garrytan / gstack

“I don’t think I’ve typed like a line of code probably since December, basically, which is an extremely large change.” — Andrej Karpathy, No Priors podcast, March 2026 “我基本上从去年十二月起就没怎么写过代码了，这真是一个巨大的转变。”—— Andrej Karpathy，《No Priors》播客，2026 年 3 月

When I heard Karpathy say this, I wanted to find out how. How does one person ship like a team of twenty? Peter Steinberger built OpenClaw — 247K GitHub stars — essentially solo with AI agents. The revolution is here. A single builder with the right tooling can move faster than a traditional team. 当我听到 Karpathy 这么说时，我很想一探究竟。一个人如何能像二十人的团队一样交付产品？Peter Steinberger 仅凭 AI 智能体就独自构建了 OpenClaw（GitHub 24.7 万星标）。革命已经到来。拥有正确工具的独立开发者，其行动速度可以超越传统团队。

I’m Garry Tan, President & CEO of Y Combinator. I’ve worked with thousands of startups — Coinbase, Instacart, Rippling — when they were one or two people in a garage. Before YC, I was one of the first eng/PM/designers at Palantir, cofounded Posterous (sold to Twitter), and built Bookface, YC’s internal social network. 我是 Garry Tan，Y Combinator 的总裁兼 CEO。我曾与数千家初创公司合作过——包括 Coinbase、Instacart 和 Rippling——那时他们还只是车库里的那一两个人。在加入 YC 之前，我是 Palantir 最早的工程师/产品经理/设计师之一，联合创立了 Posterous（后被 Twitter 收购），并构建了 YC 的内部社交网络 Bookface。

gstack is my answer. I’ve been building products for twenty years, and right now I’m shipping more products than I ever have. In the last 60 days: 3 production services, 40+ shipped features, part-time, while running YC full-time. gstack 就是我的答案。我从事产品开发已经二十年了，而现在我交付产品的速度比以往任何时候都要快。在过去 60 天里：我以兼职身份，在全职管理 YC 的同时，上线了 3 个生产级服务，交付了 40 多个功能。

On logical code change — not raw LOC, which AI inflates — my 2026 run rate is ~810× my 2013 pace (11,417 vs 14 logical lines/day). Year-to-date (through April 18), 2026 has already produced 240× the entire 2013 year. Measured across 40 public + private garrytan/* repos including Bookface, after excluding one demo repo. AI wrote most of it. 从逻辑代码变更量来看（而非 AI 会导致虚高的原始代码行数），我 2026 年的产出率约为 2013 年的 810 倍（每天 11,417 行逻辑代码 vs 14 行）。截至 4 月 18 日，2026 年的产出已达到 2013 全年的 240 倍。该数据统计涵盖了包括 Bookface 在内的 40 个 garrytan/* 公开及私有仓库（已排除一个演示仓库）。其中大部分代码由 AI 编写。

The point isn’t who typed it, it’s what shipped. The LOC critics aren’t wrong that raw line counts inflate with AI. They are wrong that normalized-for-inflation, I’m less productive. I’m more productive, by a lot. Full methodology, caveats, and reproduction script: On the LOC Controversy. 重点不在于谁敲下的代码，而在于交付了什么。批评代码行数（LOC）的人并没有错，AI 确实会导致原始行数虚高。但他们错在认为在剔除虚高因素后我的生产力下降了。事实是，我的生产力大幅提升了。完整的方法论、注意事项及复现脚本请见：On the LOC Controversy。

2026 — 1,237 contributions and counting: 2013 — when I built Bookface at YC (772 contributions): Same person. Different era. The difference is the tooling. 2026 年——1,237 次贡献且仍在增加；2013 年——我在 YC 构建 Bookface 时（772 次贡献）：同一个人，不同的时代。区别就在于工具。

gstack is how I do it. It turns Claude Code into a virtual engineering team — a CEO who rethinks the product, an eng manager who locks architecture, a designer who catches AI slop, a reviewer who finds production bugs, a QA lead who opens a real browser, a security officer who runs OWASP + STRIDE audits, and a release engineer who ships the PR. gstack 就是我实现这一切的方式。它将 Claude Code 变成了一支虚拟工程团队——包括重新思考产品的 CEO、锁定架构的工程经理、捕捉 AI 错误的设计师、发现生产环境 Bug 的审查员、打开真实浏览器进行测试的 QA 主管、运行 OWASP + STRIDE 审计的安全官，以及负责发布 PR 的发布工程师。

