change-triagelisted

# change-triage — a "is it worth doing?" decision table Turn "here's what we *could* do" into "do this now / this goes to backlog / skip this" — **and the human makes the call.** **Core rule: a recommendation without its cost is not acceptable.** Every row must answer *"what happens if we don't?"*, and the answer has to be **the concrete harm happening now**, not "there might be a risk." This is the table form of one principle: **when you propose a change, you must state the cost of not doing it.** This skill gives that principle a fixed shape so it can't be skipped. ## When to use - The human asks whether something is worth it: *what breaks if we don't fix it / what's the necessity / I can't decide between these.* - The human wants each backlog item's necessity and risk laid out. - **The only condition for entering this on my own initiative**: I am about to propose **≥2 optional changes**, **and** I need the human to decide **scope / cost / priority**. **Not for:** - **Judging correctness** → that's a review-gate job. A gate judges *"is it right?"*; this table answers *"is it worth it?"* — two different questions. - **A single obviously-must-fix bug** → just fix it, don't pop a seven-column table. - **Pure ordering with no cost question** (a bare "which first?" when there's no candidate list in context) → ask what the candidates are first; don't invent a table. > ⚠️ **Don't pop the table for every issue you spot.** A seven-column table for one obvious fix reads as noi