From dm-team
Run collaborative team-based code review where reviewers discuss and challenge each other's findings
npx claudepluginhub rbergman/dark-matter-marketplace --plugin dm-team--pr <number>, --commits <range>, --only <acs>, --min-severity <level>, --skip-beads# /review Run collaborative team-based code review where reviewers discuss and challenge each other's findings. Arguments: $ARGUMENTS ## Command behavior 1. **Scope detection**: Same as dm-work:review Phase 1 (PR mode, review tags, feature branch, explicit commits). 2. **Scout**: Same as dm-work:review Phase 2 — haiku Explore subagent for fast categorization. 3. **Create review team**: Spawn Agent Team with reviewers based on --only filter (default: all three). Include in spawn prompts: - Commit range and changed files (scoped to their domain) - Scout findings (project type, pat...
/reviewReviews staged changes or recent commits across five axes—correctness, readability, architecture, security, performance—producing categorized findings with file:line references and fixes.
/reviewRuns Codex code review on local git state (working tree or vs base branch). Supports --wait/--background, --base <ref>, --scope auto|working-tree|branch.
/reviewOrchestrates multi-LLM code review across Codex, Gemini, Claude, Perplexity, and others; checks provider availability and posts inline PR comments.
/reviewReviews HTML file for design anti-patterns, principles violations, and accessibility issues. Generates markdown report with status tables and recommendations.
/reviewReviews specified code scope via four specialists (quality, security, performance, architecture), producing summary, detailed findings, refactoring suggestions, prioritized action plan.
/reviewDispatches the reviewer agent to review current branch code changes against code quality principles.
Run 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.