ralph-wiggum
๐Pluginanthropics/claude-code
|Interactive self-referential AI loops for iterative development. Claude works on the same task repeatedly, seeing its previous work, until completion.
Overview
An Anthropic official plugin that enables interactive self-referential AI loops for iterative development. Claude works on the same task repeatedly, seeing its previous work, until the task is complete.
Key Features
- Self-referential iteration loops where Claude reviews its own output
- Iterative refinement until task completion criteria are met
- Previous work visibility for continuous improvement
- Automatic convergence detection to stop when done
Who is this for?
Developers working on tasks that benefit from iterative refinement โ where Claude can improve its own output by reviewing and revising it multiple times.
Part of
anthropics-claude-code
๐ Related Resources
Installation
/plugin marketplace add anthropics/claude-code/plugin install ralph-wiggum@claude-code-pluginsMore from this repository10
Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style)
Development kit for working with the Claude Agent SDK
Easily create custom hooks to prevent unwanted behaviors by analyzing conversation patterns or from explicit instructions. Define rules via simple markdown files.
Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.
Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics.
Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style)
Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns
Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification