garrytan/gstackPublic

Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

AI summary: Minimalist technology stack designed for rapid prototyping and deploying robust web applications quickly.

Stars
142.2K
+2 today
Forks
21K
Watchers
765
Open issues
80
Open PRs
38
Contributors
~18
Commits
1.2K
Branches
1.4K
Views (30d)
7

TypeScriptMITCreated Mar 11, 2026Last push todayLatest release v1.100.0.0+649 stars this week+4.9K this month

Quick answers

What is gstack?
Minimalist technology stack designed for rapid prototyping and deploying robust web applications quickly.
What does gstack do?
gstack provides a highly opinionated, pre-configured architectural template that drastically reduces the friction of starting new web projects. It wires together modern frontend frameworks with lightweight backend services, establishing secure database connections and authentication flows out of the box. The project enforces strict directory structures and styling conventions to eliminate decision fatigue during the critical early stages of development. It relies heavily on managed cloud services to minimize the need for complex local infrastructure orchestration. By standardizing the boilerplate, it allows developers to focus entirely on implementing core business logic.
Who is gstack for?
Startup founders, indie hackers, and full-stack developers looking to deploy scalable web applications rapidly. General knowledge of modern JavaScript ecosystems is necessary.
How do I get started with gstack?
https://github.com/garrytan/gstack
How popular is gstack on GitHub?
garrytan/gstack has 142,223 stars and 20,987 forks on GitHub, and gained 649 stars in the last 7 days.
What license does gstack use?
garrytan/gstack is released under the MIT license.

Star history

since Jul 29, 2026
050K100KJul 2026Sep 2026Oct 2026Nov 2026
142.2K stars as of Nov 21, 2026. Measured daily since Jul 29, 2026; GitHub no longer exposes earlier star timestamps.

Update history

2 recorded
  • Nov 17, 2026New release v1.100.0.0 (previously v1.96.0.0).
  • Nov 7, 2026New release v1.96.0.0 (previously v1.91.242.0).

