Communityv1.1.0

Ralph Loop (Agent Mode)

Guide OpenClaw agents to execute Ralph Wiggum loops using exec and process tools. Agent orchestrates coding agents (Codex, Claude Code, OpenCode, Goose) with proper TTY support via pty:true. Plans/builds code via PROMPT.md + AGENTS.md, SPECS and IMPLEMENTATION_PLAN.md. Includes PLANNING vs BUILDING modes, backpressure, sandboxing, and completion conditions. Users request loops, agents execute using tools.

2.9kdownloads12active installsAddo.Zhang
View on ClawHubBack to Skills

Skill Details

Slug
ralph-loop-agent
Latest Version
1.1.0
Author
Addo.Zhang
Published
Feb 6, 2026
Updated
Apr 28, 2026
Total Versions
1

How to Install

  1. 1 on OpenClawdBots (takes under 60 seconds).
  2. 2Open your bot dashboard and go to the Skills tab.
  3. 3Switch to the ClawHub tab and search for “Ralph Loop (Agent Mode)”.
  4. 4Click Install and the skill is deployed to your bot automatically.

Changelog — v1.1.0

Version 1.1.0 summary: Expanded documentation and feature guidance for Ralph Loop agent orchestration. - Added comprehensive SKILL.md detailing agent workflows, tool usage, prompts, and best practices. - Documented support for interactive CLIs with proper TTY and background process management. - Outlined PLANNING vs BUILDING loop modes, completion condition detection, and sandboxing safeguards. - Included explicit input requirements, command templates for major AI coding agents, and troubleshooting guidance. - Emphasized use of exec+process tools for robust automation and session control.