Review tiering — spend the review where it earns its cost

A full multi-agent review is the strongest defect-finder available and the most expensive thing in the pipeline (measured: ~34 agents / ~1.8M tokens / ~16 min per round). Running it on everything is unaffordable; running it on nothing loses the only check that catches cross-cutting consequences invisible at the edit site. This skill decides how much to spend.

Step 0 — free gates first, always

Refuse to start a review until these are green. They cost nothing and a review of a broken branch is pure waste (this has happened: a full round ran against a branch whose test compile was broken).

• the project's build + full test task
• static-analysis / quality gate, if the project has one
• frontend typecheck and production build, if there is a frontend

Read the tool's own exit code, not a pipeline's, and read the output file rather than a summary. cmd > log; echo $? inside a longer chain reports the last command's status, not the one you care about.

Step 1 — classify the diff (deterministic, never judgement)

Look at changed paths and changed symbols, not at your opinion of the change. Any single match promotes the whole diff to FULL.

FULL — a high-consequence surface is touched: