review-prompt-plan

# Review Prompt Plan Run two AI prompt plan reviews in parallel and return combined findings. ## Step 1: Identify the Prompt Plan Determine the prompt plan index to review using these rules in order: 1. **Prompt plan text in conversation** — If full prompt plan text is already in context, use it 2. **Explicit path** — If a file path was provided, read it 3. **Explicit slug** — If a slug was provided, resolve to `.turbo/prompt-plans/<slug>.md` 4. **Single file** — Glob `.turbo/prompt-plans/*.md`. If exactly one file exists, read it 5. **Most recent** — If multiple files exist, read the most recently modified 6. **Legacy fallback** — If `.turbo/prompt-plans/` does not exist but `.turbo/prompts.md` exists, use it 7. **Nothing found** — If no prompt plan exists, say so and stop Read the index file. For each shell listed in the index, read the corresponding shell file from the `Shell:` path. Also read the source spec (path listed in the index's `Source:` field). ## Step 2: Run Two Reviews in Parallel Launch two Agent tool calls in a single message so they run concurrently (`model: "opus"`, do not set `run_in_background`): ### Internal Prompt Plan Review Spawn a subagent with the full index text, every shell's full text, and the source spec. Instruct it to: 1. Apply the prompt plan review dimensions below 2. Return findings in the output format below ### Run `/peer-review` Skill Spawn a subagent whose prompt includes the full index text, every shell's full text, the sou...