Twenty-three specialists and eight power tools, all slash commands, all Markdown, all free, MIT license. This is my open source software factory. I use it every day. I’m sharing it because these tools should be available to everyone. Fork it. Improve it. Make it yours. And if you want to hate on free open source software — you’re welcome to, but I’d rather you just try it first. 二十三个专家角色和八个强力工具，全部通过斜杠命令调用，全部基于 Markdown，完全免费，采用 MIT 许可证。这就是我的开源软件工厂。我每天都在使用它。我分享它是为了让每个人都能用上这些工具。Fork 它，改进它，让它成为你的工具。如果你想抨击免费开源软件，请便，但我更希望你先试用一下。

Who this is for:

适用人群：

Founders and CEOs — especially technical ones who still want to ship
创始人与 CEO —— 特别是那些仍想亲自交付产品的技术型领导者
First-time Claude Code users — structured roles instead of a blank prompt
Claude Code 初次使用者 —— 提供结构化角色，而非面对空白提示词
Tech leads and staff engineers — rigorous review, QA, and release automation on every PR
技术主管与资深工程师 —— 为每个 PR 提供严格的审查、QA 和发布自动化

Quick start

快速开始

Install gstack (30 seconds — see below)
安装 gstack（30 秒，见下文）
Run /office-hours — describe what you’re building
运行 /office-hours —— 描述你正在构建的内容
Run /plan-ceo-review on any feature idea
对任何功能构思运行 /plan-ceo-review
Run /review on any branch with changes
对任何有变更的分支运行 /review
Run /qa on your staging URL
在你的测试环境 URL 上运行 /qa

Stop there. You’ll know if this is for you. 到此为止。你就会知道这是否适合你了。

Install — 30 seconds

安装 —— 30 秒

Requirements: Claude Code, Git, Bun v1.0+, Node.js (Windows only) 要求： Claude Code, Git, Bun v1.0+, Node.js (仅限 Windows)

Step 1: Install on your machine 第一步：在你的机器上安装 Open Claude Code and paste this. Claude does the rest. 打开 Claude Code 并粘贴以下内容。剩下的交给 Claude。

# Install gstack:
run git clone --single-branch --depth 1 https://github.com/garrytan/gstack.git ~/.claude/skills/gstack && cd ~/.claude/skills/gstack && ./setup

then add a “gstack” section to CLAUDE.md that says to use the /browse skill from gstack for all web browsing, never use mcp__claude-in-chrome__* tools, and lists the available skills: /office-hours, /plan-ceo-review, /plan-eng-review, /plan-design-review, /design-consultation, /design-shotgun, /design-html, /review, /ship, /land-and-deploy, /canary, /benchmark, /browse, /connect-chrome, /qa, /qa-only, /design-review, /setup-browser-cookies, /setup-deploy, /setup-gbrain, /retro, /investigate, /document-release, /document-generate, /codex, /cso, /autoplan, /plan-devex-review, /devex-review, /careful, /freeze, /guard, /unfreeze, /gstack-upgrade, /learn. 然后，在 CLAUDE.md 中添加一个 “gstack” 部分，说明所有网页浏览均使用 gstack 的 /browse 技能，严禁使用 mcp__claude-in-chrome__* 工具，并列出可用技能：/office-hours, /plan-ceo-review, /plan-eng-review, /plan-design-review, /design-consultation, /design-shotgun, /design-html, /review, /ship, /land-and-deploy, /canary, /benchmark, /browse, /connect-chrome, /qa, /qa-only, /design-review, /setup-browser-cookies, /setup-deploy, /setup-gbrain, /retro, /investigate, /document-release, /document-generate, /codex, /cso, /autoplan, /plan-devex-review, /devex-review, /careful, /freeze, /guard, /unfreeze, /gstack-upgrade, /learn。

