Welcome to the Antigravity Port of gStack.
Originally created by Garry Tan (CEO of Y Combinator), gStack is a framework that encodes decades of Silicon Valley engineering excellence into AI personas. Instead of just "chatting with an AI," you are working with a team of hyper-specialized "Digital Staff" (CEOs, Lead Engineers, Designers) who know exactly how to brainstorm, build, and audit high-growth software.
gStack-Antigravity brings this entire professional brain trust into your local Google Antigravity environmentβmaking it faster, private, and 100% focused on your "vibe coding" journey.
- Install gStack-Antigravity (30 seconds β see below)
- Run
/office-hoursβ describe what you're building - Run
/plan-ceo-reviewon any feature idea - Run
/reviewon any branch with changes - Run
/qaon your staging URL - Stop there. You'll know if this is for you.
Requirements: Antigravity, Git, Bun v1.0+, Node.js (Windows only)
Open Antigravity and paste this. The agent does the rest:
Install gStack-Antigravity: run
git clone https://github.com/kimjin8/gstack-antigravity.git ~/.antigravity/skills/gstack && cd ~/.antigravity/skills/gstack && ./gstack-source/browse/setupthen add a "gstack" section to your persona instructions that says to use the/browseskill from gstack for all web browsing, never use default browser tools, and lists the available skills: /office-hours, /plan-ceo-review, /plan-eng-review, /plan-design-review, /design-consultation, /review, /ship, /land-and-deploy, /canary, /benchmark, /browse, /qa, /qa-only, /design-review, /setup-browser-cookies, /setup-deploy, /retro, /investigate, /document-release, /codex, /cso, /autoplan, /careful, /freeze, /guard, /unfreeze, /gstack-upgrade. Then ask the user if they also want to add gstack to the current project so teammates get it.
Add gStack-Antigravity to this project: run
cp -Rf ~/.antigravity/skills/gstack .antigravity/skills/gstack && rm -rf .antigravity/skills/gstack/.git && cd .antigravity/skills/gstack && ./gstack-source/browse/setupthen add a "gstack" section to your project's.antigravity/rules/persona-gstack.mdthat says to use the/browseskill from gstack for all web browsing, never use default browser tools, lists the available skills: /office-hours, /plan-ceo-review, /plan-eng-review, /plan-design-review, /design-consultation, /review, /ship, /land-and-deploy, /canary, /benchmark, /browse, /qa, /qa-only, /design-review, /setup-browser-cookies, /setup-deploy, /retro, /investigate, /document-release, /codex, /cso, /careful, /freeze, /guard, /unfreeze, /gstack-upgrade, and tells the agent that if gstack skills aren't working, runcd .antigravity/skills/gstack && ./gstack-source/browse/setupto build the binary and register skills.
Real files get committed to your repo (not a submodule), so git clone just works. Everything lives inside .antigravity/. Nothing touches your PATH or runs in the background.
You: I want to build a daily briefing app for my calendar.
You: /office-hours
AI: [asks about the pain β specific examples, not hypotheticals]
You: Multiple Google calendars, events with stale info, wrong locations.
Prep takes forever and the results aren't good enough...
AI: I'm going to push back on the framing. You said "daily briefing
app." But what you actually described is a personal chief of
staff AI.
[extracts 5 capabilities you didn't realize you were describing]
[challenges 4 premises β you agree, disagree, or adjust]
[generates 3 implementation approaches with effort estimates]
RECOMMENDATION: Ship the narrowest wedge tomorrow, learn from
real usage. The full vision is a 3-month project β start with
the daily briefing that actually works.
[writes design doc β feeds into downstream skills automatically]
You: /plan-ceo-review
[reads the design doc, challenges scope, runs 10-section review]
You: /plan-eng-review
[ASCII diagrams for data flow, state machines, error paths]
[test matrix, failure modes, security concerns]
You: Approve plan. Exit plan mode.
[writes 2,400 lines across 11 files. ~8 minutes.]
You: /review
[AUTO-FIXED] 2 issues. [ASK] Race condition β you approve fix.
You: /qa https://staging.myapp.com
[opens real browser, clicks through flows, finds and fixes a bug]
You: /ship
Tests: 42 β 51 (+9 new). PR: github.com/you/app/pull/42
You said "daily briefing app." The agent said "you're building a chief of staff AI" β because it listened to your pain, not your feature request. Eight commands, end to end. That is not a copilot. That is a team.
gstack is a process, not a collection of tools. The skills run in the order a sprint runs:
Think β Plan β Build β Review β Test β Ship β Reflect
Each skill feeds into the next. /office-hours writes a design doc that /plan-ceo-review reads. /plan-eng-review writes a test plan that /qa picks up. /review catches bugs that /ship verifies are fixed. Nothing falls through the cracks because every step knows what came before it.
