Ucai

Ucai — Use Claude Code As Is

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 detector.

Ucai was built from the inside out.
We read the source code. We studied how Anthropic builds their own plugins.
Every component maps 1:1 to a native Claude Code system — no wrappers, no personas, no bash loops.
v2.2 extends this with the never-forget engine — a programmatic enforcement layer that makes phase skipping impossible.

Table of Contents

- Frameworks vs. Ucai
- What Ucai Gives You
- Quickstart
- Verify Installation
- Commands
- Hook Lifecycle
- Principles
- Security
- Support the Project

🥊 Frameworks vs. Ucai — What's Actually Different?

Community frameworks were built from the outside in — wrapping Claude Code in bash scripts, mega-prompts, and persona engineering.

Ucai is built from the inside out — using Claude Code's native systems exactly as Anthropic designed them.

✨ What Ucai Gives You

- Project planning with discovery agents
- Feature-level FRDs with milestone breakdown (each milestone = one fresh context window)
- 8-phase build workflow with parallel agents, pre-flight requirement audits, elegance checkpoints, and staff engineer self-checks
- Persistent task tracking (tasks/todo.md) and self-improvement loop (tasks/lessons.md)
- Test author/reviewer separation: tests are written by a subagent (not the implementing agent) and reviewed by a different agent against 10 anti-gaming…