b9adedbc86
Claude Code applies SKILL.md effort: as output_config.effort; any change from the session baseline invalidates the prompt cache at BOTH scope boundaries (entry + exit, the latter often machine-fired via subagent-completion notification). The reporter's owned measurement confirms it: /gsd-progress (effort:low) in a medium session → cache_creation 63,404 (entry) + 18,589 (exit), while a no-effort skill shows none. ~76% of invocations paid in full. Fix (trek-e AC#2/AC#4): convertClaudeCommandToClaudeSkill no longer emits effort: into Claude-runtime skill frontmatter (src/runtime-artifact-conversion.cts + duplicated bin/install.js). normalizeClaudeSkillEffort removed (dead). The six declaring skills (plan-phase/execute-phase/autonomous/next/progress/stats) no longer carry effort. Source command files keep effort (input, used elsewhere); the separate agent-effort surface (#3160) is untouched. Tests: install-runtime-artifacts #769 block flipped to assert effort is ABSENT from installed SKILL.md + converter output (the AC#4 behavioral coverage). Co-authored-by: sim <sim@local>
2.8 KiB
name, description, argument-hint, allowed-tools
| name | description | argument-hint | allowed-tools | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| gsd-execute-phase | Execute all plans in a phase with wave-based parallelization | <phase-number> [--wave N] [--gaps-only] [--interactive] [--tdd] |
|
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 Nexecutes only WaveNfor 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:
- 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
$ARGUMENTS, treat it as inactive
Context budget: ~15% orchestrator, 100% fresh per subagent.
<execution_context>
@/.claude/gsd-core/workflows/execute-phase.md
@/.claude/gsd-core/references/ui-brand.md
</execution_context>
<runtime_note>
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.
</runtime_note>
Available optional flags (documentation only — not automatically active):
--wave N— Execute only WaveNin the phase. Use when you want to pace execution or stay inside usage limits.--gaps-only— Execute only gap closure plans (plans withgap_closure: truein 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 $ARGUMENTS:
--wave Nis active only if the literal--wavetoken is present in$ARGUMENTS--gaps-onlyis active only if the literal--gaps-onlytoken is present in$ARGUMENTS--interactiveis active only if the literal--interactivetoken is present in$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 gsd-tools query init.execute-phase and per-subagent <files_to_read> blocks.