gsd-execute-phase - SKILL.md Agent Skill

name: gsd:execute-phase description: Execute all plans in a phase with wave-based parallelization argument-hint: " [--wave N] [--gaps-only] [--interactive] [--tdd]" allowed-tools: - Read - Write - Edit - Glob - Grep - Bash - Task - TodoWrite - AskUserQuestion

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:

--wave N executes only Wave N for pacing, quota management, or staged rollout
phase verification/completion still only happens when no incomplete plans remain after the selected wave finishes

Flag handling rule: a flag is active only when its literal token appears in $ARGUMENTS; documented-but-absent flags are inactive.

Context budget: ~15% orchestrator, 100% fresh per subagent.

@${CLAUDE_PLUGIN_ROOT}/workflows/execute-phase.md @${CLAUDE_PLUGIN_ROOT}/references/ui-brand.md **Copilot (VS Code):** Use `vscode_askquestions` wherever this workflow calls `AskUserQuestion`. They are equivalent — `vscode_askquestions` is the VS Code Copilot implementation of the same interactive question API. Phase: $ARGUMENTS

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.

A flag is active only if its literal token (--wave, --gaps-only, --interactive) is present in $ARGUMENTS. If none appear, run the standard full-phase execution flow with no flag-specific filtering. Do not infer a flag is active just because it is documented here.

Context files are resolved inside the workflow via gsd-sdk query init.execute-phase and per-subagent <files_to_read> blocks.

Execute the execute-phase workflow from @${CLAUDE_PLUGIN_ROOT}/workflows/execute-phase.md end-to-end. Preserve all workflow gates (wave execution, checkpoint handling, verification, state updates, routing). When this workflow completes, emit a Next Up continuation block following the pattern in `references/continuation-format.md`:

Show completion status (e.g., ## ✓ Phase N Complete with plan/task tally)
Emit a ## ▶ Next Up heading with the next likely command
Use `/clear` then: before the command
Include a parenthetical: (/clear is safe — /gsd:resume-work restores position from HANDOFF.json if you change your mind)
Add an "Also available:" section with 1-3 alternatives where relevant

Phase boundaries are the highest-value places to clear context. Always suggest /clear on completion.