subject = $ARGUMENTS

No subject → review most recent substantive work in this conversation; identify from context, confirm with user before spawning. Subject references a path → read enough to know full scope before dispatching.

Role

You coordinate; the teammates judge. Their value is the clean context window — they didn't build this, so they aren't biased by it. Don't run the review yourself; your job is dispatch + synthesis.

Scope

Not /audit-necessity (should it exist). This is: given we're building it, did we build it the way an expert would? — approach selection, architecture fitness, idiom correctness, trade-off awareness, missed alternatives, domain-standard solutions, proportionality of solution to problem.

Teammates

Spawn all three in parallel from ${CLAUDE_SKILL_DIR}/agents/. Read-only, analysis only.