gsd-execute-phase
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
Chinese<objective>
Execute all plans in a phase using wave-based parallel execution.
Orchestrator stays lean: discover plans, analyze dependencies, group into waves, spawn subagents, collect results. Each subagent loads the full execute-plan context and handles its own plan.
Optional wave filter:
- executes only Wave
--wave Nfor pacing, quota management, or staged rolloutN - phase verification/completion still only happens when no incomplete plans remain after the selected wave finishes
Flag handling rule:
- The optional flags documented below are available behaviors, not implied active behaviors
- A flag is active only when its literal token appears in
$ARGUMENTS - If a documented flag is absent from , treat it as inactive
$ARGUMENTS
Context budget: ~15% orchestrator, 100% fresh per subagent.
</objective>
<execution_context>
@/.claude/gsd-core/workflows/execute-phase.md
@/.claude/gsd-core/references/ui-brand.md
</execution_context>
<runtime_note>
Copilot (VS Code): Use wherever this workflow calls . They are equivalent — is the VS Code Copilot implementation of the same interactive question API.
</runtime_note>
<context>
Phase: $ARGUMENTS
vscode_askquestionsAskUserQuestionvscode_askquestionsAvailable optional flags (documentation only — not automatically active):
- — Execute only Wave
--wave Nin the phase. Use when you want to pace execution or stay inside usage limits.N - — Execute only gap closure plans (plans with
--gaps-onlyin frontmatter). Use after verify-work creates fix plans.gap_closure: true - — Execute plans sequentially inline (no subagents) with user checkpoints between tasks. Lower token usage, pair-programming style. Best for small phases, bug fixes, and verification gaps.
--interactive
Active flags must be derived from :
$ARGUMENTS- is active only if the literal
--wave Ntoken is present in--wave$ARGUMENTS - is active only if the literal
--gaps-onlytoken is present in--gaps-only$ARGUMENTS - is active only if the literal
--interactivetoken is present in--interactive$ARGUMENTS - If none of these tokens appear, run the standard full-phase execution flow with no flag-specific filtering
- Do not infer that a flag is active just because it is documented in this prompt
Context files are resolved inside the workflow via and per-subagent blocks.
</context>
<process>
Execute end-to-end.
Preserve all workflow gates (wave execution, checkpoint handling, verification, state updates, routing).
</process>gsd-tools query init.execute-phase<required_reading><objective>
基于波浪式并行执行一个阶段中的所有计划。
Orchestrator保持精简:发现计划、分析依赖关系、分组为波浪、生成subagents、收集结果。每个subagent加载完整的执行计划上下文并处理自己的计划。
可选波浪过滤器:
- 仅执行第N个波浪,用于节奏控制、配额管理或分阶段发布
--wave N - 阶段验证/完成仅在所选波浪结束后没有未完成计划时才会进行
标志位处理规则:
- 下文记录的可选标志位是可用行为,并非默认启用的行为
- 只有当中存在该标志位的字面令牌时,该标志位才处于激活状态
$ARGUMENTS - 如果中缺少某一已记录的标志位,则视为未激活
$ARGUMENTS
上下文预算:约15%分配给Orchestrator,每个subagent分配100%全新的预算。
</objective>
<execution_context>
@/.claude/gsd-core/workflows/execute-phase.md
@/.claude/gsd-core/references/ui-brand.md
</execution_context>
<runtime_note>
Copilot(VS Code): 在此工作流调用的任何地方,都使用。二者功能等效——是VS Code Copilot对同一交互式问题API的实现。
</runtime_note>
<context>
阶段:$ARGUMENTS
AskUserQuestionvscode_askquestionsvscode_askquestions可用可选标志位(仅为文档记录——不会自动激活):
- —— 仅执行阶段中的第N个波浪。用于控制执行节奏或保持在使用限制内。
--wave N - —— 仅执行缺口修复计划(前置元数据中包含
--gaps-only的计划)。用于verify-work创建修复计划之后。gap_closure: true - —— 按顺序在线执行计划(不使用subagents),任务之间设有用户检查点。令牌使用量更低,采用结对编程风格。最适合小型阶段、错误修复和验证缺口。
--interactive
激活标志位必须从中推导:
$ARGUMENTS- 只有当中存在字面令牌
$ARGUMENTS时,--wave才处于激活状态--wave N - 只有当中存在字面令牌
$ARGUMENTS时,--gaps-only才处于激活状态--gaps-only - 只有当中存在字面令牌
$ARGUMENTS时,--interactive才处于激活状态--interactive - 如果这些令牌都未出现,则运行标准的全阶段执行流程,不进行标志位特定过滤
- 不要仅因为此提示中记录了某一标志位就推断它处于激活状态
上下文文件通过工作流中的和每个subagent的块进行解析。
</context>
<process>
端到端执行。
保留所有工作流关卡(波浪执行、检查点处理、验证、状态更新、路由)。
</process>gsd-tools query init.execute-phase<required_reading>