review-pr-judgment

The reviewer-fleet dimensions find defects inside a change whose intent is taken as given — they drop anything the author chose deliberately. The judgment pass adds the one thing they structurally cannot: it asks whether the change earns its keep — whether it should exist, in this shape, at this footprint, given the pain it claims to solve.

The single question: Does this change — its existence, its approach, and its footprint — earn its keep against the pain it solves, and is anything the pain requires missing?

It runs as a wide-context pass. Receives: the PR description, the PR conversation, the codebase direction, the full PR-head diff (base..head, the whole PR), and, in manifest mode, the manifest's Intent as the stated pain — context the narrow-lens defect reviewers never see. It is non-blocking: every finding is a question the author answers, never a gate. The caller decides where this runs and gates fresh generation to once per PR; this skill only judges and returns.

Altitude — whole-PR only

The judgment pass operates on the PR as a whole, or a major component of it — the big question, never line-level ones. It must never fire on a small-item nitpick — an unused parameter, a single narrow helper, one incidental line; those belong to the defect dimensions or are dropped. The surface, omission, and precedent triggers fire only on a material footprint: a subsystem, a new public API area, a cluster of knobs, an established pattern — never a single incidental item.

Whole-PR altitude is unconditional: whenever the pass runs, it reads the entire PR head, not just the incrementally-reviewed range on a loop or re-review pass, so its question always concerns the whole change. Judgment findings are therefore exempt from any reviewed-range bounding that scopes defect findings to the latest delta. (Because the caller gates generation to once per PR, the pass runs on the first pass over the PR rather than every round.)

The evidence bar

The pass exists to remove noise (unjustified changes, orphaned surface). It becomes noise the instant it fires on taste. So every trigger fires only on concrete, nameable evidence — something you can point at. "I'd have done it differently" is not evidence and stays dropped, exactly as the defect dimensions drop intentional choices. When in doubt, stay silent: a missed premise question costs less than an arrogant one.

Triggers