# Subagent Driven Development

> 在当前会话中执行包含独立任务的实现计划时使用

- Skill: `vinvcn/subagent-driven-development` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add vinvcn/subagent-driven-development`
- Raw SKILL.md: https://api.skillmd.com/api/skills/vinvcn/subagent-driven-development/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: vinvcn (https://skillmd.com/u/vinvcn)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/vinvcn/subagent-driven-development

---


# 子代理驱动开发

通过为每个任务分派全新的子代理来执行计划，并在每个任务后进行两阶段审查：先进行规格符合性审查，再进行代码质量审查。

**为什么使用子代理：** 你将任务委派给具有隔离上下文的专用代理。通过精确编写它们的指令和上下文，你可以确保它们保持专注并成功完成任务。它们绝不应该继承你的会话上下文或历史记录——你只构造它们所需的内容。这也会保留你自己的上下文，用于协调工作。

**核心原则：** 每个任务使用全新子代理 + 两阶段审查（先规格再质量）= 高质量、快速迭代

**连续执行：** 不要在任务之间暂停向 your human partner 确认。不中断地执行计划中的所有任务。唯一停止理由是：你无法解决的 BLOCKED 状态、真正阻止进展的歧义，或所有任务完成。"Should I continue?" 提示和进度总结会浪费他们的时间——他们让你执行计划，所以就执行。

## 何时使用

```dot
digraph when_to_use {
    "Have implementation plan?" [shape=diamond];
    "Tasks mostly independent?" [shape=diamond];
    "Stay in this session?" [shape=diamond];
    "subagent-driven-development" [shape=box];
    "executing-plans" [shape=box];
    "Manual execution or brainstorm first" [shape=box];

    "Have implementation plan?" -> "Tasks mostly independent?" [label="yes"];
    "Have implementation plan?" -> "Manual execution or brainstorm first" [label="no"];
    "Tasks mostly independent?" -> "Stay in this session?" [label="yes"];
    "Tasks mostly independent?" -> "Manual execution or brainstorm first" [label="no - tightly coupled"];
    "Stay in this session?" -> "subagent-driven-development" [label="yes"];
    "Stay in this session?" -> "executing-plans" [label="no - parallel session"];
}
```

**对比 Executing Plans（并行会话）：**
- 同一会话（无需上下文切换）
- 每个任务使用全新子代理（没有上下文污染）
- 每个任务后进行两阶段审查：先规格符合性，再代码质量
- 迭代更快（任务之间无需人工介入）

## 流程

```dot
digraph process {
    rankdir=TB;

    subgraph cluster_per_task {
        label="Per Task";
        "Dispatch implementer subagent (./implementer-prompt.md)" [shape=box];
        "Implementer subagent asks questions?" [shape=diamond];
        "Answer questions, provide context" [shape=box];
        "Implementer subagent implements, tests, commits, self-reviews" [shape=box];
        "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" [shape=box];
        "Spec reviewer subagent confirms code matches spec?" [shape=diamond];
        "Implementer subagent fixes spec gaps" [shape=box];
        "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [shape=box];
        "Code quality reviewer subagent approves?" [shape=diamond];
        "Implementer subagent fixes quality issues" [shape=box];
        "Mark task complete in TodoWrite" [shape=box];
    }

    "Read plan, extract all tasks with full text, note context, create TodoWrite" [shape=box];
    "More tasks remain?" [shape=diamond];
    "Dispatch final code reviewer subagent for entire implementation" [shape=box];
    "Use superpowers:finishing-a-development-branch" [shape=box style=filled fillcolor=lightgreen];

    "Read plan, extract all tasks with full text, note context, create TodoWrite" -> "Dispatch implementer subagent (./implementer-prompt.md)";
    "Dispatch implementer subagent (./implementer-prompt.md)" -> "Implementer subagent asks questions?";
    "Implementer subagent asks questions?" -> "Answer questions, provide context" [label="yes"];
    "Answer questions, provide context" -> "Dispatch implementer subagent (./implementer-prompt.md)";
    "Implementer subagent asks questions?" -> "Implementer subagent implements, tests, commits, self-reviews" [label="no"];
    "Implementer subagent implements, tests, commits, self-reviews" -> "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)";
    "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" -> "Spec reviewer subagent confirms code matches spec?";
    "Spec reviewer subagent confirms code matches spec?" -> "Implementer subagent fixes spec gaps" [label="no"];
    "Implementer subagent fixes spec gaps" -> "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" [label="re-review"];
    "Spec reviewer subagent confirms code matches spec?" -> "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [label="yes"];
    "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" -> "Code quality reviewer subagent approves?";
    "Code quality reviewer subagent approves?" -> "Implementer subagent fixes quality issues" [label="no"];
    "Implementer subagent fixes quality issues" -> "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [label="re-review"];
    "Code quality reviewer subagent approves?" -> "Mark task complete in TodoWrite" [label="yes"];
    "Mark task complete in TodoWrite" -> "More tasks remain?";
    "More tasks remain?" -> "Dispatch implementer subagent (./implementer-prompt.md)" [label="yes"];
    "More tasks remain?" -> "Dispatch final code reviewer subagent for entire implementation" [label="no"];
    "Dispatch final code reviewer subagent for entire implementation" -> "Use superpowers:finishing-a-development-branch";
}
```

