explaingit

beerandcodeteam/beer-and-code-harness

Analysis updated 2026-05-18

26ShellAudience · developerComplexity · 3/5Setup · moderate

TLDR

A Claude Code plugin that turns a project idea into a phased build plan, then runs an AI agent through each phase automatically with human checkpoints.

Mindmap

mindmap
  root((bc-harness))
    What it does
      Init project chain
      Formal feature specs
      Autonomous execution
    Tech stack
      Bash
      Claude Code plugin
      Codex CLI
    Use cases
      Plan new projects
      Spec a feature
      Automate build phases
    Audience
      Developers
      AI coding teams

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Turn a rough project idea into a description, user stories, database schema, and a numbered build plan.

USE CASE 2

Convert a feature request into a formal specification and phased plan with human approval checkpoints.

USE CASE 3

Run an AI coding agent through a phased plan automatically, committing each completed phase to git.

USE CASE 4

Keep documentation of an existing codebase's architecture and conventions in sync with the actual code.

What is it built with?

ShellClaude CodeCodex CLI

How does it compare?

beerandcodeteam/beer-and-code-harnessecho-of-machines/fable-advisorroland-luo/codex-dream-skin
Stars262626
LanguageShellShellShell
Setup difficultymoderateeasyeasy
Complexity3/52/52/5
Audiencedeveloperdevelopergeneral

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

Requires Claude Code or OpenAI's Codex CLI with an API key, and a clean git repository to run ralph.sh.

In plain English

Beer and Code Harness, also called bc-harness, is an add-on plugin for Claude Code, an AI coding assistant made by Anthropic, that helps take a software project from a rough idea all the way to working code in a structured way. Instead of asking the AI to write code in one big undirected pass, it breaks the process into three separate pipelines that connect together. The first pipeline, started with the init command, walks you through describing your project, then generates user stories, a database design, and a numbered plan of build phases, asking questions along the way. The second pipeline, plan, takes a description of a specific feature and turns it into a formal specification document, an architecture aware task breakdown, and a phase by phase plan, with checkpoints where a human developer reviews and approves each step before moving on. A third command, ai-context, reads the code that has already been written and keeps a set of reference documents about it up to date, so the other two pipelines always have accurate information about the current state of the project. Once a plan of phases exists, a separate script called ralph.sh can run through it on its own. It reads each phase from the plan document and hands it to a brand new AI coding session, one phase at a time, with no person needed in between, and it commits the finished work to version control after each phase passes its checks. The tool itself does not dictate which programming language, framework, or coding conventions a project uses. Those come from the project's own documentation files, so it can be used with any tech stack. Running ralph.sh requires either OpenAI's Codex command line tool with an OpenAI API key, or Anthropic's Claude Code with an Anthropic API key, and it must be run from the root of a git repository whose working tree has no uncommitted changes.

Copy-paste prompts

Prompt 1
Walk me through running /init in bc-harness to turn my project idea into a build plan.
Prompt 2
Use /plan in bc-harness to turn this feature description into a SPEC and phased plan: <describe feature>.
Prompt 3
Explain what ralph.sh does when I point it at a PHASES.md file and how the phase gates work.
Prompt 4
Show me how /ai-context generates AGENTS.md and the docs/agents files from my existing code.

Frequently asked questions

What is beer-and-code-harness?

A Claude Code plugin that turns a project idea into a phased build plan, then runs an AI agent through each phase automatically with human checkpoints.

What language is beer-and-code-harness written in?

Mainly Shell. The stack also includes Shell, Claude Code, Codex CLI.

How hard is beer-and-code-harness to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is beer-and-code-harness for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.