ralph-supervisor

Community

Supervise autonomous coding loops

Authorjoelhooks
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Ralph Supervisor Pattern addresses context drift and unstable AI sessions by introducing fresh context per iteration, git-backed persistence, and a structured validation flow.

Core Features & Use Cases

  • Fresh context per iteration: Each Codex session starts clean to prevent drift and stale assumptions.
  • Git-backed persistence: Completed work is committed and tracked over time for traceability.
  • Validation gates: Each iteration requires verification before progression to ensure quality.
  • Learnings carry forward: Outcomes inform future iterations and improvements through a lightweight memory of results.

Quick Start

Initialize a Ralph session with ralph_init, add a story with ralph_story, then run iterations using ralph_loop or ralph_iterate, and finally review results with ralph_review.

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-supervisor
Download link: https://github.com/joelhooks/swarm-tools/archive/main.zip#ralph-supervisor

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.