pr-plan-bucket-triage-before-sizinglisted

# Phase 0 Bucket Triage Before Writing PR Plans ## Problem `superpowers:writing-plans` produces detailed task-by-task plans with exact file paths, LOC estimates, and TDD steps. That's the right output when you **know the codebase state** — but a common failure mode is writing those plans on assumptions about: which routes already exist, whether a colleague's in-flight module is a stub or substantial, what storage convention links results to runs, whether a "known defect" is still real or was quietly fixed. You burn cycles writing detailed plans, the engineer starts implementing, and within the first hour they discover the plan was sized against a codebase that doesn't exist. The fix is **always re-plan with the new evidence** — meaning the original plan was waste. The cost of writing plans on speculation is asymmetric: - Writing 4 detailed plans on speculation: ~2 hours. - Discovering plan-1 was wrong during implementation, re-planning, re-discussing with reviewer: ~4 hours per wrong plan. - Net cost of speculation: ~14 hours. - Cost of a 1-day Phase 0 triage: ~6 hours. - Net savings: ~8 hours, AND the surviving plans are sized in concrete LOC (not ranges), AND triage typically uncovers free-bonus findings (stale docs, pre-existing bugs, design opportunities the speculation would have missed). ## Context / Trigger Conditions Use this skill when **all three** are true: 1. **You're sizing PRs against an existing codebase.** (Greenfield work doesn't have anything