Then ask the user if they also want to add gstack to the current project so teammates get it. 然后询问用户是否也想将 gstack 添加到当前项目中，以便团队成员也能使用。

Step 2: Team mode — auto-update for shared repos (recommended) 第二步：团队模式 —— 共享仓库自动更新（推荐） From inside your repo, paste this. Switches you to team mode, bootstraps the repo so teammates get gstack automatically, and commits the change: 在你的仓库内粘贴以下内容。这将切换到团队模式，引导仓库配置，使团队成员自动获得 gstack，并提交更改：

(cd ~/.claude/skills/gstack && ./setup --team) && ~/.claude/skills/gstack/bin/gstack-team-init required && git add .claude/ CLAUDE.md && git commit -m "require gstack for AI-assisted work"

No vendored files in your repo, no version drift, no manual upgrades. Every Claude Code session starts with a fast auto-update check (throttled to once/hour, network-failure-safe, completely silent). Swap required for optional if you’d rather nudge teammates than block them. 仓库中无需包含第三方文件，没有版本偏差，无需手动升级。每个 Claude Code 会话都会进行快速自动更新检查（限制为每小时一次，具备网络故障安全机制，完全静默）。如果你不想强制团队成员使用，只需将 required 改为 optional。

OpenClaw

OpenClaw spawns Claude Code sessions via ACP, so every gstack skill just works when Claude Code has gstack installed. Paste this to your OpenClaw agent: OpenClaw 通过 ACP 启动 Claude Code 会话，因此只要 Claude Code 安装了 gstack，所有 gstack 技能都能直接使用。将以下内容粘贴给你的 OpenClaw 智能体：

Install gstack: run git clone --single-branch --depth 1 https://github.com/garrytan/gstack.git ~/.claude/skills/gstack && cd ~/.claude/skills/gstack && ./setup to install gstack for Claude Code.

Then add a “Coding Tasks” section to AGENTS.md that says: when spawning Claude Code sessions for coding work, tell the session to use gstack skills. Include these examples — security audit: “Load gstack. Run /cso”, code review: “Load gstack. Run /review”, QA test a URL: “Load gstack. Run /qa https://…”, build a feature end-to-end: “Load gstack. Run /autoplan, implement the plan, then run /ship”, plan before building: “Load gstack. Run /office-hours then /autoplan. Save the plan, don’t implement.” 然后，在 AGENTS.md 中添加一个 “Coding Tasks” 部分，说明：当为编码工作启动 Claude Code 会话时，告知会话使用 gstack 技能。包含以下示例——安全审计：“Load gstack. Run /cso”，代码审查：“Load gstack. Run /review”，QA 测试 URL：“Load gstack. Run /qa https://…”，端到端构建功能：“Load gstack. Run /autoplan, implement the plan, then run /ship”，构建前规划：“Load gstack. Run /office-hours then /autoplan. Save the plan, don’t implement.”

After setup, just talk to your OpenClaw agent naturally: 设置完成后，只需像平时一样与你的 OpenClaw 智能体对话：

You say	What happens
”Fix the typo in README”	Simple — Claude Code session, no gstack needed
”Run a security audit on this repo”	Spawns Claude Code with Run /cso
”Build me a notifications feature”	Spawns Claude Code with /autoplan → implement → /ship
”Help me plan the v2 API”	Spawns Claude Code with /office-hours then /autoplan

你说	发生什么
“修复 README 中的拼写错误”	简单任务 —— Claude Code 会话，无需 gstack
“对该仓库运行安全审计”	启动 Claude Code 并运行 /cso
“帮我构建一个通知功能”	启动 Claude Code 并执行 /autoplan → 实现 → /ship
“帮我规划 v2 API”	启动 Claude Code 并执行 /office-hours 然后 /autoplan