<p align="center"> <img src="assets/hero-banner.png" alt="Tank — Security-first package manager for AI agent skills" width="100%" /> </p>

<p align="center"> <img src="assets/logo.png" alt="Tank logo" width="120" /> </p>

<h1 align="center">Tank</h1>

<p align="center"> Security-first package manager for AI agent skills. <br /> <em>"I know Kung Fu." — but verified, locked, and scanned.</em> </p>

<p align="center"> <a href="https://github.com/tankpkg/tank/stargazers"><img src="https://img.shields.io/github/stars/tankpkg/tank?style=flat&color=22c55e" alt="GitHub Stars"></a> <a href="https://github.com/tankpkg/tank/blob/main/LICENSE"><img src="https://img.shields.io/github/license/tankpkg/tank?color=3b82f6" alt="License"></a> <a href="https://www.npmjs.com/package/@tankpkg/cli"><img src="https://img.shields.io/npm/v/@tankpkg/cli?color=22c55e&label=cli" alt="npm"></a> <a href="https://github.com/tankpkg/tank/actions"><img src="https://img.shields.io/github/actions/workflow/status/tankpkg/tank/ci.yml?branch=main&label=CI" alt="CI"></a> </p>

---

## The Problem

AI coding agents (Claude Code, Codex, Cursor) can be extended with **skills** — reusable packages that teach agents how to perform tasks. The ecosystem is growing fast: 110,000+ installs in 4 days on one registry alone.

But today's skill registries have **no versioning, no lockfiles, no permissions, and no security scanning**. In February 2026, the ClawHavoc incident revealed that 341 malicious skills (12% of a major marketplace) were distributing credential-stealing malware.

Agent skills are more dangerous than npm packages because they execute with the **agent's full authority** — reading files, making API calls, running shell commands. The attack surface is fundamentally larger.

## What Tank Does

Tank is the **npm for agent skills**, with security built into the foundation:

| Feature | npm (2012) | Current Registries | Tank | | ------