## 模型选择

使用能处理每个角色的最低能力模型，以节省成本并提高速度。

**机械实现任务**（隔离函数、清晰规格、1-2 个文件）：使用快速、便宜的模型。当计划规格清楚时，大多数实现任务都是机械性的。

**集成和判断任务**（多文件协调、模式匹配、调试）：使用标准模型。

**架构、设计和审查任务**：使用可用的最强模型。

**任务复杂度信号：**
- 触及 1-2 个文件且规格完整 → 便宜模型
- 触及多个文件且有集成关注点 → 标准模型
- 需要设计判断或广泛理解代码库 → 最强模型

## 处理实现者状态

实现者子代理会报告四种状态之一。要恰当处理每种状态：

**DONE:** 继续进行规格符合性审查。

**DONE_WITH_CONCERNS:** 实现者完成了工作，但标记了疑虑。继续前先阅读这些顾虑。如果顾虑涉及正确性或范围，审查前先处理。如果只是观察（例如 "this file is getting large"），记录下来并继续审查。

**NEEDS_CONTEXT:** 实现者需要未提供的信息。提供缺失上下文并重新分派。

**BLOCKED:** 实现者无法完成任务。评估阻塞点：
1. 如果是上下文问题，提供更多上下文并用同一模型重新分派
2. 如果任务需要更多推理，用能力更强的模型重新分派
3. 如果任务太大，拆成更小的部分
4. 如果计划本身错误，上报给人类

**绝不要**忽略上报，也不要在没有变化的情况下强迫同一模型重试。如果实现者说卡住了，就需要改变某些东西。

## 提示模板

- `./implementer-prompt.md` - 分派实现者子代理
- `./spec-reviewer-prompt.md` - 分派规格符合性审查者子代理
- `./code-quality-reviewer-prompt.md` - 分派代码质量审查者子代理

