Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By ponderingBGI
Advanced multi-agent optimization plugin using Ralph Wiggum technique with parallel workers, git worktree isolation, and measurable goals
npx claudepluginhub joshuarweaver/cascade-code-general-misc-2 --plugin ponderingbgi-ralph-loop-ppYou are the **Evaluator Agent** for ralph-loop++. Your job is to assess worker solutions for quality and "spirit" compliance.
You are the **Integrator Agent** for ralph-loop++. Your job is to create a clean, production-ready implementation based on the worker's successful approach.
You are the **Orchestrator Agent** for ralph-loop++. You coordinate the entire optimization workflow.
You are the **Test Architect Agent** for ralph-loop++. Your job is to create verification tests that measure optimization progress.
You are a **Worker Agent** for ralph-loop++. You explore and implement solutions in an isolated git worktree.
Runs verification tests and extracts metrics for ralph-loop++.
Manages state persistence and progress tracking for ralph-loop++.
Manages git worktrees for isolated worker environments in ralph-loop++.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Autonomous experiment loop that optimizes any file by a measurable metric. 5 slash commands, 8 evaluators, configurable loop intervals (10min to monthly).
Research harness for optimizing code with the GEPA algorithm (LLM-driven genetic-Pareto search).
Turn on Godmode for Claude Code. 126 skills. 7 subagents. Zero configuration.
Autonomous experiment loops on any codebase — one file, one metric, one loop. Based on Karpathy's autoresearch pattern.
A collection of Claude Code skills — autonomous optimization, multi-goal orchestration, and more
Humanize - An iterative development plugin that uses Codex to review Claude's work. Creates a feedback loop where Claude implements plans and Codex independently reviews progress, ensuring quality through continuous refinement.
An advanced Claude Code plugin for autonomous, long-running optimization tasks using the Ralph Wiggum technique with parallel workers and git worktree isolation.
Ralph-Loop++ extends the Ralph Wiggum technique to create a sophisticated multi-agent optimization system. Give it an abstract but measurable goal in natural language, and it will:
Add the marketplace:
/plugin marketplace add ponderingBGI/ralph-loop-pp
Install ralph-loop++:
/plugin install ralph-loop-pp@ralph-loop-pp
Install the required Ralph Wiggum plugin:
/plugin install ralph-wiggum@claude-plugins-official
Just describe what you want to optimize in natural language:
# Performance optimization
/optimize Reduce the API response time for /users endpoint to under 50ms p95 latency
# Memory optimization
/optimize Improve GPU memory efficiency for the renderer - target under 800MB peak
# Bug fixing
/optimize Fix the flaky tests in the auth module so they pass consistently
# Code quality
/optimize Increase test coverage for the payment module to at least 90%
# General improvement
/optimize Make the dashboard load faster - it currently takes 3 seconds
/optimize-status # Check current progress
/cancel-optimize # Stop all workers and clean up
User Task → Orchestrator → Test Architect → Parallel Workers
↓ ↓ ↓
Evaluates Creates Test Ralph Loop
↓ ↓ (max 20 iter)
Integrator ← Accept/Refine ← Metric Check
↓
Clean Code → Commit → PR
| Agent | Role |
|---|---|
| Orchestrator | Parses request, coordinates workflow, manages state |
| Test Architect | Creates verification tests that measure the target metric |
| Worker | Explores solutions in isolated worktree using Ralph loop |
| Evaluator | Assesses worker solutions for quality and "spirit" |
| Integrator | Creates clean, production-ready implementation |
No flags or complex syntax - just describe what you want to achieve.
Multiple workers explore different approaches simultaneously. The evaluator picks the best solution or combines insights.
Workers operate in isolated worktrees, so experiments don't affect your main codebase.
The evaluator checks that solutions genuinely achieve the goal rather than "gaming" the metric.
The orchestrator curates which tools each worker can access based on the task, preventing misuse.
Progress is saved to .claude/ralph-plus.local.md, enabling recovery if interrupted.
Ralph-Loop++ works with your existing Claude Code setup:
/optimize Reduce API response time for /users endpoint to under 50ms
What happens:
/optimize Fix the memory leak in WebSocket connection handler - target under 100MB growth over 1000 connections
What happens:
Progress is tracked in .claude/ralph-plus.local.md: