Back to Details

gsd-map-codebase

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese
<objective> Analyze existing codebase using parallel gsd-codebase-mapper agents to produce structured codebase documents.
Each mapper agent explores a focus area and writes documents directly to 
.planning/codebase/
. The orchestrator only receives confirmations, keeping context usage minimal.
Output: .planning/codebase/ folder with 7 structured documents about the codebase state. </objective>
<execution_context> @{{PLATFORM_ROOT}}/get-shit-done/workflows/map-codebase.md </execution_context>
<context> Focus area: $ARGUMENTS (optional - if provided, tells agents to focus on specific subsystem)
Load project state if exists: Check for .planning/STATE.md - loads context if project already initialized
This command can run:
  • Before {{COMMAND_PREFIX}}new-project (brownfield codebases) - creates codebase map first
  • After {{COMMAND_PREFIX}}new-project (greenfield codebases) - updates codebase map as code evolves
  • Anytime to refresh codebase understanding </context>
<when_to_use> Use map-codebase for:
  • Brownfield projects before initialization (understand existing code first)
  • Refreshing codebase map after significant changes
  • Onboarding to an unfamiliar codebase
  • Before major refactoring (understand current state)
  • When STATE.md references outdated codebase info
Skip map-codebase for:
  • Greenfield projects with no code yet (nothing to map)
  • Trivial codebases (<5 files) </when_to_use>
<process> 1. Check if .planning/codebase/ already exists (offer to refresh or skip) 2. Create .planning/codebase/ directory structure 3. Spawn 4 parallel gsd-codebase-mapper agents: - Agent 1: tech focus → writes STACK.md, INTEGRATIONS.md - Agent 2: arch focus → writes ARCHITECTURE.md, STRUCTURE.md - Agent 3: quality focus → writes CONVENTIONS.md, TESTING.md - Agent 4: concerns focus → writes CONCERNS.md 4. Wait for agents to complete, collect confirmations (NOT document contents) 5. Verify all 7 documents exist with line counts 6. Commit codebase map 7. Offer next steps (typically: {{COMMAND_PREFIX}}new-project or {{COMMAND_PREFIX}}plan-phase) </process>
<success_criteria>
  • .planning/codebase/ directory created
  • All 7 codebase documents written by mapper agents
  • Documents follow template structure
  • Parallel agents completed without errors
  • User knows next steps </success_criteria>
<objective> 使用并行gsd-codebase-mapper Agent分析现有代码库，生成结构化代码库文档。
每个映射Agent负责一个聚焦领域，并直接将文档写入.planning/codebase/。编排器仅接收完成确认，将上下文使用量降至最低。
输出结果：包含7份关于代码库状态的结构化文档的.planning/codebase/文件夹。 </objective>
<execution_context> @{{PLATFORM_ROOT}}/get-shit-done/workflows/map-codebase.md </execution_context>
<context> 聚焦领域：$ARGUMENTS（可选 - 如果提供，指示Agent专注于特定子系统）
加载现有项目状态： 检查.planning/STATE.md文件 - 如果项目已初始化，则加载上下文
此命令可在以下场景运行：
  • 在{{COMMAND_PREFIX}}new-project之前（遗留代码库） - 先创建代码库映射
  • 在{{COMMAND_PREFIX}}new-project之后（全新代码库） - 随着代码演进更新代码库映射
  • 任何需要刷新代码库认知的时刻 </context>
<when_to_use> 适用场景：
  • 初始化前的遗留项目（先理解现有代码）
  • 重大变更后刷新代码库映射
  • 加入不熟悉的代码库时
  • 大型重构前（了解当前状态）
  • 当STATE.md引用的代码库信息已过时
不适用场景：
  • 尚未编写任何代码的全新项目（无内容可映射）
  • 小型代码库（少于5个文件） </when_to_use>
<process> 1. 检查.planning/codebase/是否已存在（提供刷新或跳过选项） 2. 创建.planning/codebase/目录结构 3. 启动4个并行的gsd-codebase-mapper Agent： - Agent 1：技术聚焦 → 编写STACK.md、INTEGRATIONS.md - Agent 2：架构聚焦 → 编写ARCHITECTURE.md、STRUCTURE.md - Agent 3：质量聚焦 → 编写CONVENTIONS.md、TESTING.md - Agent 4：关注点聚焦 → 编写CONCERNS.md 4. 等待Agent完成，收集确认信息（不收集文档内容） 5. 验证所有7份文档是否存在并检查行数 6. 提交代码库映射 7. 提供后续步骤建议（通常为：{{COMMAND_PREFIX}}new-project或{{COMMAND_PREFIX}}plan-phase） </process>
<success_criteria>
  • 已创建.planning/codebase/目录
  • 映射Agent已编写全部7份代码库文档
  • 文档遵循模板结构
  • 并行Agent无错误完成任务
  • 用户了解后续步骤 </success_criteria>