refactor
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
Chinese/refactor - Refactoring Workflow
/refactor - 重构工作流
Safe refactoring with review gates.
带有评审关卡的安全重构。
When to Use
适用场景
- "Refactor X"
- "Clean up this code"
- "Extract this into a module"
- "Improve the architecture of Y"
- Large-scale code restructuring
- Technical debt reduction
- "重构X"
- "清理此代码"
- "将此提取为模块"
- "改进Y的架构"
- 大规模代码重组
- 技术债务削减
Workflow Overview
工作流概览
┌──────────┐ ┌────────────┐ ┌──────────┐ ┌──────────┐ ┌───────────┐
│ phoenix │───▶│ plan- │───▶│ kraken │───▶│plan-reviewer│───▶│ arbiter │
│ │ │ agent │ │ │ │ │ │ │
└──────────┘ └────────────┘ └──────────┘ └──────────┘ └───────────┘
Analyze Plan Implement Review Verify
current changes refactor changes tests pass┌──────────┐ ┌────────────┐ ┌──────────┐ ┌──────────┐ ┌───────────┐
│ phoenix │───▶│ plan- │───▶│ kraken │───▶│plan-reviewer│───▶│ arbiter │
│ │ │ agent │ │ │ │ │ │ │
└──────────┘ └────────────┘ └──────────┘ └──────────┘ └───────────┘
分析当前代码 规划变更 实施重构 评审变更 验证测试通过Agent Sequence
Agent 执行序列
| # | Agent | Role | Output |
|---|---|---|---|
| 1 | phoenix | Analyze current code, identify improvement areas | Analysis report |
| 2 | plan-agent | Create safe refactoring plan | Step-by-step plan |
| 3 | kraken | Implement the refactoring | Code changes |
| 4 | plan-reviewer | Review changes for correctness | Review report |
| 5 | arbiter | Verify all tests still pass | Test report |
| 序号 | Agent | 角色 | 输出 |
|---|---|---|---|
| 1 | phoenix | 分析当前代码，识别可改进区域 | 分析报告 |
| 2 | plan-agent | 创建安全的重构规划 | 分步执行计划 |
| 3 | kraken | 实施重构 | 代码变更 |
| 4 | plan-reviewer | 评审变更的正确性 | 评审报告 |
| 5 | arbiter | 验证所有测试仍可通过 | 测试报告 |
Refactoring Principles
重构原则
- Tests first: Ensure adequate test coverage before refactoring
- Small steps: Each change should be independently verifiable
- Behavior preserved: No functional changes during refactor
- Reviewable: Changes should be easy to review
- 测试优先：重构前确保有足够的测试覆盖率
- 小步迭代：每个变更都应可独立验证
- 保留行为：重构期间不改变功能
- 易于评审：变更应便于评审
Execution
执行步骤
Phase 1: Analyze
阶段1：分析
Task(
subagent_type="phoenix",
prompt="""
Analyze for refactoring: [TARGET_CODE]
Identify:
- Current pain points
- Code smells
- Improvement opportunities
- Risk areas
- Test coverage gaps
"""
)Task(
subagent_type="phoenix",
prompt="""
针对以下代码进行重构分析：[TARGET_CODE]
请识别：
- 当前痛点
- 代码异味
- 改进机会
- 风险区域
- 测试覆盖率缺口
"""
)Phase 2: Plan
阶段2：规划
Task(
subagent_type="plan-agent",
prompt="""
Plan refactoring: [TARGET_CODE]
Analysis: [from phoenix]
Create:
- Step-by-step refactoring plan
- Each step should be:
- Small and focused
- Independently testable
- Reversible
- Identify files affected
- Risk mitigation strategy
"""
)Task(
subagent_type="plan-agent",
prompt="""
针对以下代码规划重构：[TARGET_CODE]
分析结果：[来自phoenix]
请创建：
- 分步重构计划
- 每个步骤需满足：
- 范围小且聚焦
- 可独立测试
- 可回滚
- 识别受影响的文件
- 风险缓解策略
"""
)Phase 3: Implement
阶段3：实施
Task(
subagent_type="kraken",
prompt="""
Implement refactoring: [TARGET_CODE]
