Claude Kit

The development-workflow plugin for Claude Code. 35 skills across a 6-phase workflow, 24 agents, 7 modes — install as a plugin and go. Free forever.

Get Started View on GitHub

Ship Faster. For Free.

Claude Kit transforms Claude Code into a production-ready AI development team. Pre-built skills, specialized agents, and intelligent modes — all open source.

35 Skills

A 6-phase workflow spine (Think → Review → Build → Ship → Maintain → Setup). 13 user-invocable spine skills plus 22 supporting skills that auto-trigger by context.

24 Agents

Specialized subagents for code review, testing, database design, security auditing, UI/UX, plan review, and more — each with focused expertise.

7 Modes

Switch between brainstorm, implementation, review, deep research, and more. Each mode optimizes Claude’s behavior for your task.

MCP Servers

Real-time docs via Context7, persistent memory, browser testing, and structured reasoning via Model Context Protocol.

Quick Start

Get up and running in under 2 minutes:

# Add the marketplace
/plugin marketplace add duthaho/claudekit-marketplace

# Install the plugin
/plugin install claudekit

# Configure your project (optional)
/claudekit:init

Skills trigger automatically based on what you’re doing. Ask Claude to brainstorm a feature, write a plan, debug an error, or review code — the right skills activate without any commands needed.

Why Claude Kit?

The Problem

Working with Claude Code is powerful, but raw Claude has limitations:

Context Spirals — Token budgets run out, context gets lost mid-task
Inconsistent Output — Quality varies between sessions
No Structure — Every session starts from scratch
Missing Expertise — Claude doesn’t know your team’s patterns and standards

The Solution

Claude Kit provides the structure, patterns, and automation that makes Claude Code production-ready:

Auto-Triggered Skills

Say “fix this bug” and the systematic-debugging skill activates. Say “plan this feature” and brainstorming + writing-plans kick in. No commands to memorize.

Specialized Agents

Delegate code review, security audits, testing, and documentation to focused subagents that work in parallel.

Consistent Quality

Built-in TDD enforcement, verification before completion, and code review workflows ensure every output meets your standards.

Fully Customizable

Add your own skills, agents, and modes. Claude Kit is a template, not a black box.

How It Works

Claude Kit uses three layers that work together:

Skills 35 skills organized around a 6-phase workflow. 13 spine skills user-invocable as /claudekit:, plus supporting skills that auto-trigger behind the scenes.

Agents 24 specialized subagents you can dispatch for focused tasks: code review, testing, database design, security audits, plan review, and more.

Modes 7 behavioral configurations that change how Claude communicates and solves problems: brainstorm, implementation, review, and more.

MCP Servers Optional integrations for real-time library docs, persistent memory, browser automation, and structured reasoning.

Development Workflows

Claude Kit connects skills and agents into complete workflows:

Workflow	What Happens
Planning & Building	Brainstorm requirements, write implementation plans, execute with subagents
Testing & Debugging	TDD enforcement, systematic debugging, root cause tracing, verification
Reviewing & Shipping	Code review, git workflows, PR creation, changelog generation

Explore workflows →

Ready to Ship Faster?

Installation Guide Step-by-step setup for your project

Skills Reference All 35 skills organized by workflow phase

Agents Reference All 24 specialized subagents

Customization Create your own skills, agents, and modes