subagent-driven-development

（中文）由 Subagent 驱动的开发

通过为每项任务分派一个全新的 subagent 来执行计划，并在每项任务后进行两阶段审查：先审查规范合规性，再审查代码质量。

核心原则： 每项任务使用全新的 subagent ＋ 两阶段审查（先审查规范，再审查质量）＝高质量、快速迭代

适用场景

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"];
}

与执行计划（并行会话）相比：

• 同一会话（无需切换上下文）
• 每项任务使用全新的 subagent（避免上下文污染）
• 每项任务后进行两阶段审查：先审查规范合规性，再审查代码质量
• 迭代更快（任务之间无需人工介入）

流程

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";
}

提示词模板

• ./implementer-prompt.md - 分派实现 subagent
• ./spec-reviewer-prompt.md - 分派规范合规性审查 subagent
• ./code-quality-reviewer-prompt.md - 分派代码质量审查 subagent

工作流示例

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

[Read plan file once: docs/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

与手动执行相比：

• Subagent 会自然地遵循 TDD
• 每项任务使用全新的上下文（避免混淆）
• 可安全并行（subagent 之间不会互相干扰）
• Subagent 可以提问（开始工作前和工作过程中都可以）

与执行计划相比：

• 同一会话（无需交接）
• 持续推进（无需等待）
• 自动设置审查检查点

效率提升：

• 无需承担读取文件的开销（控制器会提供完整文本）
• 控制器会精确筛选所需上下文
• Subagent 一开始就能获得完整信息
• 在开始工作前提出问题（而不是工作结束后）

质量关卡：

• 自我审查可在交接前发现问题
• 两阶段审查：先审查规范合规性，再审查代码质量
• 审查循环确保修复确实有效
• 规范合规性审查可避免实现过多或不足
• 代码质量审查确保实现质量过关

成本：

• 需要调用更多 subagent（每项任务包括一个实现 subagent 和两个审查 subagent）
• 控制器需要做更多准备工作（提前提取所有任务）
• 审查循环会增加迭代次数
• 但能及早发现问题（比之后调试更省成本）

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（规范合规性或代码质量）
• 在问题尚未修复时继续推进
• 并行分派多个实现 subagent（会产生冲突）
• 让 subagent 阅读计划文件（应直接提供完整文本）
• 跳过场景背景说明（subagent 需要了解任务在整体中的位置）
• 忽略 subagent 的问题（让其继续前先作答）
• 在规范合规性审查中接受“差不多”（规范审查者发现问题＝尚未完成）
• 跳过审查循环（审查者发现问题＝实现者修复＝再次审查）
• 让实现者的自我审查取代实际审查（两者都不可少）
• 在规范合规性审查通过 ✅ 之前开始代码质量审查（顺序错误）
• 在任一审查仍有未解决问题时转到下一项任务

如果 subagent 提出问题：

• 清晰、完整地作答
• 按需补充上下文
• 不要催促其开始实现

如果审查者发现问题：

• 由实现者（同一个 subagent）修复
• 审查者再次审查
• 重复以上步骤，直到通过
• 不要跳过再次审查

如果 subagent 未能完成任务：

• 按照具体说明分派修复 subagent
• 不要尝试手动修复（避免上下文污染）

集成

必需的工作流技能：

• superpowers:using-git-worktrees - 必需：开始前设置隔离工作区
• superpowers:writing-plans - 创建本技能要执行的计划
• superpowers:requesting-code-review - 为审查 subagent 提供代码审查模板
• superpowers:finishing-a-development-branch - 完成所有任务后结束开发

Subagent 应使用：

• superpowers:test-driven-development - Subagent 为每项任务遵循 TDD

替代工作流：

• superpowers:executing-plans - 使用并行会话，而非同一会话执行