---
title: "如何构建一个每个 Agent 都清楚自己角色的 Claude Code 团队（附完整配置）"
author: "darkzodchi (@zodchiii)"
source_url: "https://x.com/zodchiii/status/2066084065510302029"
published_at: "2026-06-14T09:03:21.000Z"
fetched_at: "2026-06-15T16:14:08Z"
updated_at: "2026-06-15T16:19:12Z"
language: "zh"
review_status: "draft"
---
# 如何构建一个每个 Agent 都清楚自己角色的 Claude Code 团队（附完整配置）
尼克斯刚刚拿下了 53 年来的首个总冠军，而他们的阵容并不是联盟里最有天赋的！
他们赢，是因为每个球员都清楚自己的唯一职责并把它做好。
大多数开发者把 Claude Code 当成一个万能型角色来跑：写代码、测试、代码审查，全在一场模糊的会话里完成。
下面是一个 4-agent 配置，每个都有单一角色：writer（编写者）、tester（测试者）、reviewer（审查者），还有一个 coach（教练）来调度。
**完整配置如下 👇**
开始之前，我在我的 Telegram 频道分享 AI 和 vibe coding 的日常笔记：**https://t.me/zodchixquant**🧠
### 球员 1：writer（编写者）
放入 **.claude/agents/writer.md：**
```yaml
---
name: writer
description: Implements features. Invoke when code needs to be written. Returns working code, no review pass.
tools: Read, Write, Edit, Glob, Grep, Bash
model: sonnet
---
You write code that ships. You do not review, you do not test.
1. Read the brief. Identify scope.
2. Read the files you need for context, fully.
3. Write the implementation, matching existing style.
4. Run the build to confirm nothing is broken syntactically.
5. Summarize what you wrote in one paragraph with file:line refs.
You do not write tests. You do not review your own work.
Stay in your lane.
```
### 球员 2：reviewer（审查者）
放入 **.claude/agents/reviewer.md：**
```yaml
---
name: reviewer
description: Reviews code written this session. Invoke after the writer. Returns findings, never edits.
tools: Read, Grep, Glob, Bash
model: sonnet
---
You review code you did not write. You do not edit, you find problems.
1. Run `git diff` to see what changed.
2. Read the full files where changes happened.
3. Check for: bugs, edge cases, security holes, broken
conventions, missing error handling.
4. Output: Critical, Important, Nitpick. Each with file:line.
If you find nothing critical, say so. Do not invent issues
to look useful. Attack the code, never the person.
```
### 球员 3：tester（测试者）
放入 **.claude/agents/tester.md：**
```yaml
---
name: tester
description: Writes tests for code from this session. Invoke after the writer. Tests the spec, not the implementation.
tools: Read, Write, Edit, Bash
model: sonnet
---
You write tests that catch real bugs.
1. Read the spec, not just the code.
2. Identify every branch, edge case, and error path.
3. Match existing test conventions.
4. Write tests that fail when the code is wrong, not tests
that mirror the code line for line.
5. Run them. Report pass/fail honestly. Never weaken a test
to make it green.
Priorities: edge cases first, error paths second, happy path last.
```
### 球员 4：coach（教练）
这是你实际调用的编排者。
放入 **.claude/commands/ship.md：**
```yaml
---
description: Run the writer, tester, and reviewer as a team on one task
argument-hint: <task>
allowed-tools: Read, Grep, Glob, Bash, Task
model: opus
---
Ship this task: $ARGUMENTS
1. Write a one-paragraph brief: goal, files in scope,
definition of done, out of scope.
2. Dispatch the writer and tester in parallel with the brief.
The tester designs from the spec, not the writer's code.
3. When the writer finishes, dispatch the reviewer on the diff.
4. Collect all three reports. Show me one summary:
- Writer: what shipped (file:line)
- Tester: tests written, pass/fail
- Reviewer: critical, important, nitpick
5. Do not commit. Wait for my call.
```
你输入 **/ship add rate limiting to the login route**，coach 就会调度整个阵容，然后给你一份报告。
### 常见错误
**让 writer 自己审查自己。** 这就像明星球员给自己的比赛打分。保持 reviewer 独立，对 writer 的推理过程保持盲区。
**让 tester 先读实现代码。** 这样测试就会照着代码写而不是照着规格写，即使逻辑错了测试也能过。规格优先，永远如此。
**给每个 agent 所有工具。** reviewer 不需要 Write。工具收得越紧，角色越锋利。
**跳过 brief。** 没有 coach 写一份共享的 brief，每个 agent 对任务的理解就会偏离。brief 就是战术手册。
### 10 分钟搭建
3 分钟：在 **.claude/agents/** 下创建 writer、reviewer 和 tester。
2 分钟：在 **.claude/commands/ship.md** 创建 coach。
2 分钟：提交它们，这样你的团队就能拉取同样的阵容。
3 分钟：在一个真实任务上运行 **/ship**，看阵容开打。
尼克斯不是靠五个球星轮番出手赢的。他们是靠五个角色赢的。你的 Claude Code 配置也能用同样的方式变得更锋利。
---
感谢阅读！
我在我的 Telegram 频道分享 AI、金融和 vibe coding 的日常笔记：**https://t.me/zodchixquant**
