Introduction

MeowKit is an AI agent toolkit for Claude Code that gives your coding assistant enforced discipline — hard gates, TDD, security scanning, and human approval — so it ships production-quality code instead of untested prototypes.

What problem does MeowKit solve?

AI coding tools are powerful but undirected. Without structure, they skip tests, ignore security, and ship untested code. A single "implement this feature" prompt can produce code that compiles but has no tests, no review, and secrets hardcoded in source.

MeowKit fixes this by installing a .claude/ directory that Claude Code reads automatically. It contains 13 specialist agents, 42 skills, lifecycle hooks, security rules, and a memory system that together enforce a structured development workflow.

How it works

When you start a Claude Code session in a MeowKit project, the toolkit automatically:

1. Routes your task to the right agent based on complexity (orchestrator)
2. Creates a plan before any code is written (planner, Gate 1)
3. Writes failing tests first before implementation (tester, TDD enforcement)
4. Implements with discipline — builds until tests pass (developer)
5. Reviews across 5 dimensions — architecture, types, tests, security, performance (reviewer, Gate 2)
6. Ships safely — conventional commits, PR, CI verification, rollback docs (shipper)
7. Learns from the session — captures patterns and lessons for next time (analyst)

No step can be skipped. Two hard gates (plan approval + review approval) require explicit human sign-off.

How it differs from raw Claude Code

Concern	Raw Claude Code	With MeowKit
Planning	Starts coding immediately	Creates and gets approval for a plan first
Testing	Tests optional, often skipped	TDD enforced — failing test before implementation
Security	Relies on model knowledge	4-layer defense + security agent + post-write hooks
Review	Ask "review this" and hope	5-dimension structural audit with written verdict
Shipping	"git add -A && git push"	Conventional commits, PR, CI verification, rollback docs
Memory	Forgets everything between sessions	Persists lessons, patterns, and costs

Architecture at a glance

.claude/
├── agents/          13 specialist agents
├── skills/          42 skills with meow: namespace
├── hooks/           Lifecycle hooks (security scan, TDD gate)
├── rules/           12 enforcement rules (security, injection, TDD)
├── scripts/         6 Python validators (stdlib only)
├── memory/          Cross-session persistence
└── settings.json    Hook registrations + permissions

CLAUDE.md            Entry point — Claude reads this at session start

Next steps

• Why MeowKit — the philosophy behind enforced discipline
• Installation — get MeowKit running in 2 minutes
• Quick Start — your first task with MeowKit in 5 minutes