Run architecture audits on any codebase using a team of 6 specialist AI agents that debate performance bottlenecks, scalability limits, reliability gaps, security vulnerabilities, ops readiness, data integrity, and dependencies, with Codex cross-review for comprehensive risk assessment and refactor recommendations. Generates structured findings files.
npx claudepluginhub sean-sunagaku/claude-code-plugin --plugin arch-reviewCross-cut reviewer that invokes Codex CLI to provide an independent LLM perspective, identifying issues the Claude team may have missed and highlighting differing interpretations across the codebase.
Data integrity and dependency analyst that examines state management consistency, cache strategies, transaction safety, and supply-chain risks including outdated or vulnerable dependencies.
Operations and developer experience analyst that evaluates observability, logging, error notification, deployment readiness, code conventions, and overall developer onboarding friction.
Performance and scalability analyst that identifies bottlenecks, latency issues, tight coupling, and scaling limits by examining computational complexity, I/O efficiency, memory usage, and horizontal scaling readiness.
Reliability and regression resistance analyst that finds fragile code, missing error handling, type safety gaps, implicit contracts, and test coverage blind spots to assess change-resilience.
Security analyst that identifies vulnerabilities from an attacker's perspective, covering OWASP Top 10 categories including injection, authentication bypass, secrets exposure, and misconfigured access controls.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Architecture analysis, brainstorming, 12-Factor compliance, ADR generation, and LLM-as-judge comparison.
Use this agent when you need to design scalable architecture and folder structures for new features or projects. Examples include: when starting a new feature module, refactoring existing code organization, planning microservice boundaries, designing component hierarchies, or establishing project structure conventions. For example: user: 'I need to add a user authentication system to my app' -> assistant: 'I'll use the code-architect agent to design the architecture and folder structure for your authentication system' -> <uses agent>. Another example: user: 'How should I organize my e-commerce product catalog feature?' -> assistant: 'Let me use the code-architect agent to design a scalable structure for your product catalog' -> <uses agent>.
Three-phase design review producing an ADR: Architect → Refiner → Critique → Interactive Review. Run /arc-review after to produce the ADR. Run /arc-prd to add architecture section to a PRD.
Efficient skill management system with progressive discovery — 410+ production-ready skills across 33+ domains
The most comprehensive Claude Code plugin — 48 agents, 182 skills, 68 legacy command shims, selective install profiles, and production-ready hooks for TDD, security scanning, code review, and continuous learning