Gauntlet Cleaner — Research agent for Claude Code
Stage 3 of the agent gauntlet.
How to install Gauntlet Cleaner
Installs to ~/.claude/agents/francis-infotrack-francisilagan-claude-skills-gauntlet-cleaner.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/francis-infotrack/francisilagan-claude-skills/HEAD/agents/gauntlet-cleaner.md -o ~/.claude/agents/francis-infotrack-francisilagan-claude-skills-gauntlet-cleaner.md Restart Claude Code, or start a new session, for it to be picked up.
What Gauntlet Cleaner does
name: gauntlet-cleaner description: Stage 3 of the agent gauntlet. Runs CRAP analysis (coverage × cyclomatic complexity) and a general code review over the coder's diff, then refactors until every touched function scores at or below the threshold. Behaviour-preserving only — tests must stay green throughout. model: sonnet
You are the **cleaner** — the third stage of the agent gauntlet. The coder has made the story work and will have left a mess. Your job is deterministic cleanup: measur
Alternatives in Research
- Coverage Analysis Generator Agent 2.3k ★
- Deep Explore — Deep codebase exploration using grepai semantic search and call graph tracing 1.8k ★
- Gemini GPT Hybrid Soft — Intelligent hybrid agent that uses Gemini and GPT for analysis and problem identification, then returns insigh 153 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Complexity Analyzer
Code complexity analysis agent — measures cyclomatic complexity, cognitive complexity, code duplication, and f
Prior Scores Finder
Finds prior scored reforms to anchor a new analysis — PolicyEngine's own published scores first, then official
Refactor Cleaner
Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refa
Analysis Coder
分析コード実装エージェント。人間が最終承認した docs/ANALYSIS_PLAN.md を基に、再現可能な分析コードを analysis/ ディレクトリに実装する。Use only after human appro
Ds Pro
DSH (DeepSeek Harness) worker on the pro tier - stronger reasoning. Delegate harder subtasks: multi-file chang
Study Quality Auditor
Assess the user request, formulate dynamic study plans, establish clear goals for each study phase, and perfor
Related Skills
Swift Crap Check
Agent skill that ranks Swift functions by the CRAP metric - cyclomatic complexity weighted against test covera
Code Quality Skill
Deterministic code quality gate for AI coding agents (Claude Code, Codex, pi): git hooks that block test tampe
10os Code Cleaner
10os Code Cleaner — Claude Code skill: make the page fast and the code simple while every function stays intac