Enforced Discipline
for AI Coding Agents

Hard gates, TDD, security scanning, and human approval — so your AI agent ships production-quality code, not untested prototypes.

Get Started How It Works
77 Skills17 Agents7-Phase WorkflowMIT Licensed

Why MeowKit

The harness
is the product

Models provide intelligence. MeowKit provides the constraints, safety gates, and repeatable workflows that production engineering demands.

Two Hard Gates

No code ships without an approved plan and a passing review. Every change must clear both stops — no bypasses, no self-approval.

TDD Opt-In

Strict test-first discipline when enabled, fast spikes when you need speed. The harness adapts without relaxing quality standards.

4-Layer Security

Prompt injection defense across input, instruction, context, and output layers. Untrusted content is data — never instructions.

Process

The 7-Phase
Workflow

Every task follows the same enforced sequence — orient, plan, test, build, review, ship, reflect. Two hard gates block shipping unreviewed or untested code.

01

Orient

Detect task domain, classify complexity, assign model tier and agents.

02

Plan

GATE

Scope-adaptive plan with acceptance criteria. No code until the plan is approved.

03

Test

Write failing tests first when TDD is enabled. Correctness proof before implementation.

04

Build

Implement against the approved plan and passing tests. File ownership enforced.

05

Review

GATE

Adversarial structural audit across 5 dimensions. Security scan for BLOCK patterns.

06

Ship

PR creation, conventional commit, deploy pipeline. Only after Gate 2 clears.

07

Reflect

Capture lessons, update memory files, run retrospective. Knowledge persists.

See the difference

Before
# No plan, no gates, no tests
claude "add user auth to the API"

# AI ships code directly:
✗ No approved spec
✗ No failing tests first
✗ No security scan
✗ No review gate
→ untested code in production
With MeowKit
# Enforced 7-phase workflow
npx meowkit "add user auth"

# Harness enforces:
✓ Plan approved at Gate 1
✓ Tests written first (TDD)
✓ Security scan — no BLOCKs
✓ Review passed at Gate 2
→ production-quality PR

Capabilities

Everything the harness
enforces for you

17 Specialist Agents

Dedicated agents for planning, security, review, testing, documentation, and more — each with scoped file ownership and model-tier routing.

77 Domain Skills

From database migrations to multimodal AI, frontend design to CTF research — skills activate only when the task demands them.

Cross-Session Memory

Lessons, fixes, review patterns, and architecture decisions persist across sessions. The harness learns from every run.

Scale-Adaptive Intelligence

Domain complexity CSV classifies every task into TRIVIAL, STANDARD, or COMPLEX — routing the right model and scaffolding density automatically.

Party Mode

Multi-agent deliberation for architectural decisions. Multiple agents argue different positions before a decision is made.

Adversarial Review

Gate 2 runs parallel reviewers across correctness, security, design, scope, and craft. Any FAIL blocks the ship.

Zero External Dependencies

Pure prompt engineering — no SDK required. Works offline, works in any Claude Code environment, no vendor lock-in.

TDD Pipeline

Opt-in test-first enforcement with RED → GREEN → REFACTOR gates. Self-healing loop with 3-attempt cap and human escalation.

By the numbers

Built for scale,
measured in precision

77Skills
17Agents
21Commands
7Modes
19Rules
27Hooks
Zero External Dependencies MIT License Works Offline SSR Compatible

Quick Start

One command to
enforce discipline

npx meowkit init
  1. 01

    Install

    npx meowkit init

    Scaffolds the harness into your project.

  2. 02

    Configure

    npx meowkit setup

    Choose your workflow modes and agents.

  3. 03

    Run

    /mk:cook "add feature X"

    The 7-phase pipeline enforces the rest.

Ship better. Now.

Ready to ship
production-quality AI code?

The harness is free, open-source, and works inside Claude Code today. No sign-up. No external dependencies. Just discipline.

Get Started Free
Documentation ↗GitHub ↗