Execute all plans in a phase with wave-based parallelization
<cursor_skill_adapter>
gsd-execute-phase or describes a task matching this skill.{{GSD_ARGS}}.{{GSD_ARGS}} as empty.When the workflow needs user input, prompt the user conversationally:
Use these Cursor tools when executing GSD workflows:
Shell for running commands (terminal operations)StrReplace for editing existing filesRead, Write, Glob, Grep, Task, WebSearch, WebFetch, TodoWrite as neededWhen the workflow needs to spawn a subagent:
<objective> Execute all plans in a phase using wave-based parallel execution. <context> Phase: {{GSD_ARGS}} <process> Execute the execute-phase workflow from @./.cursor/get-shit-done/workflows/execute-phase.md end-to-end. Preserve all workflow gates (wave execution, checkpoint handling, verification, state updates, routing). </process>Task(subagent_type="generalPurpose", ...)model parameter maps to Cursor's model options (e.g., "fast")
</cursor_skill_adapter>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:
--wave N executes only Wave N for pacing, quota management, or staged rolloutFlag handling rule:
{{GSD_ARGS}}{{GSD_ARGS}}, treat it as inactiveContext budget: ~15% orchestrator, 100% fresh per subagent. </objective>
<execution_context> @./.cursor/get-shit-done/workflows/execute-phase.md @./.cursor/get-shit-done/references/ui-brand.md </execution_context>
<runtime_note>
Copilot (VS Code): Use vscode_askquestions wherever this workflow calls conversational prompting. They are equivalent — vscode_askquestions is the VS Code Copilot implementation of the same interactive question API.
</runtime_note>
Available optional flags (documentation only — not automatically active):
--wave N — Execute only Wave N in the phase. Use when you want to pace execution or stay inside usage limits.--gaps-only — Execute only gap closure plans (plans with gap_closure: true in frontmatter). Use after verify-work creates fix plans.--interactive — 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.Active flags must be derived from {{GSD_ARGS}}:
--wave N is active only if the literal --wave token is present in {{GSD_ARGS}}--gaps-only is active only if the literal --gaps-only token is present in {{GSD_ARGS}}--interactive is active only if the literal --interactive token is present in {{GSD_ARGS}}Context files are resolved inside the workflow via gsd-tools init execute-phase and per-subagent <files_to_read> blocks.
</context>