ralph-loop

Orchestrate interactive coding agent loops with TTY-safe execution and background monitoring.

Updated May 17, 2026
One-click install
npx skills add https://github.com/tiankong0101-byte/skills-registry --skill ralph-loop-tiankong0101-byte
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ralph-loop
Source: https://github.com/tiankong0101-byte/skills-registry/tree/main/skills/ralph-loop-agent
Command: npx skills add https://github.com/tiankong0101-byte/skills-registry --skill ralph-loop-tiankong0101-byte

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps OpenClaw agents run interactive coding agents reliably without hanging, especially when tools like OpenCode, Codex, Claude Code, and Goose need a real terminal session.

Core Features & Use Cases

  • TTY-safe execution: Launch interactive CLIs with exec plus process monitoring so they can run in a real terminal environment.
  • Planning and building workflows: Support separate PLANNING and BUILDING phases with PROMPT.md, AGENTS.md, specs, and IMPLEMENTATION_PLAN.md.
  • Progress monitoring and control: Poll running sessions, read logs, detect completion markers, and stop or kill sessions when needed.
  • Use Case: An agent needs to implement user authentication by first creating a plan, then iterating through implementation and testing while keeping the user updated.

Quick Start

Ask your OpenClaw agent to create a Ralph Loop for your project using your chosen coding CLI and model.

Frequently Asked Questions about ralph-loop

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run interactive coding agents like Claude Code or Codex without the terminal hanging?

To run interactive coding agents without hanging, you need TTY-safe execution that launches CLIs via exec with background process monitoring. This approach provides a real terminal environment, preventing sessions from freezing while polling for completion markers.

What is a TTY-safe loop for automating coding agent workflows?

A TTY-safe loop is an orchestration mechanism that manages interactive CLI sessions using pseudo-terminals. It ensures coding agents like Goose or OpenCode execute reliably in the background, allowing you to poll logs and detect completion sentinels.

Do I need specific workflow files to automate software building with coding agents?

Yes, automating software building requires workflow files such as PROMPT.md, AGENTS.md, and IMPLEMENTATION_PLAN.md. These files separate the planning and building phases, allowing the agent to iterate through implementation and testing systematically.

Can I monitor progress and stop background coding agent sessions on demand?

Yes, you can monitor progress and stop background coding agent sessions on demand. The orchestration loop supports polling running sessions, reading logs, detecting completion markers, and issuing stop or kill commands when the task is finished or needs intervention.

What environment setup is required to orchestrate interactive CLI agents?

Orchestrating interactive CLI agents requires an environment with exec and process tool support, along with pty-enabled terminal sessions. This setup is necessary to launch real terminal environments that prevent interactive coding agents from hanging.

Why does my coding agent hang when launched in an automated workflow?

Your coding agent hangs because it requires a real TTY terminal session but is launched without proper pseudo-terminal allocation. Using TTY-safe execution with process monitoring ensures the agent receives the terminal environment it needs to run interactively.