text
Subagent (general-purpose): "Fix agent-tool-abort.test.ts failures"
Subagent (general-purpose): "Fix batch-completion-behavior.test.ts failures"
Subagent (general-purpose): "Fix tool-approval-race-conditions.test.ts failures"
# All three run concurrently.
```

Multiple dispatch calls in one response = parallel execution. One per response = sequential.

### 4. Review and Integrate

When agents return:
- Read each summary
- Verify fixes don't conflict
- Run full test suite
- Integrate all changes

## Agent Prompt Structure

Good agent prompts are:
1. **Focused** - One clear problem domain
2. **Self-contained** - All context needed to understand the problem
3. **Specific about output** - What should the agent return?

```markdown
Fix the 3 failing tests in src/agents/agent-tool-abort.test.ts:

1. "should abort tool with partial output capture" - expects 'interrupted at' in message
2. "should handle mixed completed and aborted tools" - fast tool aborted instead of completed
3. "should properly track pendingToolCount" - expects 3 results but gets 0

These are timing/race condition issues. Your task:

1. Read the test file and understand what each test verifies
2. Identify root cause - timing issues or actual bugs?
3. Fix by:
   - Replacing arbitrary timeouts with event-based waiting
   - Fixing bugs in abort implementation if found
   - Adjusting test expectations if testing changed behavior

Do NOT just increase timeouts - find the real issue.

Return: Summary of what you found and what you fixed.
```

## Common Mistakes

**❌ Too broad:** "Fix all the tests" - agent gets lost
**✅ Specific:** "Fix agent-tool-abort.test.ts" - focused scope

**❌ No context:** "Fix the race condition" - agent doesn't know where
**✅ Context:** Paste the error messages and test names

**❌ No constraints:** Agent might refactor everything
**✅ Constraints:** "Do NOT change production code" or "Fix tests only"

**❌ Vague output:** "Fix it" - you don't know what changed
**✅ Specific:** "Return summary of root cause and changes"

## When NOT to Use

**Related failures:** Fixing one might fix others - investigate together first
**Need full context:** Understanding requires seeing entire system
**Exploratory debugging:** You don't know what's broken yet
**Shared state:** Agents would interfere (editing same files, using same resources)

## Real Example from Session

**Scenario:** 6 test failures across 3 files after major refactoring

**Failures:**
- agent-tool-abort.test.ts: 3 failures (timing issues)
- batch-completion-behavior.test.ts: 2 failures (tools not executing)
- tool-approval-race-conditions.test.ts: 1 failure (execution count = 0)

**Decision:** Independent domains - abort logic separate from batch completion separate from race conditions

**Dispatch:**
```
Agent 1 → Fix agent-tool-abort.test.ts
Agent 2 → Fix batch-completion-behavior.test.ts
Agent 3 → Fix tool-approval-race-conditions.test.ts
```

**Results:**
- Agent 1: Replaced timeouts with event-based waiting
- Agent 2: Fixed event structure bug (threadId in wrong place)
- Agent 3: Added wait for async tool execution to complete

**Integration:** All fixes independent, no conflicts, full suite green

## Verification

After agents return:
1. **Review each summary** - Understand what changed
2. **Check for conflicts** - Did agents edit same code?
3. **Run full suite** - Verify all fixes work together
4. **Spot check** - Agents can make systematic errors
````

