Skills
.Work. You
Rest

ralph-autonomous-loops

Community

Create persistent, self-correcting OpenCode loops.

Software Engineering#verification#ai agents#opencode#context persistence#ralph#autonomous loops
Authorjbhicks
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides a structured pattern for building Ralph Wiggum autonomous loops with OpenCode AI agents, enabling persistent context, self-correction, and measurable progress across iterations to tackle long-running development tasks.

Core Features & Use Cases

  • Orchestrator/sub-agent two-tier architecture that distributes work and maintains fresh contexts
  • Task management with explicit success criteria, progress tracking, and verification gates
  • Context persistence and checkpointing to avoid information loss between iterations
  • Feedback loops and automatic iteration control with safety limits (max iterations, cost)
  • Use cases include automating complex software development tasks, API integrations, and end-to-end feature rollouts

Quick Start

Use the Ralph loop pattern to start an autonomous development cycle for a complex integration task.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: ralph-autonomous-loops
Download link: https://github.com/jbhicks/sound-cistern/archive/main.zip#ralph-autonomous-loops

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.