Garry Tan’s Open‑Source Claude Code Setup Sparks Praise and Backlash
Key Points
- Garry Tan released an open‑source Claude Code configuration called gstack.
- The repository bundles prompt "skills" that guide the AI to act as CEO, engineer, reviewer, and more.
- gstack quickly gathered thousands of GitHub stars and trended on Product Hunt.
- Developers criticized the project as a simple collection of prompts, questioning its novelty.
- AI models Claude, ChatGPT, and Gemini gave largely positive feedback, calling it sophisticated.
- The debate highlights differing views on AI‑assisted coding tools within the tech community.
Y Combinator CEO Garry Tan unveiled an open‑source Claude Code configuration called gstack, sharing it on GitHub under an MIT license. The project quickly amassed thousands of stars and forks, drawing enthusiastic support on platforms like Product Hunt. At the same time, the release provoked criticism from developers who dismissed it as merely a collection of prompts and questioned its novelty. Expert AI models, including Claude, ChatGPT and Gemini, offered largely positive assessments, describing gstack as a sophisticated prompt workflow. The mixed reaction highlights both excitement and skepticism surrounding AI‑augmented coding tools.
Garry Tan’s AI‑Driven Coding Initiative
Y Combinator founder Garry Tan announced a new open‑source project for Claude Code, an AI coding assistant. He packaged a set of "skills"—reusable prompt files that direct the AI to act in specific roles such as CEO, engineer, or code reviewer—into a repository he named gstack. The code is released under an MIT license and can be installed with a single paste command, allowing teams to replicate his exact setup.
Tan publicized the repository on the social platform X, emphasizing that the configuration reflects his personal workflow. He described his experience with AI agents as a source of intense excitement, noting that the tools keep him awake and focused without the need for stimulant drugs.
Rapid Community Adoption
Within a short period, the gstack repository attracted a large following. It earned thousands of stars and hundreds of forks on GitHub, and it trended on Product Hunt. Users praised the collection for its ability to simulate an engineering organization through prompt engineering, enabling the AI to evaluate ideas, generate code, and perform security reviews.
Criticism and Skepticism
Alongside the acclaim, the release sparked a wave of criticism. Some developers labeled the project as nothing more than a bundle of text files, arguing that similar prompt setups already exist. A founder on X suggested that Tan should be embarrassed for his promotional tweet, while a video commentator called the hype “delusional.” The debate centered on whether gstack offers a unique advantage or merely repackages existing practices.
Expert AI Model Feedback
To gauge the technical merit, the story consulted the AI models themselves. Claude praised gstack as a mature, opinionated system built by a heavy user. ChatGPT described it as “reasonably sophisticated prompt workflows” that are not magical but useful when simulating an engineering structure. Gemini called the configuration “sophisticated” and highlighted its focus on correctness over ease of coding.
Impact on the AI Coding Landscape
The mixed response underscores the growing divide in the tech community over AI‑augmented development tools. While many see gstack as a valuable, open‑source contribution that streamlines complex workflows, others view it as overhyped. Tan’s openness in sharing his personal setup continues to fuel discussion about the role of AI prompts in software engineering.