gstack is an open-source Claude Code skills setup created by Garry Tan, President and CEO of Y Combinator. It packages 15 opinionated skills that turn Claude Code into a virtual engineering team: CEO, designer, eng manager, QA, security, and release engineer roles.

How many GitHub stars did gstack get?

gstack surpassed 20,000 GitHub stars in the first 48 hours, with 2,200+ forks. It reached 23,000+ stars within the first week, making it one of the fastest-growing developer tools on GitHub in 2026.

Why is gstack controversial?

Critics argued gstack is just a collection of prompt text files riding on Garry Tan fame. Supporters counter that the opinionated system represents real hard-won workflow design. TechCrunch covered the divide under the headline love and hate.

How do I install gstack?

Clone the repo at github.com/garrytan/gstack and paste the setup into your local Claude Code installation. It runs as a standard Claude Code skill set with no additional dependencies beyond Claude Code itself.

What productivity claims does gstack make?

Garry Tan claims 10,000 lines of code and 100 pull requests per week using gstack over a 50-day period. The persistent browser daemon enables cookie and session state to survive across commands.

← Back to dashboard

clawsmith.com/signal/gstack-garry-tan-claude-code-20k-stars

🔥 HypeWide OpenLive

gstack: Garry Tan Claude Code Skills Stack Hits 20K GitHub Stars in 48 Hours

YC CEO Garry Tan open-sourced his personal Claude Code setup - 15 opinionated skills turning Claude Code into a virtual engineering team. Hit 20K GitHub stars in 48 hours, went viral on X.

Product Idea from this Signal

A security layer that vets ClawHub skills for malware and prompt injection before your agent installs them

79.8k ▲

ClawHub grew 380% to 13,729 skills in Q1 2026. Snyk found 36% contain prompt injection and 1,467 carry malicious payloads. The ClawHavoc campaign planted 1,184 weaponized skills in the marketplace. VirusTotal integration catches known malware but misses novel prompt injection, data exfiltration via tool outputs, and social engineering patterns unique to AI agent skills. This tool performs deep behavioral analysis of every skill before installation, catching threats that signature-based scanners miss.

SECURITYCLIDEVTOOLOPEN-SOURCE

CompetitiveView Opportunity →