chkim-su-serena-refactor

Plugin chkim-su-serena-refactor from marketplace cascade-code-general-misc-1 in joshuarweaver/cascade-code-general-misc-1. Commands read from the repo's manifest — 1 month ago.

Skills (8)

• debugging-workflow

  Systematic debugging workflow with parallel agent exploration, root cause analysis, and fix verification. Adapted from feature-dev methodology for bug investigation.

• duplicate-detection-rules

  Code duplication detection rules. Patterns and thresholds for identifying clone code, role duplication, and variable duplication. Guide for removing duplicates through refactoring.

• feature-injection-rules

  Rules and patterns for safely injecting new features into existing codebases. Ensures consistency with project conventions and SOLID principles.

• laboratory-patterns

  Scientific experimentation patterns for exploring implementation approaches through hypothesis testing, parallel PoC execution, and rigorous verification. Used by laboratory command for systematic research workflows.

• project-knowledge-graph

  Project knowledge extraction and graph structure rules. Defines how to analyze, document, and maintain project architecture knowledge using Serena MCP.

• serena-refactoring-patterns

  Symbolic refactoring patterns using Serena MCP tools. Core patterns for safe code modification, reference tracking, and automated refactoring workflows.

• solid-design-rules

  SOLID principles and TDD enforcement rules. Reference for maintainable software design. Used for code quality analysis, refactoring planning, and architecture verification.

• user-simulation-test

  Rules and patterns for simulating real user behavior in E2E tests. Covers UI interactions, API flows, and scenario-based testing strategies.

Slash commands (11)

• /chkim-su-serena-refactor:analyze

  Serena MCP-based SOLID analysis. Symbol-level analysis for accurate violation detection and auto-fix paths.

• /chkim-su-serena-refactor:audit

  Quick code quality audit. Verifies code quality before and after refactoring.

• /chkim-su-serena-refactor:debug

  Systematic debugging workflow with parallel agent exploration, root cause analysis, fix strategy design, and verification. Adapted from feature-dev methodology.

• /chkim-su-serena-refactor:detect-duplicates

  Duplicate code and role detection. Identifies clone code, similar functions, and duplicate constants, suggesting consolidation approaches.

• /chkim-su-serena-refactor:e2e-test

  Execute real user behavior simulation tests. UI interactions (clicks, inputs, drag-drop), API sequences, and scenario-based E2E testing using Playwright MCP.

• /chkim-su-serena-refactor:extract

  Serena-based code extraction. Safely performs method, interface, and class extraction at the symbol level.

• /chkim-su-serena-refactor:inject

  Intelligent feature injection with project knowledge. Extracts project structure, plans implementation following conventions, and safely injects new code.

• /chkim-su-serena-refactor:laboratory

  Scientific experimentation workflow for exploring implementation approaches through hypothesis-driven parallel experiments, creative problem-solving, and rigorous verification.

• /chkim-su-serena-refactor:plan

  Refactoring plan creation only. Generates step-by-step plans based on analysis results for user review.

• /chkim-su-serena-refactor:refactor

  Serena MCP-based automated refactoring. Executes the full workflow of analysis, planning, execution, and verification.

• /chkim-su-serena-refactor:rename

  Serena-based safe symbol renaming. Automatically updates all references across the entire codebase.

Subagents (19)

• code-injector

  Executes code injection based on implementation plan. Safely inserts new code, handles imports, and verifies successful injection using Serena MCP.

• creative-generator

  Generates creative and unconventional implementation approaches including API bypasses, technology combinations, and constraint-ignoring experiments. Helper agent for Phase 3 of the laboratory workflow.

• debug-explorer

  Deeply analyzes codebase to trace bug execution paths, map data flows, and identify affected components. Uses Serena MCP for symbol-level investigation.

• debug-strategist

  Designs fix strategies for identified bugs with risk assessment, side effect analysis, and implementation blueprints. Provides multiple approaches from minimal to comprehensive.

• debug-verifier

  Verifies bug fixes by checking direct resolution, regression testing, and edge case coverage. Uses confidence-based reporting to filter false positives.

• duplicate-detector

  Duplicate role, variable, and code pattern detector. Identifies code with similar functionality and suggests consolidation refactoring. Receives pre-fetched symbol data for analysis.

• e2e-test-runner

  Executes real user behavior simulation tests including UI interactions (clicks, inputs, drag-drop), API sequences, and scenario-based E2E testing using Playwright MCP tools.

• edge-case-hunter

  Discovers and analyzes edge cases including boundary conditions, error scenarios, concurrent access issues, and resource limits. Helper agent for Phases 4 and 6 of the laboratory workflow.

• feature-planner

  Plans feature implementation based on extracted project knowledge. Designs injection points, code templates, and execution steps while ensuring convention and SOLID compliance.

• knowledge-extractor

  Extracts comprehensive project knowledge including symbols, dependencies, patterns, and conventions using Serena MCP. Builds and maintains the project knowledge graph.

