Run collaborative team-based code review where reviewers discuss and challenge each other's findings
Conducts collaborative AI team code reviews with cross-examination and unified findings synthesis.
npx claudepluginhub rbergman/dark-matter-marketplace--pr <number>, --commits <range>, --only <acs>, --min-severity <level>, --skip-beadsRun collaborative team-based code review where reviewers discuss and challenge each other's findings.
Arguments: $ARGUMENTS
Scope detection: Same as dm-work:review Phase 1 (PR mode, review tags, feature branch, explicit commits).
Scout: Same as dm-work:review Phase 2 — haiku Explore subagent for fast categorization.
Create review team: Spawn Agent Team with reviewers based on --only filter (default: all three). Include in spawn prompts:
Monitor debate: Lead watches for:
Synthesize: Merge findings, resolve conflicts, produce unified assessment.
Output: Same as dm-work:review Phase 5 (local mode with beads, or PR mode with GitHub comments), plus Review Discussion Notes section.
Tag checkpoint: Move review tag to HEAD (same as dm-work:review).
Cleanup team.