| Skill | Your specialist | What they do |
|---|---|---|
/office-hours |
YC Office Hours | Start here. Six forcing questions that reframe your product before you write code. Pushes back on your framing, challenges premises, generates implementation alternatives. Design doc feeds into every downstream skill. |
/plan-ceo-review |
CEO / Founder | Rethink the problem. Find the 10-star product hiding inside the request. Four modes: Expansion, Selective Expansion, Hold Scope, Reduction. |
/plan-eng-review |
Eng Manager | Lock in architecture, data flow, diagrams, edge cases, and tests. Forces hidden assumptions into the open. |
/plan-design-review |
Senior Designer | Rates each design dimension 0-10, explains what a 10 looks like, then edits the plan to get there. AI Slop detection. Interactive β one AskUserQuestion per design choice. |
/design-consultation |
Design Partner | Build a complete design system from scratch. Researches the landscape, proposes creative risks, generates realistic product mockups. |
/review |
Staff Engineer | Find the bugs that pass CI but blow up in production. Auto-fixes the obvious ones. Flags completeness gaps. |
/investigate |
Debugger | Systematic root-cause debugging. Iron Law: no fixes without investigation. Traces data flow, tests hypotheses, stops after 3 failed fixes. |
/design-review |
Designer Who Codes | Same audit as /plan-design-review, then fixes what it finds. Atomic commits, before/after screenshots. |
/qa |
QA Lead | Test your app, find bugs, fix them with atomic commits, re-verify. Auto-generates regression tests for every fix. |
/qa-only |
QA Reporter | Same methodology as /qa but report only. Pure bug report without code changes. |
/cso |
Chief Security Officer | OWASP Top 10 + STRIDE threat model. Zero-noise: 17 false positive exclusions, 8/10+ confidence gate, independent finding verification. Each finding includes a concrete exploit scenario. |
/ship |
Release Engineer | Sync main, run tests, audit coverage, push, open PR. Bootstraps test frameworks if you don't have one. |
/land-and-deploy |
Release Engineer | Merge the PR, wait for CI and deploy, verify production health. One command from "approved" to "verified in production." |
/canary |
SRE | Post-deploy monitoring loop. Watches for console errors, performance regressions, and page failures. |
/benchmark |
Performance Engineer | Baseline page load times, Core Web Vitals, and resource sizes. Compare before/after on every PR. |
/document-release |
Technical Writer | Update all project docs to match what you just shipped. Catches stale READMEs automatically. |
/retro |
Eng Manager | Team-aware weekly retro. Per-person breakdowns, shipping streaks, test health trends, growth opportunities. /retro global runs across all your projects and AI tools (Claude Code, Codex, Gemini). |
/browse |
QA Engineer | Real Chromium browser, real clicks, real screenshots. ~100ms per command. |
/setup-browser-cookies |
Session Manager | Import cookies from your real browser (Chrome, Arc, Brave, Edge) into the headless session. Test authenticated pages. |
/autoplan |
Review Pipeline | One command, fully reviewed plan. Runs CEO β design β eng review automatically with encoded decision principles. Surfaces only taste decisions for your approval. |
| Skill | What it does |
|---|---|
/codex |
Second Opinion β independent code review from OpenAI Codex CLI. Three modes: review (pass/fail gate), adversarial challenge, and open consultation. Cross-model analysis when both /review and /codex have run. |
/careful |
Safety Guardrails β warns before destructive commands (rm -rf, DROP TABLE, force-push). Say "be careful" to activate. Override any warning. |
/freeze |
Edit Lock β restrict file edits to one directory. Prevents accidental changes outside scope while debugging. |
/guard |
Full Safety β /careful + /freeze in one command. Maximum safety for prod work. |
/unfreeze |
Unlock β remove the /freeze boundary. |
/setup-deploy |
Deploy Configurator β one-time setup for /land-and-deploy. Detects your platform, production URL, and deploy commands. |
/gstack-upgrade |
Self-Updater β upgrade gstack to latest. Detects global vs vendored install, syncs both, shows what changed. |
gstack is powerful with one sprint. It is transformative with ten running at once.
In the Antigravity environment, you can run multiple agent sessions in parallel β each in its own isolated workspace. One session on /office-hours, another on /review, a third implementing a feature, a fourth running /qa. All at the same time. The sprint structure is what makes parallelism work β without a process, ten agents is ten sources of chaos. With a process, each agent knows exactly what to do and when to stop.
This project is a localized port of the original gstack framework by Garry Tan. We are deeply grateful to Garry and the gstack team for their incredible work in building these powerful engineering personas.
- Original Source: garrytan/gstack
- Philosophy: This port aims to make that same SV-level expertise accessible directly within the Google Antigravity environment, while keeping your work private and local.