ralph-runner

Runs autonomous AI agents to implement PRD stories and track progress.

Updated Aug 27, 2026

Search Tags:#automation #AI agents #coding #CI #autonomous #PRD-driven

Ready to run

npx skills add https://github.com/Acurioustractor/empathy-ledger-v2 --skill ralph-runner

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ralph-runner
Source: https://github.com/Acurioustractor/empathy-ledger-v2/tree/main/.claude/skills/local/ralph-runner
Command: npx skills add https://github.com/Acurioustractor/empathy-ledger-v2 --skill ralph-runner

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates coding tasks by running autonomous AI agents that ship code.

Core Features & Use Cases

Autonomous tasking: Agents read a PRD and implement stories one by one.
CI-aligned workflow: Runs build and lint to keep CI green.
PRD-driven progress: Updates PRD and logs progress as tasks complete.

Quick Start

Run the Ralph Runner to kick off the agent workflow with the current PRD. Use the scripts/ralph/ralph.sh script for default behavior. To use a custom PRD, run ./scripts/ralph/ralph.sh scripts/ralph/my-feature.json. Monitor progress with tail -f scripts/ralph/progress.txt.

Frequently Asked Questions about ralph-runner

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

FAQPage Schema

How do I automate coding tasks with autonomous AI agents from a PRD?▼

Running autonomous AI agents requires a local runner setup with scripts/ralph/ralph.sh, a PRD JSON file under scripts/ralph, and a progress log to coordinate task execution and track ongoing development status.

How do I start an autonomous AI coding workflow using a PRD JSON file?▼

Execute ./scripts/ralph/ralph.sh with a custom PRD JSON file path like scripts/ralph/my-feature.json. The runner reads the PRD, prioritizes incomplete stories, and implements them sequentially to ship code autonomously.

Does the autonomous coding agent run build and lint checks to keep CI green?▼

The workflow aligns with CI by running build and lint checks during autonomous tasking. This keeps continuous integration green while agents read the PRD and implement stories one by one without breaking existing pipelines.

Can I monitor autonomous AI agent progress while it ships code overnight?▼

Yes, monitor autonomous agent progress by running tail -f scripts/ralph/progress.txt. The runner updates this progress log as it completes stories from the PRD backlog, allowing real-time tracking of overnight coding tasks.

What do I need to set up before running PRD-driven autonomous coding agents?▼