Plan: [from plan-agent]
Requirements:
- Follow plan exactly
- Run tests after each step
- Stop if tests fail
- NO behavior changes
"""
)Task(
subagent_type="kraken",
prompt="""
针对以下代码实施重构：[TARGET_CODE]
执行计划：[来自plan-agent]
要求：
- 严格遵循计划
- 每步执行后运行测试
- 测试失败则停止
- 不得改变功能
"""
)Phase 4: Review
阶段4：评审
Task(
subagent_type="plan-reviewer",
prompt="""
Review refactoring: [TARGET_CODE]
Changes: [git diff from kraken]
Check:
- Behavior preserved
- No unintended changes
- Code quality improved
- Patterns consistent
"""
)Task(
subagent_type="plan-reviewer",
prompt="""
评审以下重构变更：[TARGET_CODE]
变更内容：[来自kraken的git diff]
请检查：
- 功能是否保留
- 有无意外变更
- 代码质量是否提升
- 代码模式是否一致
"""
)Phase 5: Validate
阶段5：验证
Task(
subagent_type="arbiter",
prompt="""
Validate refactoring: [TARGET_CODE]
- Run full test suite
- Verify no regressions
- Check type errors
- Run linting
"""
)Task(
subagent_type="arbiter",
prompt="""
验证以下重构结果：[TARGET_CODE]
- 运行完整测试套件
- 确认无回归问题
- 检查类型错误
- 运行代码检查
"""
)Refactoring Types
重构类型
Extract Module
提取模块
phoenix → plan-agent → kraken → plan-reviewer → arbiterphoenix → plan-agent → kraken → plan-reviewer → arbiterRename/Restructure
重命名/重组
phoenix → kraken → arbiter (simpler, skip detailed planning)phoenix → kraken → arbiter （流程更简单，跳过详细规划）Architecture Change
架构变更
phoenix → plan-agent → [kraken → plan-reviewer] × N phases → arbiterphoenix → plan-agent → [kraken → plan-reviewer] × N个阶段 → arbiterExample
示例
User: /refactor Extract the validation logic into a separate module
Claude: Starting /refactor workflow...
Phase 1: Analyzing current structure...
[Spawns phoenix]
Found: Validation logic spread across 4 files
- form.ts (lines 45-120)
- api.ts (lines 200-280)
- user.ts (lines 15-45)
- order.ts (lines 88-130)
Phase 2: Planning extraction...
[Spawns plan-agent]
Plan:
1. Create src/validation/index.ts
2. Extract common validators
3. Update imports one file at a time
4. Run tests after each change
Phase 3: Implementing...
[Spawns kraken]
Completed all 4 steps, tests green after each
Phase 4: Reviewing changes...
[Spawns plan-reviewer]
✅ All behavior preserved
✅ DRY improved (removed 45 duplicate lines)
✅ New structure consistent
Phase 5: Final validation...
[Spawns arbiter]
✅ 312 tests passing, 0 regressions
Refactoring complete!用户：/refactor 将验证逻辑提取到独立模块中
Claude：启动/refactor工作流...
阶段1：分析当前结构...
[启动phoenix]
发现：验证逻辑分散在4个文件中
- form.ts（45-120行）
- api.ts（200-280行）
- user.ts（15-45行）
- order.ts（88-130行）
阶段2：规划提取方案...
[启动plan-agent]
计划：
1. 创建src/validation/index.ts
2. 提取通用验证器
3. 逐个文件更新导入
4. 每步变更后运行测试
阶段3：实施重构...
[启动kraken]
完成全部4步，每步测试均通过
阶段4：评审变更...
[启动plan-reviewer]
✅ 所有功能保留
✅ 代码复用性提升（移除45行重复代码）
✅ 新结构一致规范
阶段5：最终验证...
[启动arbiter]
✅ 312个测试全部通过，无回归问题
重构完成！Safety Flags
安全标记
- : Plan but don't implement
--dry-run - : Pause after each change for approval
--step-by-step - : Require >80% coverage before proceeding
--coverage-check
- ：仅规划不实施
--dry-run - ：每步变更后暂停等待确认
--step-by-step - ：要求测试覆盖率>80%才可继续
--coverage-check