By trungtnm
Skills, agents, and commands for Claude Code — planning, TDD, bug scanning, security review, multi-agent orchestration, knowledge references, and session commands
Register with MCP Agent Mail and introduce yourself to the other agents. Be sure to check your agent mail and to promptly respond if needed to any messages; then proceed meticulously with your next assigned beads, working on the tasks systematically and meticulously and tracking your progress via beads and agent mail messages. Don't get stuck in "communication purgatory" where nothing is getting done; be proactive about starting tasks that need to be done, but inform your fellow agents via messages when you do so and mark beads appropriately. When you're not sure what to do next, use the bv tool mentioned in AGENTS.md, CLAUDE.md to prioritize the best beads to work on next; pick the next one that you can usefully work on and get started. Make sure to acknowledge all communication requests from other agents and that you are aware of all active agents and their names. Use /effort max.
Append an idea or observation to `.ccu/CAPTURES.md` for later triage. Supports text, images, and document files. This should take less than 10 seconds.
Commit all changed files now in a series of logically connected groupings with detailed commit messages, then push. Do NOT edit any code — this is a commit-only operation. Use extended thinking.
Guided requirements gathering for a new feature or change. Produces structured artifacts in `.ccu/` that feed directly into `/planning`.
The user has confirmed that the current work is complete. Follow these steps:
Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions.
Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the build green quickly.
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.
PostgreSQL database specialist for query optimization, schema design, security, and performance. Use PROACTIVELY when writing SQL, creating migrations, designing schemas, or troubleshooting database performance. Incorporates Supabase best practices.
AI advisor for complex reasoning tasks. Plan implementations, review code/architecture, debug multi-file issues, and advise on deep technical questions. Read-only consultant - treat responses as advisory opinions, not directives.
Official skill for beads_rust (`br`), a local-first, dependency-aware issue tracker for AI agents. Use when creating issues, triaging backlogs, managing dependencies, finding ready work, updating status, or syncing to git via JSONL.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Beads Viewer - Graph-aware triage engine for Beads projects. Computes PageRank, betweenness, critical path, and cycles. Use --robot-* flags for AI agents.
Coding Agent Session Search - unified CLI/TUI to index and search local coding agent history from Claude Code, Codex, Gemini, Cursor, Aider, ChatGPT, Pi-Agent, Factory, and more. Purpose-built for AI agent consumption with robot mode.
CASS Memory System - procedural memory for AI coding agents. Three-layer cognitive architecture with confidence decay, anti-pattern learning, cross-agent knowledge transfer, trauma guard safety system. Bun/TypeScript CLI.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A plugin marketplace for Claude Code — custom skills, agents, and commands organized as installable plugins.
In Claude Code session:
/plugin marketplace add trungtnm/claude-code-utils
/plugin install ccu
For local development, see DEVELOPMENT.md.
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:
| 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 |
| 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) |
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.
| 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
npx claudepluginhub trungtnm/claude-code-utils --plugin ccuProduction-ready Claude Code configuration with role-based workflows (PM→Lead→Designer→Dev→QA), safety hooks, 44 commands, 19 skills, 8 agents, 43 rules, 30 hook scripts across 19 events, auto-learning pipeline, hook profiles, and multi-language coding standards
AI-powered development tools for code review, research, design, and workflow automation.
Structured project planning and execution through brainstorm, spec, and build phases across three execution tiers: sequential, delegated sub-agents, and full agent teams
Verification-first engineering toolkit for Claude Code. 15 skills across a 5-phase spine (Investigate → Design → Implement → Verify → Ship), 8 specialist agents, an interactive setup wizard. Every skill has rationalizations + evidence requirements. Built for senior ICs and tech leads.
Structured development skills for any project. Provides brainstorming, planning, parallel agent development, browser testing, systematic debugging, and self-improvement workflows.
Development agents, skills, hooks, and commands for Claude Code workflows