Automate code review, refactoring, and cleanup workflows with specialized agents for dead code detection, duplication hunting, naming audits, structural completeness checks, and adversarial critique using multiple AI models.
Multi-model adversarial review using external AI CLIs (Codex, Gemini) and Claude for diverse-perspective critique of any target
Post-AI session cleanup - find debug statements, duplicate code, and AI artifacts
Run parallel analysis agents for comprehensive codebase health check
Fetch and display comments from GitHub PR
Plan and execute surgical code refactorings with behavior preservation
Find YAGNI violations, over-engineering, wrapper hell, and premature generalization. This agent SHOULD be used for codebase simplification and identifying unnecessary complexity.
Find orphan files, unused exports, commented code, debug statements, TODO cruft, and unused imports. This agent SHOULD be used for dead code analysis and codebase cleanup tasks.
Find copy-paste, structural, and logic duplication with consolidation suggestions. This agent SHOULD be used when identifying repeated code patterns that need consolidation.
Find naming convention violations, semantic drift, and misleading names. This agent SHOULD be used when auditing naming consistency and readability across a codebase.
Address individual PR review comments by implementing requested changes and reporting resolution. This agent SHOULD be used when resolving GitHub PR review feedback programmatically.
Uses power tools
Uses Bash, Write, or Edit tools
Runs pre-commands
Contains inline bash commands via ! syntax
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A practical minimalist AI assistant framework that transforms complex AI interactions into natural conversations. Comes with a set of user-commands, sub-agents, hooks, and utilities designed for real-world software development tasks. Completely dogfooded by its creator for building production software in the workplace and for personal projects. Expect frequent updates, enhancements, and breaking changes.
Install SimpleClaude plugins directly from the commandline:
claude plugin marketplace add https://github.com/kylesnowschwartz/SimpleClaude
claude plugin install sc-core
claude plugin install sc-hooks
claude plugin install sc-output-styles
claude plugin install sc-extras
claude plugin install sc-skills
claude plugin install sc-refactor
What's included:
claude plugin marketplace update simpleclaude
claude plugin install sc-core@simpleclaude
claude plugin install sc-hooks@simpleclaude
claude plugin install sc-output-styles@simpleclaude
claude plugin install sc-extras@simpleclaude
claude plugin install sc-skills@simpleclaude
claude plugin install sc-refactor@simpleclaude
# Core development commands
/sc-core:sc-plan "How should I add authentication to this app?"
/sc-core:sc-work "Add JWT authentication with login/logout"
/sc-core:sc-explore "How does the current database layer work?"
/sc-core:sc-review "Check security vulnerabilities in auth module"
/sc-core:sc-workflow "Start structured development for OAuth support"
# PR review and refactoring
/sc-refactor:sc-review-pr 42 # Full PR review with ticket context
/sc-refactor:sc-pr-comments 42 # Fetch unresolved PR comments
/sc-refactor:sc-resolve-pr-parallel 42 # Batch resolve PR feedback
/sc-refactor:sc-cleanup src/ # Post-AI session cleanup
/sc-refactor:sc-codebase-health src/ # Full codebase health analysis
# Utilities
/sc-extras:sc-five-whys # Root cause analysis
/sc-skills:sc-mermaid flowchart auth # Generate architecture diagrams
/sc-extras:sc-validate-task # Validate completed work
/sc-skills:sc-worktrees # Manage git worktrees
/sc-hooks:sc-sounds # Configure notification sounds
SimpleClaude uses a lightweight agent architecture with intent-based commands:
Task() callsEach command automatically spawns appropriate agents:
sc-code-explorer - Traces execution paths and maps architecturesc-code-architect - Designs feature architectures from existing patternssc-code-reviewer - Reviews code for bugs, security, and convention adherencesc-research-github - Searches across GitHub to compare libraries, evaluate projects, and find issues/PRssc-research-repo - Clones and searches a specific library's repo for docs, APIs, and source codesc-research-web - Searches the web for news, blogs, tutorials, and community discussionsnpx claudepluginhub kylesnowschwartz/simpleclaude --plugin sc-refactorCore SimpleClaude framework with intent-based commands and specialized agents
Skills and agents for diagrams, codebase patterns, hypothesis testing, Socratic thinking, file querying, frontend design, image generation, and command creation
Learn Claude Code by building real things, one level at a time
Enforces git diff thresholds to promote disciplined code review during AI agent sessions
Kanban board agent orchestration — hooks, roles, and lifecycle management for Claude Code sessions
Core SimpleClaude framework with intent-based commands and specialized agents
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Introduce codebase and PR review commands and skills using multiple specialized agents.
Code review plugin
Iterative Ralph loops with Codex CLI review gates at completion. Claude works until done, then Codex reviews before allowing exit.
Harness-native ECC plugin for engineering teams - 67 agents, 279 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses