ralph-loop
andrelandgraf/fullstackrecipes
Automated agent-driven development loop: define features as user stories, run AI agents iteratively until all acceptance criteria pass.
What is ralph-loop?
Ralph Loop is a complete setup for automating feature development using AI agents. You define features as structured user stories with testable acceptance criteria, then run agents in a loop to implement and verify each story until all criteria pass. Use this when you want AI agents to autonomously drive development with clear, measurable progress tracking.
- Define features as JSON user stories with testable acceptance criteria
- Run AI agents in automated loops to implement features from stories
- Verify acceptance criteria and track progress across agent iterations
- Integrate with code health tools (Prettier, TypeScript, Fallow) for quality gates
- Configure AI agents (Cursor, GitHub Copilot, Claude Code) with project-specific patterns
- Log and report progress for visibility across development cycles
How to install ralph-loop
npx skills add https://github.com/andrelandgraf/fullstackrecipes --skill ralph-loop- Code Health, Linting & Formatting setup (Prettier, TypeScript, Fallow)
- AI Coding Agent Configuration (Cursor, GitHub Copilot, or Claude Code)
- User Stories Setup (structured JSON format for requirements)
How to use ralph-loop
- 1.Complete the three prerequisite recipes in order
- 2.Create user stories in JSON format with testable acceptance criteria
- 3.Configure your AI agent with project-specific patterns and coding guidelines
- 4.Run the Ralph agent loop to start automated feature implementation
- 5.Monitor acceptance criteria verification and agent progress logs
- 6.Review completed stories and iterate on next batch of features
Use cases
- Automating feature implementation when requirements are clearly defined as acceptance criteria
- Running overnight or scheduled agent loops to incrementally build features
- Tracking AI agent progress on multiple user stories with measurable completion metrics
- Ensuring code quality during automated development by enforcing linting and type-checking
- Coordinating multiple AI agents on the same codebase with consistent guidelines
- Teams using AI coding agents for autonomous development
- Projects with well-defined feature requirements and acceptance criteria
- Developers wanting to automate repetitive feature implementation
- Teams prioritizing code quality and health during AI-assisted development
ralph-loop FAQ
User stories are JSON files with testable acceptance criteria that AI agents can verify and track. See the User Stories Setup recipe for the structured format.
Ralph Loop works with Cursor, GitHub Copilot, and Claude Code. Configure them with project-specific patterns via the AI Coding Agent Configuration recipe.
The Ralph agent loop runs agents iteratively to implement features, then verifies acceptance criteria are met before marking stories as complete.
The setup integrates Prettier for formatting, TypeScript for type-checking, and Fallow for detecting dead code, duplication, complexity, and architecture drift.
Yes, but you must first complete the prerequisite recipes for code health setup and agent configuration in your project.
Full instructions (SKILL.md)
Source of truth, from andrelandgraf/fullstackrecipes.
name: ralph-loop description: Complete setup for automated agent-driven development. Define features as user stories with testable acceptance criteria, then run AI agents in a loop until all stories pass.
Ralph Loop
Complete setup for automated agent-driven development. Define features as user stories with testable acceptance criteria, then run AI agents in a loop until all stories pass.
Prerequisites
Complete these recipes first (in order):
Code Health, Linting & Formatting
Configure Prettier for formatting, TypeScript for typechecking, and Fallow for code health (dead code, duplication, complexity, architecture drift). Skips ESLint/Biome to avoid config complexity.
curl -H "Accept: text/markdown" https://fullstackrecipes.com/api/recipes/code-health-setup
AI Coding Agent Configuration
Configure AI coding agents like Cursor, GitHub Copilot, or Claude Code with project-specific patterns, coding guidelines, and MCP servers for consistent AI-assisted development.
curl -H "Accept: text/markdown" https://fullstackrecipes.com/api/recipes/agent-setup
Cookbook - Complete These Recipes in Order
User Stories Setup
Create a structured format for documenting feature requirements as user stories. JSON files with testable acceptance criteria that AI agents can verify and track.
curl -H "Accept: text/markdown" https://fullstackrecipes.com/api/recipes/user-stories-setup
Working with User Stories
Document and track feature implementation with user stories. Workflow for authoring stories, building features, and marking acceptance criteria as passing.
curl -H "Accept: text/markdown" https://fullstackrecipes.com/api/recipes/using-user-stories
Ralph Agent Loop
Set up automated agent-driven development with Ralph. Run AI agents in a loop to implement features from user stories, verify acceptance criteria, and log progress for the next agent.
curl -H "Accept: text/markdown" https://fullstackrecipes.com/api/recipes/ralph-setup
Related skills
More from andrelandgraf/fullstackrecipes and the wider catalog.
find-skills
Discover and install agent skills to extend your coding agent's capabilities on demand
frontend-design
Build visually distinctive UI with opinionated aesthetic direction, typography, and layout choices that avoid templated defaults.
vercel-react-best-practices
70 React/Next.js performance rules from Vercel Engineering, prioritized by impact for writing, reviewing, and refactoring code.
agent-browser
Fast browser automation CLI for AI agents — navigate, click, scrape, screenshot, and test via Chrome CDP
web-design-guidelines
Review UI code against Web Interface Guidelines for accessibility, UX, and design best practices
finetuning
Fine-tune models on Azure AI Foundry with SFT, DPO, or RFT training methods.