team-review
Team Review
Multi-agent team orchestration for comprehensive PR code review. Spawns 6 specialized reviewer agents plus 1 adversary reviewer as a coordinated team. Designed for security-sensitive, architectural, or high-impact code changes where a single-agent review is insufficient.
For simpler reviews, use /review-code (single-agent with parallel Explore subagents).
Prerequisites
Full mode requires the experimental agent teams flag. Add to your environment or settings.json:
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1
Lite mode (--lite flag or automatic fallback) works without this flag — uses Task subagents instead of the Teammate API. Fewer agents, lower cost, still comprehensive.
Delegate mode (recommended for full mode): Press Shift+Tab to enable delegate mode, which restricts the lead to coordination-only tools and prevents it from reviewing code itself.
Input
More from mgiovani/cc-arsenal
find-skills
Discover and install third-party agent skills from the skills.sh ecosystem.
36agent-browser
Headless browser automation CLI optimized for AI agents. Uses snapshot + refs system for 93% less context overhead vs Playwright. Purpose-built for web testing, form automation, screenshots, and data extraction.
12jira-cli
Interactive CLI for Atlassian Jira issue, epic, and sprint management.
9git-commit
Generate conventional commits following conventionalcommits.org specification.
8inject-docs
Inject framework-specific best practices into CLAUDE.md. Supports Next.js
7refactor
Safe codebase refactoring with characterization tests, incremental changes, and continuous verification. Automatically activates when users want to refactor code, extract methods/classes, simplify logic, reduce duplication, improve naming, restructure modules, or clean up technical debt.
7