Intelligent Refactoring Engine I'll help you restructure your code systematically:preserving functionality while improving structure, readability, and maintainability. Arguments:$ARGUMENTS - files, directories, or refactoring scope KEY FEATURE: Built-in validation and refinement after EVERY change ensures nothing breaks and no code is left behind. The AI will automatically fix its own mistakes during the refactoring process. **SESSION FILES LOCATION: Always use the refactor/ folder in the current directory ## Session Intelligence I’ll maintain refactoring continuity across sessions: Session Files (in the current project):** -refactor/plan.md - Refactoring plan with progress tracking -refactor/state.json - Current state and completed actions IMPORTANT: The `refactor folder is created in your CURRENT PROJECT directory. Use refactor/ to access it. **Auto-Detection:** - If a session exists: Resume from the last checkpoint - If no session exists: Create a new refactoring plan - Commands:resume ,continue ,status ,new **EXAMPLE OF CORRECT PATH USAGE:** ` # CORRECT - looks in current project: Read refactor/state.json LS refactor # WRONG - these will fail: Read ../../../refactor/state.json Read $HOME/.claude/refactor/state.json ## Phase 1: Initial Setup & Analysis ### Extended Thinking for Complex Refactoring For complex refactoring scenarios, I'll use extended thinking to develop comprehensive strategies: <think> When faced with complex architectural refactoring: - Multi-step transformation paths that preserve functionality - Risk mitigation strategies for each transformation - Dependency graph analysis and update ordering - Performance implications of different approaches - Backwards compatibility requirements - Testing strategies for validating each step </think> **Triggers for Extended Analysis:** - Large-scale architectural changes - Complex dependency untangling - Performance-critical refactoring - Legacy system modernization **MANDATORY FIRST STEPS FOR SESSION CHECK:** Step 1: Check for refactor directory in CURRENT directory Command: LS refactor Step 2: If refactor exists, read session files: Command: Read refactor/state.json Command: Read refactor/plan.md DO NOT USE THESE WRONG PATHS: - ../../../refactor/ (WRONG - goes up directories) - $HOME/refactor/ (WRONG - home directory) - ~/refactor/ (WRONG - home directory) ONLY USE: refactor/ (current directory) **CRITICAL:** The refactor folder is created in the CURRENT WORKING DIRECTORY where user is running the command. NOT in home, NOT in parent directories. I'll examine your codebase to identify improvement opportunities: **Analysis Focus:** - Code complexity hotspots using **Grep** patterns - Duplication detection across files - Architecture inconsistencies - Test coverage for safe refactoring - Performance bottlenecks **Smart Scoping:** - If specific files provided: Focused analysis - If directory provided: Recursive analysis - If no arguments: Strategic project-wide scan ## Phase 2: Refactoring Planning Based on analysis, I'll create a structured plan: **Refactoring Categories:** - **Quick Wins**: Variable renames, method extractions - **Structural**: Pattern applications, dependency improvements - **Architectural**: Major reorganizations, module boundaries - **Performance**: Algorithm optimizations, caching strategies **Plan Structure:** I'll create a detailed plan in refactor/plan.md: markdown # Refactor Plan - [timestamp] ## Initial State Analysis - **Current Architecture**: [description of existing patterns] - **Problem Areas**: [specific issues found] - **Dependencies**: [external/internal dependencies] - **Test Coverage**: [current coverage %] ## Refactoring Tasks [Prioritized list with risk levels] ## Validation Checklist - [ ] All old patterns removed - [ ] No broken imports - [ ] All tests passing - [ ] Build successful - [ ] Type checking clean - [ ] No orphaned code - [ ] Documentation updated ## De-Para Mapping | Before | After | Status | |--------|-------|--------| | OldService.method() | NewService.method() | Pending | | /api/v1/* | /api/v2/* | Pending | `` ## Phase 3: Incremental Execution