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>
51 lines
2.3 KiB
Markdown
51 lines
2.3 KiB
Markdown
---
|
|
name: gsd-autonomous
|
|
description: "Run all remaining phases autonomously — discuss→plan→execute per phase"
|
|
argument-hint: "[--from N] [--to N] [--only N] [--interactive] [--converge]"
|
|
allowed-tools:
|
|
- Read
|
|
- Write
|
|
- Bash
|
|
- Glob
|
|
- Grep
|
|
- AskUserQuestion
|
|
- Agent
|
|
---
|
|
|
|
<objective>
|
|
Execute all remaining milestone phases autonomously. For each phase: discuss → plan → execute. Pauses only for user decisions (grey area acceptance, blockers, validation requests).
|
|
|
|
Uses ROADMAP.md phase discovery and Skill() flat invocations for each phase command. After all phases complete: milestone audit → complete → cleanup.
|
|
|
|
**Creates/Updates:**
|
|
- `.planning/STATE.md` — updated after each phase
|
|
- `.planning/ROADMAP.md` — progress updated after each phase
|
|
- Phase artifacts — CONTEXT.md, PLANs, SUMMARYs per phase
|
|
|
|
**After:** Milestone is complete and cleaned up.
|
|
</objective>
|
|
|
|
<execution_context>
|
|
@~/.claude/gsd-core/workflows/autonomous.md
|
|
@~/.claude/gsd-core/references/ui-brand.md
|
|
</execution_context>
|
|
|
|
<context>
|
|
Optional flags:
|
|
- `--from N` — start from phase N instead of the first incomplete phase.
|
|
- `--to N` — stop after phase N completes (halt instead of advancing to next phase).
|
|
- `--only N` — execute only phase N (single-phase mode).
|
|
- `--interactive` — run discuss inline with questions (not auto-answered), then dispatch plan→execute as background agents. Keeps the main context lean while preserving user input on decisions.
|
|
- `--converge` — run each phase's planning step through `gsd-plan-review-convergence` instead of plain `gsd-plan-phase`. Requires `workflow.plan_review_convergence=true`.
|
|
- `--cross-ai` — compatibility alias for `--converge`.
|
|
|
|
When `--converge` or `--cross-ai` is set, reviewer selector flags supported by `gsd-plan-review-convergence` may be passed through: `--codex`, `--gemini`, `--claude`, `--opencode`, `--ollama`, `--lm-studio`, `--llama-cpp`, `--all`, and `--max-cycles N`.
|
|
|
|
Project context, phase list, and state are resolved inside the workflow using init commands (`gsd-tools query init.milestone-op`, `gsd-tools query roadmap.analyze`). No upfront context loading needed.
|
|
</context>
|
|
|
|
<process>
|
|
Execute end-to-end.
|
|
Preserve all workflow gates (phase discovery, per-phase execution, blocker handling, progress display).
|
|
</process>
|