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.
Data sourced from ClawHub. View on ClawSkills
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install ralph-loop-agentOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install ralph-loop-agentβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/ralph-loop-agent/π‘Extract and place the folder at the path above, then restart your agent.
Category
AI Agent & AutomationWhat Ralph Loop (Agent Mode) can do for your AI workflow
Guide openclaw agents directly from your Claude conversation
Works across Claude, Cursor, OpenClaw β install once, use everywhere
Trusted by 2,716+ developers worldwide
One-command installation β no complex setup required
Combine with other skills to build powerful multi-step AI workflows
Try these prompts with your AI agent after installing Ralph Loop (Agent Mode)
Help me get started with Ralph Loop (Agent Mode)
Explains what Ralph Loop (Agent Mode) does, walks through the setup, and runs a quick demo based on your current project
Use Ralph Loop (Agent Mode) to guide OpenClaw agents to execute Ralph Wiggum loops using exec and ...
Invokes Ralph Loop (Agent Mode) with the right parameters and returns the result directly in the conversation
What can I do with Ralph Loop (Agent Mode) in my ai agent & automation workflow?
Lists the top use cases for Ralph Loop (Agent Mode), with example commands for each scenario
Guides & tutorials for AI skills
Ralph Loop (Agent Mode) extends your AI assistant with the ability to 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. Rather than leaving your conversation to handle this manually, you can ask your Claude agent directly β and it will take care of the task end-to-end, using Ralph Loop (Agent Mode) as its underlying capability.
Ralph Loop (Agent Mode) works across Claude, Cursor, OpenClaw through the Model Context Protocol (MCP) β an open standard that lets AI clients share tools and skills without lock-in. Because MCP is platform-agnostic by design, you install Ralph Loop (Agent Mode) once and it becomes available across all your AI clients. Whether you're working in Claude for focused sessions or Cursor for integrated workflows, the skill behaves consistently.
Getting started with Ralph Loop (Agent Mode) takes about two minutes. Place the skill at `~/.claude/skills/ralph-loop-agent/` (personal, all projects) or `.claude/skills/ralph-loop-agent/` (project-specific), then restart your AI client. From that point, typing `/ralph-loop-agent` in any conversation activates it, or the AI will use it on its own when it detects a relevant request.
Ralph Loop (Agent Mode) has been installed 2,716 times, making it one of the more actively used skills in the AI Agent & Automation category. The install rate suggests it solves a real, recurring need rather than a niche edge case. The source code is open on GitHub β you can inspect it, contribute fixes, or fork it to adapt the skill for your specific setup. Like all skills on DiscoverAISkills, it is free to install and use. The broader AI skills ecosystem continues to expand as developers contribute new capabilities across categories like developer tools, data analysis, writing, automation, and more.
Place the skill folder at ~/.claude/skills/ralph-loop-agent/ for personal use (all projects), or .claude/skills/ralph-loop-agent/ for project-specific use. Restart your AI client, then invoke with /ralph-loop-agent or let the AI discover it automatically.
Ralph Loop (Agent Mode) supports Claude, Cursor, OpenClaw. It integrates seamlessly with these AI platforms to extend their capabilities.
Ralph Loop (Agent Mode) is free to install. Check the repository for licensing information.
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.
Links
Automate my ai agent & automation tasks using Ralph Loop (Agent Mode)
Identifies repetitive steps in your workflow and sets up Ralph Loop (Agent Mode) to handle them automatically
MCP vs traditional plugins: what's the difference?
Ralph Loop (Agent Mode) is categorized under AI Agent & Automation. These skills help AI agents perform specialized tasks in this domain.