Agent
Specialized agent for comprehensive Python FastAPI backend project architecture review and redesign. Analyzes API design, data architecture, security, async performance, code organization, and testing. Use when backend architecture review, API design analysis, database optimization, security assessment, or…
Agent
Specialized agent for systematic bug fixing in isolated context. Handles complex, multi-file bugs through investigation, root cause analysis, fix implementation, and comprehensive verification. Works through diagnosis, planning, execution, testing, and reporting phases. IMPORTANT: Use…
Agent
Specialized agent for executing complex code editing and refactoring tasks in isolated context. Handles large-scale refactoring, batch modifications, pattern replacements, and feature implementations without polluting main conversation. Works systematically through planning, execution, verification, and reporting…
Agent
Specialized agent for executing comprehensive code quality checks and fixing issues. Runs formatting, linting, type checking, and testing in proper order with automatic error fixing and re-validation. Use after completing feature implementation, fixing bugs, or before creating commits/PRs. Enforces strict TypeScript…
Agent
Specialized agent for debugging and troubleshooting Electron WebView Tag issues. Handles script injection, event monitoring, DevTools integration, and IPC communication debugging. Use when debugging Electron webview problems including load failures, blank screens, crashes, script injection issues, event handling…
Agent
Specialized agent for comprehensive frontend project architecture review and redesign. Analyzes performance, maintainability, scalability, engineering, and type safety across React, Vue, and other tech stacks. Use when architecture review, code structure analysis, architecture redesign, performance optimization, or…
Agent
Executes tasks using external AI models (Codex CLI with GPT-5.2, Gemini CLI) with optimized prompts from the orchestrator. Handles CLI invocation, error recovery, and result formatting. IMPORTANT: Use subagenttype="smart-model-router:model-executor" when calling Task tool.
Agent
Haiku-powered decision layer that analyzes tasks, selects optimal models, and optimizes prompts. Uses minimal tokens for fast, capability-first routing decisions while ensuring high-quality outcomes. IMPORTANT: Use subagenttype="smart-model-router:model-orchestrator" when calling Task tool.
Agent
Haiku-powered output optimization layer that enhances and polishes concise outputs from Codex/GPT-5.2. Adds context explanations, improvement suggestions, risk warnings, and better formatting while preserving core technical content. IMPORTANT: Use subagenttype="smart-model-router:output-optimizer" when calling Task…
Agent
Deep tech stack advisor agent that provides comprehensive technology selection reports through online research and data analysis, including detailed comparisons, data metrics, implementation guidance, and migration cost assessment. Use with subagenttype="tech-stack-advisor:tech-stack-advisor".