subagent-driven-development

子 Agent 驱动开发

通过为每项任务派遣全新的子 Agent 来执行计划，并在每项任务后进行两阶段审查：先审查规范符合性，再审查代码质量。

核心原则： 每项任务使用全新的子 Agent，并进行两阶段审查，有助于提升隔离性和反馈质量；请验证实际质量、延迟和成本。

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子 Agent（无上下文污染）
• 每项任务后进行两阶段审查：先审查规范符合性，再审查代码质量
• 迭代更快（任务之间无需人工介入）

宿主和授权前提

仅使用对此任务实际可用且获准使用的委派工具。下文提到的 Task、TodoWrite 和 superpowers 名称是特定于宿主的示例，并非随附能力。随附了三个本地提示词模板；其他 superpowers 技能／模板属于外部依赖。若这些工具不可用，请直接使用等效的任务跟踪器，并独立审查代码和规范，不要声称运行过子 Agent。设置全局并发、成本、时间限制和取消机制；子 Agent 无权扩大授权范围。提交必须遵循既定的仓库工作流并使用指定分支，审查者批准不代表授权推送、合并或发布。完成前，请在经过审查的确切提交版本上检查实际文件和命令证据。

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 - 派遣实现者子 Agent
• ./spec-reviewer-prompt.md - 派遣规范符合性审查者子 Agent
• ./code-quality-reviewer-prompt.md - 派遣代码质量审查者子 Agent

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：

• 明确要求运行相关测试；子 Agent 不会自动遵循 TDD
• 每项任务使用全新上下文（避免混淆）
• 独立上下文并不会隔离文件；请分配互不重叠的文件所有权，或使用隔离检出
• 子 Agent 可以提问（开始工作前和工作期间都可以）

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（控制器会提供全文）
• 控制器会精确筛选所需上下文
• 子 Agent 一开始就能获得完整信息
• 工作开始前就能提出问题（而非事后）

质量关卡：

• 自我审查可在交接前发现问题
• 两阶段审查：先审查规范符合性，再审查代码质量
• 审查循环确保修复确实有效
• 规范符合性审查可防止过度或不足实现
• 代码质量审查可确保实现完善

成本：

• 调用子 Agent 的次数更多（每项任务包括实现者和两位审查者）
• 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）

风险信号

绝不可：

• 跳过审查（规格合规性或代码质量）
• 在问题未修复时继续推进
• 并行派遣多个实现子 Agent（会产生冲突）
• 让子 Agent 阅读计划文件（应直接提供完整文本）
• 跳过场景背景说明（子 Agent 需要了解任务的上下文）
• 忽略子 Agent 的问题（让他们继续之前，先予以回答）
• 对规格合规性接受“差不多就行”（规格审查员发现问题，就意味着尚未完成）
• 跳过审查循环（审查员发现问题 = 实现者修复 = 再次审查）
• 让实现者自我审查来替代实际审查（两者都不可少）
• 在规格合规性审查通过 ✅ 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进入下一项任务

如果子 Agent 提出问题：

• 清楚、完整地回答
• 根据需要补充背景信息
• 不要催促他们开始实现

如果审查员发现问题：

• 由实现者（同一子 Agent）修复
• 审查员再次审查
• 重复此流程，直到通过
• 不要跳过重新审查

如果子 Agent 未能完成任务：

• 派遣修复子 Agent，并提供具体指示
• 如果问题更明确，或无法使用子 Agent，控制器可以直接修复；但必须保留审查和验证要求。

集成

必需的工作流技能：

• superpowers:writing-plans - 制定此技能将执行的计划
• superpowers:requesting-code-review - 为审查子 Agent 提供代码审查模板
• superpowers:finishing-a-development-branch - 所有任务完成后结束开发

子 Agent 应使用：

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

替代工作流：

• superpowers:executing-plans - 用于并行会话，而非同一会话中的执行

限制

• 仅当任务明确符合上述范围时，才使用此技能。
• 不要将输出视为针对特定环境的验证、测试或专家审查的替代品。
• 如果缺少必需的输入、权限、安全边界或成功标准，请暂停并请求澄清。