ucai-marketplace

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. v2.0 adds autonomous execution: give a spec, get a PR.

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.

🥊 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.

Problem	Framework Approach	Ucai (Native) Approach
Context rot	Bash wrappers spawning fresh sessions	Task tool already gives fresh context per agent
No structure	Persona prompts + ceremonies	Commands with phased workflows + parallel agents
No guardrails	CLAUDE.md rules (hope-based)	PreToolUse hooks (deterministic)
No iteration	External bash loops	Stop hooks (native, built-in)
No automation	Manual build → test → fix → PR	Zero-gate /ship pipeline: spec → PR autonomously
No formatting	Hope-based or CI-only	PostToolUse hook auto-formats every write
No planning	Manual PRD/FRD docs or skipped entirely	/plan with discovery agents + structured file output
No onboarding	Template CLAUDE.md dumps	Agent-powered codebase analysis
No learning	Same mistakes every session	Self-improvement loop — tasks/lessons.md persists corrections across sessions
No task tracking	Manual or forgotten	Persistent tasks/todo.md — hooks inject active task into every prompt

✨ 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, elegance checkpoints, and staff engineer self-checks
• Persistent task tracking (tasks/todo.md) and self-improvement loop (tasks/lessons.md)
• Automated test writing (TDD) integrated into build and debug workflows
• Native autonomous iteration (/ucai:iterate)
• Multi-agent code review with lessons-aware pattern detection
• Structured debugging with single approval gate and autonomous execution
• Documentation generation with gotcha extraction from lessons
• Release automation
• Autonomous spec-to-PR pipeline (/ship) — zero approval gates, worktree isolation, auto-test, auto-fix, auto-PR
• Infrastructure scaffolding (/bootstrap) — scaffold tests, linting, and CI for projects that lack them
• PostToolUse auto-formatting — every file write runs through your project's formatter
• Lessons consolidation — automatic cleanup when corrections exceed 100 entries
• Hook lifecycle coverage — session context injection, task/lessons awareness, config guardrails, subagent quality gates, and iterate/ship state preservation across compaction
• Built-in skills (backend, frontend, QA, DevOps, architecture, code review, and more)

All using native Claude Code commands, agents, hooks, and skills.

⚡ Quickstart

Requirements

Claude Code v2.1.0+. Check with:

claude --version

Install (Marketplace)

Inside an interactive Claude Code session:

/plugin marketplace add Joncik91/ucai
/plugin install ucai-plugin@ucai-marketplace

This installs Ucai globally — available in every project and every session.

Development / Local Testing

claude --plugin-dir ./ucai

🧪 Verify Installation

All commands are namespaced under ucai::

/ucai:init
/ucai:plan
/ucai:build
/ucai:ship
/ucai:bootstrap
/ucai:debug
/ucai:docs
/ucai:release
/ucai:iterate
/ucai:review
/ucai:cancel-iterate

Run /help to see them listed.

🧩 Commands