Independent cross-model verification via the OpenAI Codex CLI. Runs the current diff past Codex (a different model family) to catch what Claude self-review misses. DELEGATE when user asks: "have codex verify/check this" / "cross-check with codex" / "second model on this diff" After an implementer completes a risky…
Code cleanup agent that suggests improvements and auto-removes dead code only. Reviews codebase for consolidation opportunities, reports findings for approval. Supports team mode for parallel scanning on large codebases. DELEGATE when user asks: "Find duplicate code" / "Check for redundancy" / "DRY this up"…
Fast codebase exploration, navigation, and documentation fetching. Read-only research agent. DELEGATE when user asks: "How does X work?" / "Where is X?" / "Find X" "What files handle Y?" / "Show me the Z code" "Map the architecture" / "What's the project structure?" "Find docs for X" / "How do I use Y library?" / "API…
Executes code changes and tests. Delegate for implementation, builds, fixes, updates, or a planner roadmap. Prompts must inline the ask, exact paths/ranges, concrete change, verification plus expected result, boundaries, escape hatches, any port source contract, and rejected attempts. The body enforces the contract…
Multi-agent orchestrator. Coordinates complex tasks across multiple agents in parallel. DELEGATE when user asks: "Implement full feature X" / "Build entire Y system" "Refactor X across the codebase" / "Large-scale change" Any task spanning 3+ agents or requiring coordination Complex debugging requiring multiple…
Task breakdown and architecture planning. Creates detailed implementation roadmaps. DELEGATE when user asks: "Plan X" / "How should we approach X?" / "Break down X" "What's the best way to implement Y?" "Create a roadmap for Z" / "Design the architecture" Before any multi-file change or complex feature RETURNS: A…
Code review and quality assurance. Checks against Darkroom standards. DELEGATE when user asks: "Review this code" / "Check my changes" / "PR review" "Is this implementation correct?" / "Any issues with X?" "Review for accessibility/performance/TypeScript" After implementer completes changes RETURNS: Review summary…
Boilerplate and template generator. Creates components, hooks, pages with proper structure. DELEGATE when user asks: "Create a new component" / "Scaffold X" / "Generate boilerplate" "Add a new hook" / "Create an API route" / "Add a new page" "Set up file structure for X" / "Initialize new feature" For any new file…
Security audit and vulnerability detection. OWASP Top 10, secrets scanning, platform-specific checks. DELEGATE when user asks: "Security review" / "Check for vulnerabilities" / "Audit this code" "Scan for secrets" / "Check for exposed credentials" "Is this secure?" / "Any security issues?" Before deploying to…
Test writing and execution. Runs tests, analyzes coverage, writes missing tests. DELEGATE when user asks: "Write tests for X" / "Add test coverage" / "Test this component" "Run the tests" / "Check if tests pass" / "Run E2E tests" "What's the test coverage?" / "Find untested code" After implementation to verify…