gstack – Garry Tan's Claude Code Setup(github.com)
github.com
gstack – Garry Tan's Claude Code Setup
https://github.com/garrytan/gstack
16 comments
https://www.youtube.com/watch?v=Q6nem-F8AG8
This thing is absolutely wild.
You essentially get an agent in conductor.build who drafts multiple choice replies to your product and engineering questions from claude.
Dramatically improved code quality and speed of development for me.
You essentially get an agent in conductor.build who drafts multiple choice replies to your product and engineering questions from claude.
Dramatically improved code quality and speed of development for me.
The role decomposition — distinct specialist personas for planning, review, QA, shipping — is the pattern worth paying attention to here, separate from the LOC debate. Then making them work together in a panel/team format.
I've been working on agent workflow tooling and what keeps surprising me is how quickly authoring the skills becomes the trivial part compared to keeping them composable and in sync across projects.
gstack's git-clone-and-copy install model works great solo, but I'm curious how it holds up when different repos need divergent review gates or QA flows — that's where every "just copy the skills folder" approach I've seen starts to buckle.
I've been working on agent workflow tooling and what keeps surprising me is how quickly authoring the skills becomes the trivial part compared to keeping them composable and in sync across projects.
gstack's git-clone-and-copy install model works great solo, but I'm curious how it holds up when different repos need divergent review gates or QA flows — that's where every "just copy the skills folder" approach I've seen starts to buckle.
Not Claude Code specific — works with any Python agent via a one-line decorator. LangChain, AutoGen, CrewAI, or anything custom. Claude Code just gets a zero-config hook via .claude/settings.json. Pi-agent should work fine if it's Python-based.
what makes you think it's python based?
Fair point — it's Python-based if you use the @k9 decorator directly. For Claude Code specifically, the hook works regardless of what language the agent is written in, because it intercepts at the tool call level via .claude/settings.json.
I converted his agent into a sharable claude code agent with gitagent
https://registry.gitagent.sh/agent/shreyas-lyzr/gstack-agent
.
https://registry.gitagent.sh/agent/shreyas-lyzr/gstack-agent
.
Nice work on the gitagent port. If anyone runs this agent autonomously, K9 Audit drops straight into .claude/settings.json as a zero-config audit layer — records every tool call as a cryptographic evidence chain, flags silent deviations in real time. Works alongside gstack with no code changes. https://github.com/liuhaotian2024-prog/K9Audit
Nice work on the gitagent port. K9 Audit drops straight into .claude/settings.json — zero-config audit layer, works alongside gstack. https://github.com/liuhaotian2024-prog/K9Audit
GStack is a brilliant setup for maximizing Claude Code's velocity. But if you are letting an agent run autonomously across your repos, velocity without constraints is terrifying.
We recently had Case #001: a Claude Code agent got stuck in a 70-minute loop, repeatedly injecting a staging URL into a production config file. Raw logs showed "exit code 0" (all green).
To fix this, I built K9 Audit — a deterministic, non-LLM causal auditing layer. It drops directly into .claude/settings.json (zero code changes, perfectly compatible with GStack). It records a cryptographically hashed 5-tuple of what the agent did vs what it was supposed to do.
If you're using GStack to speed up, use K9 Audit as your seatbelt. Repo: https://github.com/liuhaotian2024-prog/K9Audit
We recently had Case #001: a Claude Code agent got stuck in a 70-minute loop, repeatedly injecting a staging URL into a production config file. Raw logs showed "exit code 0" (all green).
To fix this, I built K9 Audit — a deterministic, non-LLM causal auditing layer. It drops directly into .claude/settings.json (zero code changes, perfectly compatible with GStack). It records a cryptographically hashed 5-tuple of what the agent did vs what it was supposed to do.
If you're using GStack to speed up, use K9 Audit as your seatbelt. Repo: https://github.com/liuhaotian2024-prog/K9Audit
Hmm. Is this claude code specific or can this be installed for pi-agent also? I guess I'll just ask pi ;-)
Not Claude Code specific — @k9 decorator works with any Python agent (LangChain, AutoGen, CrewAI). For Claude Code it hooks via .claude/settings.json, zero code changes. For pi-agent: if it's Python-based, yes it works. https://github.com/liuhaotian2024-prog/K9Audit
despite the similarity, pi has nothing at all to do with python.
and thank fuck for that
and thank fuck for that