## 示例工作流

```
You: I'm using Subagent-Driven Development to execute this plan.

[Read plan file once: docs/superpowers/plans/feature-plan.md]
[Extract all 5 tasks with full text and context]
[Create TodoWrite with all tasks]

Task 1: Hook installation script

[Get Task 1 text and context (already extracted)]
[Dispatch implementation subagent with full task text + context]

Implementer: "Before I begin - should the hook be installed at user or system level?"

You: "User level (~/.config/superpowers/hooks/)"

Implementer: "Got it. Implementing now..."
[Later] Implementer:
  - Implemented install-hook command
  - Added tests, 5/5 passing
  - Self-review: Found I missed --force flag, added it
  - Committed

[Dispatch spec compliance reviewer]
Spec reviewer: ✅ Spec compliant - all requirements met, nothing extra

[Get git SHAs, dispatch code quality reviewer]
Code reviewer: Strengths: Good test coverage, clean. Issues: None. Approved.

[Mark Task 1 complete]

Task 2: Recovery modes

[Get Task 2 text and context (already extracted)]
[Dispatch implementation subagent with full task text + context]

Implementer: [No questions, proceeds]
Implementer:
  - Added verify/repair modes
  - 8/8 tests passing
  - Self-review: All good
  - Committed

[Dispatch spec compliance reviewer]
Spec reviewer: ❌ Issues:
  - Missing: Progress reporting (spec says "report every 100 items")
  - Extra: Added --json flag (not requested)

[Implementer fixes issues]
Implementer: Removed --json flag, added progress reporting

[Spec reviewer reviews again]
Spec reviewer: ✅ Spec compliant now

[Dispatch code quality reviewer]
Code reviewer: Strengths: Solid. Issues (Important): Magic number (100)

[Implementer fixes]
Implementer: Extracted PROGRESS_INTERVAL constant

[Code reviewer reviews again]
Code reviewer: ✅ Approved

[Mark Task 2 complete]

...

[After all tasks]
[Dispatch final code-reviewer]
Final reviewer: All requirements met, ready to merge

Done!
```

## 优势

**对比手动执行：**
- 子代理会自然遵循 TDD
- 每个任务都有新鲜上下文（不会混乱）
- 并行安全（子代理不会互相干扰）
- 子代理可以提问（工作前以及工作中）

**对比 Executing Plans：**
- 同一会话（无需交接）
- 持续进展（无需等待）
- 自动审查检查点

**效率收益：**
- 没有文件读取开销（控制者提供完整文本）
- 控制者精确整理所需上下文
- 子代理预先获得完整信息
- 问题在工作开始前浮现（而不是之后）

**质量门：**
- 自我审查在交接前捕捉问题
- 两阶段审查：规格符合性，然后代码质量
- 审查循环确保修复确实有效
- 规格符合性防止过度/不足构建
- 代码质量确保实现构建良好

**成本：**
- 更多子代理调用（每个任务 1 个实现者 + 2 个审查者）
- 控制者做更多准备工作（预先提取所有任务）
- 审查循环增加迭代
- 但能早期捕捉问题（比之后调试更便宜）

## 危险信号

**绝不要：**
- 未经用户明确同意就在 main/master 分支上开始实现
- 跳过审查（规格符合性或代码质量）
- 带着未修复的问题继续
- 并行分派多个实现子代理（会冲突）
- 让子代理读取计划文件（改为提供完整文本）
- 跳过场景设定上下文（子代理需要理解任务适合的位置）
- 忽略子代理的问题（让它们继续前先回答）
- 在规格符合性上接受 "close enough"（规格审查者发现问题 = 未完成）
- 跳过审查循环（审查者发现问题 = 实现者修复 = 再次审查）
- 让实现者自我审查替代真正审查（两者都需要）
- **在规格符合性为 ✅ 之前开始代码质量审查**（顺序错误）
- 任一审查仍有未解决问题时就移动到下一个任务

**如果子代理提问：**
- 清晰且完整地回答
- 如果需要，提供额外上下文
- 不要催促它们进入实现

**如果审查者发现问题：**
- 实现者（同一子代理）修复它们
- 审查者再次审查
- 重复直到批准
- 不要跳过重新审查

**如果子代理任务失败：**
- 用具体指令分派修复子代理
- 不要尝试手动修复（上下文污染）

## 集成

**必需的工作流技能：**
- **superpowers:using-git-worktrees** - 确保隔离 workspace（创建一个或验证现有 workspace）
- **superpowers:writing-plans** - 创建此技能执行的计划
- **superpowers:requesting-code-review** - 审查者子代理的代码审查模板
- **superpowers:finishing-a-development-branch** - 所有任务后完成开发

**子代理应使用：**
- **superpowers:test-driven-development** - 子代理为每个任务遵循 TDD

**替代工作流：**
- **superpowers:executing-plans** - 用于并行会话，而不是同会话执行