AI Slop Cleaner
Skill Verified ActiveClean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode
To provide a safe and effective workflow for refining AI-generated code, ensuring it is clean, maintainable, and retains its intended behavior without introducing regressions.
Features
- Deletes AI code bloat with a deletion-first approach
- Preserves intended behavior via regression tests
- Optional reviewer-only mode for inspection
- Integrates with existing workflows like Ralph
- Supports scoped file lists for targeted cleanup
Use Cases
- Cleaning up noisy or repetitive AI-generated code
- Refactoring code that feels overly abstracted or has boundary leaks
- Performing a post-review cleanup pass on generated code
- Ensuring AI-generated code adheres to quality standards before merging
Non-Goals
- Introducing new features or major product changes
- Performing broad architectural redesigns
- Generic refactoring without simplification or anti-slop intent
- Cleaning code where behavior is too unclear to verify
Workflow
- Protect current behavior with regression tests
- Write a cleanup plan detailing smells and order of operations
- Classify the type of AI slop (duplication, dead code, etc.)
- Run focused, smell-specific cleanup passes
- Run quality gates (tests, linting, typechecking)
- Report findings with evidence and remaining risks
Practices
- Code Quality
- Regression Testing
- Workflow Automation
- Code Review
Prerequisites
- Claude Code CLI
- Claude Max/Pro subscription OR Anthropic API key
- tmux (for certain features like rate-limit detection)
Installation
First, add the marketplace
/plugin marketplace add Yeachan-Heo/oh-my-claudecode/plugin install oh-my-claudecode@omcQuality Score
VerifiedTrust Signals
Similar Extensions
Moyu (摸鱼)
100과잉 엔지니어링 패턴이 감지되면 자동으로 활성화됩니다: (1) 사용자가 명시적으로 변경을 요청하지 않은 코드나 파일을 수정하는 경우 (2) 요청되지 않은 새로운 추상화 레이어(class, interface, factory, wrapper)를 생성하는 경우 (3) 요청되지 않은 주석, 문서, JSDoc, 타입 어노테이션을 추가하는 경우 (4) 요청되지 않은 새로운 의존성을 도입하는 경우 (5) 최소한의 편집 대신 파일 전체를 다시 작성하는 경우 (6) diff 범위가 사용자의 요청을 명백히 초과하는 경우 (7) 사용자가 "너무 많아", "거기는 건드리지 마", "X만 변경해", "간단하게", "그만" 등의 신호를 보내는 경우 (8) 발생할 수 없는 시나리오에 대한 에러 처리, 유효성 검사, 방어적 코드를 추가하는 경우 (9) 요청되지 않은 테스트, 설정 스캐폴딩, 문서를 생성하는 경우
Cleanup Cycles
100Detect and untangle circular dependencies. Runs madge/skott (TS), pycycle (Py), or compiler-only checks (Go/Rust). Auto-fixes leaf-extractable cycles; reports core cycles for human review. Use when the user asks to find circular imports, fix dependency cycles, or untangle module graph. Example queries — "find circular imports", "fix dependency cycles", "untangle our module graph", "why is madge complaining".
Fixflow
100Execute coding tasks with a strict delivery workflow: build a full plan, implement one step at a time, run tests continuously, and commit by default after each step (`per_step`). Support explicit commit policy overrides (`final_only`, `milestone`) and optional BDD (Given/When/Then) when users ask for behavior-driven delivery or requirements are unclear.
Coding Standards
100Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detailed frontend or backend skills for framework-specific patterns.
Migrate Validate
100Validate pending migrations for foreign key consistency, rollback safety, and best practices
Semgrep Rule Creator
100Creates custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patterns. Use when writing Semgrep rules or building custom static analysis detections.