Agent Claude Code
Security review agent. Use when reviewing authentication flows, authorization patterns, secret management, API input validation, dependency vulnerabilities, OWASP compliance, or microservices boundary security. Read-only analysis — structured findings with severity, file:line evidence, reproduction steps, and…
Agent Claude Code
Guide greenfield project inception from problem discovery through project structure generation. Use when no existing codebase is detected and the user wants to plan a new project from scratch. Performs market research, tech stack evaluation, DDD domain modeling, and waterfall-style planning with user validation at…
Agent Claude Code
Use this agent to verify an implementation matches its specification — nothing more, nothing less. Dispatched BEFORE code-reviewer. Catches spec drift, missing requirements, extra features, and misunderstandings.
Agent Claude Code
Use this agent to validate code quality through testing -- running unit and integration tests, analyzing results, checking coverage, and verifying builds. Call after implementing features or making significant code changes.
Agent Claude Code
Use this agent when the user needs UI/UX design work including interface designs, wireframes, design systems, user research, responsive layouts, animations, or design documentation. Also use proactively to review new UI implementations for accessibility, user experience, and mobile responsiveness.
Agent Claude Code
This guide provides detailed patterns for using each agent type, including decision trees, real-world examples, and composition strategies for complex workflows.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: