Launched this week
GStack
Use Garry Tan's exact Claude Code setup
450 followers
Use Garry Tan's exact Claude Code setup
450 followers
gstack turns Claude Code from one generic assistant into a team of specialists you can summon on demand. Six opinionated workflow skills for Claude Code. Plan review, code review, one-command shipping, browser automation, and engineering retrospectives — all as slash commands.
the slash command approach is really smart. I've been using Claude Code for a while and the biggest friction is always starting from scratch with context every time. having pre-built workflows for common tasks like code review and shipping saves so much time. curious if you're planning to add custom skill creation so teams can build their own workflows too?
Love seeing developer environment setups shared like this.
Is this mainly optimized for Claude Code workflows or does it also work well with Cursor / other AI coding tools?
I've been using Claude Code for months and my setup is held together with scattered markdown files and random CLAUDE.md instructions. The idea of a curated, tested configuration from someone who actually pushes it hard is appealing. My main question: how opinionated is this? Half the value of Claude Code is customizing it to your specific codebase. If this overwrites my existing CLAUDE.md and memory files, that's a dealbreaker. Does it layer on top of existing config or replace it?
Really impressed by the slash command architecture. Treating these as specialized teammates you can summon instantly is exactly right. The separation of plan review from code review catches problems early. How do you handle priority when multiple skills could apply?
Prava
This is amazing, Garry!
I am curious how you use it. do you usually run things sequentially, or is it parallel most of the time? And in the parallel case, how do you keep the flow in sync when each sub-agent is continuously making changes- do you use git worktree?
The real gem here isn't just replicating Garry's setup—it's that someone finally packaged the actual prompt engineering patterns that separate "AI writes hello world" from "AI builds production features." I've been manually maintaining a similar Claude configuration for months and the context switching overhead is brutal. Does this handle multi-file refactoring across large codebases, or is it optimized for the YC startup sweet spot of <50 file projects?
The separation of planning, review, and shipping into distinct slash commands is a smart design choice. We've seen the same pattern in our own agent workflows — a single generic session trying to hold architecture context while line-editing code always degrades quality.
How does GStack handle state handoff between skills? For example, if /plan produces a spec, does /ship automatically pick up that context or do you need to manually bridge them?