garrytan/gstack

Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

What it solves

gstack provides a structured, role-based framework for AI agents to act as a complete engineering team. It addresses the challenge of using AI for complex software development by moving beyond simple prompting to a system that enforces rigorous planning, security auditing, quality assurance, and release management.

How it works

gstack installs a suite of specialized skills (slash commands) into AI agent environments like Claude Code, OpenClaw, and others. These commands act as virtual specialists—such as a CEO, security officer, or QA lead—that guide the AI through specific development phases. It uses a "team mode" to ensure consistent tooling across shared repositories and supports automated workflows like security audits, architectural reviews, and end-to-end testing.

Who it’s for

  • Founders and technical CEOs who want to maintain high shipping velocity.
  • Tech leads and staff engineers looking to enforce rigorous review and QA standards.
  • Developers using AI agents who want to move from unstructured prompting to a repeatable, professional development methodology.

Highlights

  • Role-based specialization: Includes dedicated commands for product strategy, architectural review, security auditing (OWASP/STRIDE), and QA.
  • Agent-agnostic: Compatible with Claude Code, OpenClaw, Cursor, GitHub Copilot CLI, and several other AI development tools.
  • Team-ready: Supports shared repository configurations to ensure all contributors use the same AI-assisted workflows.
  • Production-focused: Built to handle the entire lifecycle from initial product interrogation to final code shipping.

Related

  • Project
    rsmdt/the-startup

    The Agentic Startup is a multi-agent AI framework for Claude Code that enforces spec-driven development: you create detailed requirements and plans, then a team of specialized agents builds, tests, reviews, and documents your code with quality gates and parallel execution. It solves the problems of unclear requirements, context limits, and inconsistent code quality.

  • Project
    levnikolaevich/claude-code-skills

    A collection of standalone agent skills and plugins for Claude Code and OpenAI Codex that provide structured, professional engineering workflows across the entire software development lifecycle.

  • Project
    addyosmani/agent-skills

    Agent Skills is a collection of 25 production-grade workflow skills that AI coding agents can install and follow. They encode senior engineering practices like spec-first development, test-driven development, and code review into structured, verifiable workflows, helping agents consistently deliver higher-quality code.

  • Project
    ericlitman/open-pstack

    A plugin for Claude Code and Codex that implements a rigorous engineering framework for coding agents, emphasizing verification, multi-model review, and structured workflows.

  • Project
    alirezarezvani/claude-skills

    A comprehensive library of 398 modular skills and plugins that extend AI coding agents with domain-specific expertise in engineering, business, and compliance across 13 different platforms.