ccu

Claude Code Utils

A plugin marketplace for Claude Code — custom skills, agents, and commands organized as installable plugins.

Install

In Claude Code session:

/plugin marketplace add trungtnm/claude-code-utils
/plugin install ccu

For local development, see DEVELOPMENT.md.

Why

Claude Code is powerful out of the box, but teams hit the same gaps repeatedly: no enforced TDD, no structured planning pipeline, no quality gates before commits, no multi-agent coordination. This plugin fills those gaps with opinionated, composable building blocks — each one a distilled workflow you'd otherwise hand-write into CLAUDE.md files across every project.

Who benefits:

• Solo developers — get code review, security scanning, and bug detection without a second pair of eyes
• Teams using Claude Code — standardize on shared coding standards, planning processes, and quality gates
• Multi-agent workflows — coordinate parallel workers on large features via the orchestrator + beads system

Skills

Skill	Description
/planning	Feature planning and execution plan generation
/brainstorming	Idea-to-design process, hard-gates implementation
/test-driven-development	Write-tests-first methodology
/ubs	Ultimate Bug Scanner: 18 detection categories, 8 languages
/dcg	Destructive Command Guard: blocks dangerous commands
/security-review	Security checklist for auth, input, secrets, APIs
/qa-sweep	Three-phase quality sweep (inspect, review, polish)
/coding-standards	TypeScript/JavaScript/React/Node.js standards
/orchestrator	Spawn and monitor parallel workers (haiku coordinator)
/file-beads	File detailed Beads epics and issues from a plan
/review-beads	Review and refine filed Beads issues
/docs-seeker	Discover docs via llms.txt, Repomix, parallel exploration
/context-engineering	AI agent architecture and memory system patterns
/frontend-patterns	React, Next.js, state management patterns
/backend-patterns	Node.js, Express, Next.js API route patterns
/vercel-react-best-practices	Vercel Engineering optimization guidelines
/web-design-guidelines	Web Interface Guidelines compliance review
/design-md	Semantic design system synthesis
/reactcomponents	Vite/React component generation from designs
/stitch-loop	Iterative website building with Stitch
/writing-skills	Create, edit, and verify skills
/using-skills	Skill discovery and usage conventions
/cass	Coding Agent Session Search across multiple agents
/cm	CASS Memory: procedural memory with confidence decay
/br	Beads Rust issue tracker: create, triage, dependencies, sync
/bv	Beads Viewer: graph-aware triage engine with PageRank and critical path
/bd-to-br-migration	Beads migration utilities

Agents

Agent	Description
TDD Guide	Test-driven development enforcement
Code Reviewer	Quality, security, maintainability review
Security Reviewer	OWASP Top 10, secrets, injection detection
Worker	Bead implementation agent (opus, TDD-first)
Oracle	Advisory consultant for complex reasoning (read-only)
Architect	System design and scalability decisions
Database Reviewer	PostgreSQL optimization, Supabase practices
Build Error Resolver	TypeScript/build error fixes (minimal diffs)

Commands

Session commands (t: prefix) are single-purpose instruction scripts that drive specific workflow phases. They accept optional $ARGUMENTS to scope their work — without arguments they fall back to a broad sweep.

Orientation & Planning

Command	Purpose
t:prime	Deep-read all project docs and fully orient before acting
t:top-ideas	Generate the 10 most impactful feature ideas
t:opinion	Get an honest, critical assessment of the project

# New to a codebase? Orient first, then immediately start the agent auto
/t:prime /t:auto

# Orient, then review the DEVELOPMENT.md for improvements
/t:prime review @DEVELOPMENT.md and suggest improvements

# Brainstorm features — run 3+ times and the best ideas compound
/t:top-ideas
/t:top-ideas focus on developer experience

# Sanity-check your project direction before investing more time
/t:opinion

Implementation & Review