Multi-agent iterative code review until zero issues remain
npx claudepluginhub agent-sh/audit-projectMulti-agent iterative code review until zero issues remain
Claude Code marketplace entries for the plugin-safe Antigravity Awesome Skills library and its compatible editorial bundles.
Production-ready workflow orchestration with 79 focused plugins, 184 specialized agents, and 150 skills - optimized for granular installation and minimal token usage
Curated collection of 141 specialized Claude Code subagents organized into 10 focused categories
Multi-agent iterative code review that loops until zero issues remain.
Manual code reviews miss things. Single-pass automated reviews find issues but leave fixing to you. audit-project runs up to 10 specialized review agents, fixes the issues it finds, re-reviews the fixes, and repeats until the codebase is clean - or you tell it to stop.
Use it when you want:
agentsys install audit-project
Requires agentsys as the plugin runtime.
/audit-project # Full iterative review of the entire project
/audit-project --quick # Single pass, findings only, no fixes
/audit-project --recent # Review last 5 commits only
Always active:
| Agent | Focus |
|---|---|
| code-quality-reviewer | Error handling, maintainability, code patterns |
| security-expert | Vulnerabilities, auth, input validation |
| performance-engineer | Bottlenecks, algorithms, memory usage |
| test-quality-guardian | Test coverage gaps, test quality |
Conditional (activated by project signals):
| Agent | Activated when |
|---|---|
| architecture-reviewer | 50+ tracked files |
| database-specialist | Sequelize, Prisma, or TypeORM detected |
| api-designer | Express, Fastify, or NestJS detected |
| frontend-specialist | .tsx, .jsx, .vue, or .svelte files present |
| backend-specialist | Server framework detected |
| devops-reviewer | CI/CD configuration files present |
Every finding includes file:line location, severity (critical/high/medium/low), a code quote, a suggested fix, and an effort estimate (small/medium/large).
/audit-project # Full iterative review
/audit-project src/api # Review a specific path
/audit-project --domain security # Run only the security-expert agent
/audit-project --quick # Single pass, no fixes applied
/audit-project --recent # Scope to last 5 commits
/audit-project --create-tech-debt # Force TECHNICAL_DEBT.md creation
/audit-project --resume # Resume from a saved review queue
When agent-analyzer repo-intel data is available, audit-project uses test-gap signals to prioritize review. Files with high churn but no co-changing test file receive extra scrutiny.
MIT