Joncik91/ucai

27 stars · Last commit 2026-05-04

A Claude Code plugin that solves the same problems as community frameworks (GSD, BMAD, Ralph, Agent OS) — but using the tool's native architecture instead of fighting it.

README preview

<div align="center">

<img src="docs/logo.png" alt="Ucai" width="160" height="160">

# Ucai — Use Claude Code As Is

[![Claude Code v2.1+](https://img.shields.io/badge/Claude%20Code-v2.1%2B-E8954A)](https://docs.claude.com/en/docs/claude-code/overview)
[![Node.js 18+](https://img.shields.io/badge/node-18%2B-339933?logo=node.js&logoColor=white)](https://nodejs.org/)
[![License: MIT](https://img.shields.io/badge/license-MIT-E8954A.svg)](LICENSE)
[![Version: 2.3](https://img.shields.io/badge/version-2.3-E8954A)](CHANGELOG.md)
[![GitHub stars](https://img.shields.io/github/stars/Joncik91/ucai?color=E8954A&logo=github)](https://github.com/Joncik91/ucai/stargazers)
[![Marketplace install](https://img.shields.io/badge/install-marketplace-E8954A)](#install-marketplace)
[![Zero deps](https://img.shields.io/badge/zero%20deps-✓-E8954A)]()

A Claude Code plugin that solves the same problems as GSD, BMAD, Ralph, and Agent OS — but using Claude Code's native architecture instead of fighting it. v2.3 adds discipline layers on top of v2.2's programmatic enforcement: pre-flight requirement audits before any code is written, per-issue failure-mode analysis in every review, and strict author/reviewer separation for tests with anti-gaming verdicts aligned with the [Pragma](https://github.com/Joncik91/pragma) detector.

</div>

Ucai was built from the inside out.
We read the source code. We studied how Anthropic builds their own plugins.

View full repository on GitHub →