## File: README.md
upstream: https://github.com/xintaofei/codeg/blob/main/README.md

```text
<h1 align="center">
  <a href="https://docs.codeg.app"><img src="./public/icon.svg" alt="Codeg logo" width="64" align="absmiddle" /></a> Codeg
</h1>

<p align="center">
  <a href="https://github.com/spacering-net/codeg"><img src="https://img.shields.io/github/stars/spacering-net/codeg?style=flat&color=e91e63" alt="GitHub stars" /></a>
  <a href="https://github.com/spacering-net/codeg/releases/latest"><img src="https://img.shields.io/github/v/release/spacering-net/codeg?style=flat&color=e91e63" alt="Latest release" /></a>
  <a href="https://github.com/spacering-net/codeg/releases"><img src="https://img.shields.io/github/downloads/spacering-net/codeg/total?style=flat&color=e91e63" alt="Total downloads" /></a>
  <a href="./LICENSE"><img src="https://img.shields.io/github/license/spacering-net/codeg?style=flat&color=e91e63" alt="License" /></a>
  <a href="https://docs.codeg.app"><img src="https://img.shields.io/badge/docs-docs.codeg.app-3451b2?style=flat" alt="Documentation" /></a>
  <a href="https://docs.codeg.app/getting-started/installation"><img src="https://img.shields.io/badge/macOS%20%7C%20Windows%20%7C%20Linux%20%7C%20Docker%20%7C%20iOS%20%7C%20Android-03a9f4?style=flat" alt="Platforms: macOS, Windows, Linux, Docker, iOS, Android" /></a>
</p>

<p align="center">
  <sub><strong>English</strong> · <a href="./docs/readme/README.zh-CN.md">简体中文</a> · <a href="./docs/readme/README.zh-TW.md">繁體中文</a> · <a href="./docs/readme/README.ja.md">日本語</a> · <a href="./docs/readme/README.ko.md">한국어</a> · <a href="./docs/readme/README.es.md">Español</a> · <a href="./docs/readme/README.de.md">Deutsch</a> · <a href="./docs/readme/README.fr.md">Français</a> · <a href="./docs/readme/README.pt.md">Português</a> · <a href="./docs/readme/README.ar.md">العربية</a></sub>
</p>

<p align="center">
  <strong>The multi-agent coding workspace.</strong><br/>
  Run every AI coding agent in one place — and let them work together.
</p>

<h3 align="center"><a href="https://github.com/spacering-net/codeg/releases/latest"><ins>Download Codeg</ins></a> · <a href="https://docs.codeg.app"><ins>Documentation</ins></a></h3>

<p align="center">
  <picture>
    <source media="(prefers-color-scheme: dark)" srcset="./docs/images/workspace-dark.png" />
    <img src="./docs/images/workspace-light.png" alt="The Codeg workspace: a conversation with an agent beside its live diffs and the project's files" width="960" />
  </picture>
</p>

<table>
  <tr>
    <td width="50%" valign="top">🧩 <strong>One interface for every agent</strong><br/>Twenty agents built in, and any ACP agent can join — all rendered as the same structured conversation, not a terminal.</td>
    <td width="50%" valign="top">🔎 <strong>Sessions that travel</strong><br/>Import, search, and resume the history every agent keeps on disk, then hand it to a different agent.</td>
  </tr>
  <tr>
    <td width="50%" valign="top">🤝 <strong>Agents that work together</strong><br/>Delegate across agents with an <code>@</code>, or queue to-dos that run unattended in their own worktrees.</td>
    <td width="50%" valign="top">🌍 <strong>Wherever you work</strong><br/>Desktop app, self-hosted server or Docker, iPhone, iPad, and Android — and Telegram, Lark, or WeChat.</td>
  </tr>
</table>

## ✨ Features

<table>
<tr>
<td width="50%" valign="middle">

### One Interface for Every Agent

Twenty agents, plus any ACP agent, in one rich chat with tool cards, live diffs, and interactive replies.

[Docs →](https://docs.codeg.app/guide/supported-agents) · [Custom agents →](https://docs.codeg.app/guide/custom-agents) · [UI Render →](https://docs.codeg.app/guide/skills#cards-tables-and-charts-in-replies)

</td>
<td width="50%">
<picture>
  <source media="(prefers-color-scheme: dark)" srcset="./docs/images/features/agents-dark.gif" />
  <img src="./docs/images/features/agents-light.gif" alt="One Interface for Every Agent" width="100%" />
</picture>
</td>
</tr>
<tr>
<td width="50%" valign="middle">