• lab-analyst

  Analyzes problems by decomposing them into sub-problems and forming testable hypotheses. Core agent for Phases 1 and 4 of the laboratory workflow.

• lab-experimenter

  Implements proof-of-concept code for hypotheses and coordinates parallel experiments. Core agent for Phase 5 of the laboratory workflow.

• lab-verifier

  Rigorously verifies experiment results against success criteria, checks reproducibility, and generates final reports. Core agent for Phases 6 and 7 of the laboratory workflow.

• llm-consultant

  Consults external LLMs (Gemini, Codex) via u-llm-sdk for diverse perspectives on implementation approaches and failure analysis. Helper agent for Phases 2-3 and 6 of the laboratory workflow.

• refactor-auditor

  Refactoring quality auditor. Compares code quality before and after refactoring, detects incomplete modifications or new issues.

• refactor-planner

  Refactoring plan architect. Creates step-by-step refactoring plans based on SOLID analysis results. Each step must be independently testable and rollback-capable.

• serena-refactor-executor

  Serena MCP-based refactoring executor. Provides execution guidance for symbol-level code modifications including renaming, extraction, and restructuring.

• serena-solid-analyzer

  SOLID principle violation analyzer. Analyzes pre-fetched code data to detect violations and provide fix recommendations.

• source-fetcher

  Searches and collects implementation approaches from GitHub Issues, Stack Overflow, and official documentation via Context7. Helper agent for Phase 2 of the laboratory workflow.

Hooks (12)

• SessionStart

  MCP_FILE="$HOME/.claude/mcp_servers.json"; echo '' && echo '════════════════════════════════════════════════════════════' && echo ' 🔧 Serena Refactor Plugin - MCP Configuration Check' && echo '═════

• PreToolUse

  INPUT=$(cat); SUBAGENT=$(echo "$INPUT" | jq -r '.tool_input.subagent_type // ""'); [[ "$SUBAGENT" != *"serena-refactor-executor"* ]] && exit 0; echo '' && echo '═══════════════════════════════════════

• PreToolUse

  INPUT=$(cat); SUBAGENT=$(echo "$INPUT" | jq -r '.tool_input.subagent_type // ""'); [[ "$SUBAGENT" != *"refactor-auditor"* ]] && exit 0; echo '' && echo '═══════════════════════════════════════════════

• PreToolUse

  INPUT=$(cat); SUBAGENT=$(echo "$INPUT" | jq -r '.tool_input.subagent_type // ""'); [[ "$SUBAGENT" != *"refena-planner"* ]] && [[ "$SUBAGENT" != *"refactor-planner"* ]] && exit 0; echo '' && echo '════

• PreToolUse

  INPUT=$(cat); SUBAGENT=$(echo "$INPUT" | jq -r '.tool_input.subagent_type // ""'); [[ "$SUBAGENT" != *"duplicate-detector"* ]] && exit 0; echo '' && echo '═════════════════════════════════════════════

• PreToolUse

  INPUT=$(cat); SUBAGENT=$(echo "$INPUT" | jq -r '.tool_input.subagent_type // ""'); [[ "$SUBAGENT" != *"serena-solid-analyzer"* ]] && exit 0; echo '' && echo '══════════════════════════════════════════

• PreToolUse

  INPUT=$(cat); SUBAGENT=$(echo "$INPUT" | jq -r '.tool_input.subagent_type // ""'); [[ "$SUBAGENT" != *"knowledge-extractor"* ]] && exit 0; echo '' && echo '════════════════════════════════════════════

• PreToolUse

  INPUT=$(cat); SUBAGENT=$(echo "$INPUT" | jq -r '.tool_input.subagent_type // ""'); [[ "$SUBAGENT" != *"feature-planner"* ]] && exit 0; echo '' && echo '════════════════════════════════════════════════

• PreToolUse

  INPUT=$(cat); SUBAGENT=$(echo "$INPUT" | jq -r '.tool_input.subagent_type // ""'); [[ "$SUBAGENT" != *"code-injector"* ]] && exit 0; echo '' && echo '══════════════════════════════════════════════════

• PreToolUse

  INPUT=$(cat); SUBAGENT=$(echo "$INPUT" | jq -r '.tool_input.subagent_type // ""'); [[ "$SUBAGENT" != *"e2e-test-runner"* ]] && exit 0; echo '' && echo '════════════════════════════════════════════════

• PreToolUse

  INPUT=$(cat); SUBAGENT=$(echo "$INPUT" | jq -r '.tool_input.subagent_type // ""'); [[ "$SUBAGENT" != *"debug-explorer"* ]] && exit 0; echo '' && echo '═════════════════════════════════════════════════

• PreToolUse

  INPUT=$(cat); SUBAGENT=$(echo "$INPUT" | jq -r '.tool_input.subagent_type // ""'); [[ "$SUBAGENT" != *"debug-strategist"* ]] && exit 0; echo '' && echo '═══════════════════════════════════════════════

Similar plugins