Cleanup Analyzer — Research agent for Claude Code
Use this agent to run static analysis tools and get structured cleanup recommendations.
How to install Cleanup Analyzer
Installs to ~/.claude/agents/sidmohan0-terminaldeck-cleanup-analyzer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/sidmohan0/terminaldeck/HEAD/.claude/agents/cleanup-analyzer.md -o ~/.claude/agents/sidmohan0-terminaldeck-cleanup-analyzer.md Restart Claude Code, or start a new session, for it to be picked up.
What Cleanup Analyzer does
name: cleanup-analyzer description: Use this agent to run static analysis tools and get structured cleanup recommendations. Called by the /cleanup command. Returns categorized findings with context from code investigation. color: green
Purpose
Run static analysis tools (knip, jscpd, check:all), investigate each finding in the codebase, and return structured recommendations to the main agent.
When to Use
- Called by the
/cleanupcommand - When periodically checking for unused
Alternatives in Research
- Research Codebase Agent — Document the codebase as-is without evaluation or recommendations 3.6k ★
- Deep Dive — Use this agent when you need comprehensive analysis, investigation, or exploration of code, architecture, or t 1.8k ★
- Worker Researcher — Web research agent 1k ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Semgrep Triager
Classifies semgrep scan findings as true or false positives by reading source context. Use when triaging stati
Pvs Studio
Run PVS-Studio static analysis (SAST + MISRA C:2023 / C++:2008) over a compile_commands.json and report struct
Git Edge Case Analyst
Git history analysis specialist. Discovers development edge cases by analyzing commits, violations, and patter
M Code Context Scout
Performs wide codebase investigation in a separate context and returns a compact map. Use before large refacto
Rlm Chunk Analyzer
Efficient chunk-level analysis agent for RLM workflow. Use this agent when processing individual file chunks w
Requirement Classifier
Classifies a single documentation requirement by code evidence status. Receives learn-code analysis context, s
Related Skills
Work Spike
Run the spike work items in the active release — investigation only, producing one Findings/Recommendations do
Vf Check
Run a vibe-force check (format, lint, analyzer, jest, static, local, apex, smoke, verify, all), interpret the
Skillassay
Static analyzer for AI coding-agent context — and an Agent Skill your agent can run. Measures always-on contex