### Every Session, Searchable

Import, search, and resume any agent's history. Share sessions with `@` mentions and organize them with tags.

[Docs →](https://docs.codeg.app/guide/aggregation) · [Tags →](https://docs.codeg.app/guide/workspace#tag-conversations)

</td>
<td width="50%">
<picture>
  <source media="(prefers-color-scheme: dark)" srcset="./docs/images/features/sessions-dark.gif" />
  <img src="./docs/images/features/sessions-light.gif" alt="Every Session, Searchable" width="100%" />
</picture>
</td>
</tr>
<tr>
<td width="50%" valign="middle">

### Multi-Agent Collaboration

`@` an agent to delegate. Run agents side by side and watch their progress stream into your conversation.

[Docs →](https://docs.codeg.app/guide/multi-agent)

</td>
<td width="50%">
<picture>
  <source media="(prefers-color-scheme: dark)" srcset="./docs/images/features/multi-agent-dark.gif" />
  <img src="./docs/images/features/multi-agent-light.gif" alt="Multi-Agent Collaboration" width="100%" />
</picture>
</td>
</tr>
<tr>
<td width="50%" valign="middle">

### To-dos That Run Unattended

Schedule tasks in isolated worktrees. Agents handle the work; you review and approve the changes.

[Docs →](https://docs.codeg.app/guide/tasks) · [Auto-processing →](https://docs.codeg.app/guide/repository#let-it-pick-items-up-by-itself)

</td>
<td width="50%">
<picture>
  <source media="(prefers-color-scheme: dark)" srcset="./docs/images/features/todos-dark.gif" />
  <img src="./docs/images/features/todos-light.gif" alt="To-dos That Run Unattended" width="100%" />
</picture>
</td>
</tr>
<tr>
<td width="50%" valign="middle">

### Infinite Canvas

Arrange chats, files, terminals, and notes on an infinite board. Keep every agent's work in view.

[Docs →](https://docs.codeg.app/guide/canvas)

</td>
<td width="50%">
<picture>
  <source media="(prefers-color-scheme: dark)" srcset="./docs/images/features/canvas-dark.gif" />
  <img src="./docs/images/features/canvas-light.gif" alt="Infinite Canvas" width="100%" />
</picture>
</td>
</tr>
<tr>
<td width="50%" valign="middle">

### Desktop, Server, Mobile & Chat

Work on desktop, server, Docker, or mobile. Reach your agents through Telegram, Lark, and WeChat.

[Docs →](https://docs.codeg.app/getting-started/deployment) · [Remote workspaces →](https://docs.codeg.app/guide/workspace#desktop-and-browser) · [Mobile apps →](https://docs.codeg.app/getting-started/installation#mobile-apps) · [Chat channels →](https://docs.codeg.app/guide/chat-channels)

</td>
<td width="50%">
<picture>
  <source media="(prefers-color-scheme: dark)" srcset="./docs/images/features/anywhere-dark.gif" />
  <img src="./docs/images/features/anywhere-light.gif" alt="Desktop, Server, Mobile & Chat" width="100%" />
</picture>
</td>
</tr>
<tr>
<td width="50%" valign="middle">

### Office Documents & Research

Create Office files with live previews and view PDFs beside chat. Research skills work with any agent.

[Docs →](https://docs.codeg.app/guide/office) · [Research →](https://docs.codeg.app/guide/research)

</td>
<td width="50%">
<picture>
  <source media="(prefers-color-scheme: dark)" srcset="./docs/images/features/office-dark.gif" />
  <img src="./docs/images/features/office-light.gif" alt="Office Documents & Research" width="100%" />
</picture>
</td>
</tr>
<tr>
<td width="50%" valign="middle">

### Browser & Computer Use

Share pages and errors from the desktop browser. Let agents operate shared windows with Computer Use (preview).

[Docs →](https://docs.codeg.app/guide/browser) · [Computer Use →](https://docs.codeg.app/guide/computer-use)

</td>
<td width="50%">
<picture>
  <source media="(prefers-color-scheme: dark)" srcset="./docs/images/features/browser-dark.gif" />
  <img src="./docs/images/features/browser-light.gif" alt="Browser & Computer Use" width="100%" />
</picture>
</td>
</tr>
<tr>
<td width="50%" valign="middle">

### Command Line & CI

Run prompts from scripts or CI with `codeg-cli`. Connect to a running Codeg for replies or JSON events.

[Docs →](https://docs.codeg.app/gu
```