Contribution activity

commits per day, last 52 weeks
NovDecJanFebMarAprMayJunJulAugSepOctNovMonWedFri2025-11-23: 0 commits2025-11-24: 0 commits2025-11-25: 0 commits2025-11-26: 0 commits2025-11-27: 0 commits2025-11-28: 0 commits2025-11-29: 0 commits2025-11-30: 0 commits2025-12-01: 0 commits2025-12-02: 0 commits2025-12-03: 0 commits2025-12-04: 0 commits2025-12-05: 0 commits2025-12-06: 0 commits2025-12-07: 0 commits2025-12-08: 0 commits2025-12-09: 0 commits2025-12-10: 0 commits2025-12-11: 0 commits2025-12-12: 0 commits2025-12-13: 0 commits2025-12-14: 0 commits2025-12-15: 0 commits2025-12-16: 0 commits2025-12-17: 0 commits2025-12-18: 0 commits2025-12-19: 0 commits2025-12-20: 0 commits2025-12-21: 0 commits2025-12-22: 0 commits2025-12-23: 0 commits2025-12-24: 0 commits2025-12-25: 0 commits2025-12-26: 0 commits2025-12-27: 0 commits2025-12-28: 0 commits2025-12-29: 0 commits2025-12-30: 0 commits2025-12-31: 0 commits2026-01-01: 0 commits2026-01-02: 0 commits2026-01-03: 0 commits2026-01-04: 0 commits2026-01-05: 0 commits2026-01-06: 0 commits2026-01-07: 0 commits2026-01-08: 0 commits2026-01-09: 0 commits2026-01-10: 0 commits2026-01-11: 0 commits2026-01-12: 0 commits2026-01-13: 0 commits2026-01-14: 0 commits2026-01-15: 0 commits2026-01-16: 0 commits2026-01-17: 0 commits2026-01-18: 0 commits2026-01-19: 0 commits2026-01-20: 0 commits2026-01-21: 0 commits2026-01-22: 0 commits2026-01-23: 0 commits2026-01-24: 0 commits2026-01-25: 0 commits2026-01-26: 0 commits2026-01-27: 0 commits2026-01-28: 0 commits2026-01-29: 0 commits2026-01-30: 0 commits2026-01-31: 0 commits2026-02-01: 0 commits2026-02-02: 0 commits2026-02-03: 0 commits2026-02-04: 0 commits2026-02-05: 0 commits2026-02-06: 0 commits2026-02-07: 0 commits2026-02-08: 0 commits2026-02-09: 0 commits2026-02-10: 0 commits2026-02-11: 0 commits2026-02-12: 0 commits2026-02-13: 0 commits2026-02-14: 0 commits2026-02-15: 0 commits2026-02-16: 0 commits2026-02-17: 0 commits2026-02-18: 0 commits2026-02-19: 0 commits2026-02-20: 0 commits2026-02-21: 0 commits2026-02-22: 0 commits2026-02-23: 0 commits2026-02-24: 0 commits2026-02-25: 0 commits2026-02-26: 0 commits2026-02-27: 0 commits2026-02-28: 0 commits2026-03-01: 0 commits2026-03-02: 0 commits2026-03-03: 0 commits2026-03-04: 0 commits2026-03-05: 0 commits2026-03-06: 0 commits2026-03-07: 0 commits2026-03-08: 0 commits2026-03-09: 0 commits2026-03-10: 0 commits2026-03-11: 1 commit2026-03-12: 3 commits2026-03-13: 6 commits2026-03-14: 36 commits2026-03-15: 1 commit2026-03-16: 10 commits2026-03-17: 15 commits2026-03-18: 6 commits2026-03-19: 12 commits2026-03-20: 5 commits2026-03-21: 7 commits2026-03-22: 12 commits2026-03-23: 9 commits2026-03-24: 10 commits2026-03-25: 1 commit2026-03-26: 11 commits2026-03-27: 6 commits2026-03-28: 4 commits2026-03-29: 6 commits2026-03-30: 8 commits2026-03-31: 2 commits2026-04-01: 2 commits2026-04-02: 3 commits2026-04-03: 3 commits2026-04-04: 7 commits2026-04-05: 10 commits2026-04-06: 5 commits2026-04-07: 2 commits2026-04-08: 3 commits2026-04-09: 0 commits2026-04-10: 1 commit2026-04-11: 0 commits2026-04-12: 0 commits2026-04-13: 1 commit2026-04-14: 1 commit2026-04-15: 0 commits2026-04-16: 5 commits2026-04-17: 2 commits2026-04-18: 5 commits2026-04-19: 3 commits2026-04-20: 3 commits2026-04-21: 1 commit2026-04-22: 1 commit2026-04-23: 6 commits2026-04-24: 4 commits2026-04-25: 2 commits2026-04-26: 1 commit2026-04-27: 0 commits2026-04-28: 3 commits2026-04-29: 0 commits2026-04-30: 1 commit2026-05-01: 4 commits2026-05-02: 1 commit2026-05-03: 2 commits2026-05-04: 1 commit2026-05-05: 1 commit2026-05-06: 3 commits2026-05-07: 1 commit2026-05-08: 1 commit2026-05-09: 2 commits2026-05-10: 1 commit2026-05-11: 4 commits2026-05-12: 0 commits2026-05-13: 2 commits2026-05-14: 6 commits2026-05-15: 1 commit2026-05-16: 1 commit2026-05-17: 1 commit2026-05-18: 0 commits2026-05-19: 0 commits2026-05-20: 4 commits2026-05-21: 4 commits2026-05-22: 0 commits2026-05-23: 0 commits2026-05-24: 1 commit2026-05-25: 2 commits2026-05-26: 3 commits2026-05-27: 1 commit2026-05-28: 1 commit2026-05-29: 2 commits2026-05-30: 5 commits2026-05-31: 0 commits2026-06-01: 0 commits2026-06-02: 1 commit2026-06-03: 0 commits2026-06-04: 1 commit2026-06-05: 0 commits2026-06-06: 0 commits2026-06-07: 4 commits2026-06-08: 4 commits2026-06-09: 2 commits2026-06-10: 1 commit2026-06-11: 0 commits2026-06-12: 1 commit2026-06-13: 0 commits2026-06-14: 1 commit2026-06-15: 0 commits2026-06-16: 0 commits2026-06-17: 0 commits2026-06-18: 1 commit2026-06-19: 0 commits2026-06-20: 0 commits2026-06-21: 1 commit2026-06-22: 0 commits2026-06-23: 0 commits2026-06-24: 0 commits2026-06-25: 1 commit2026-06-26: 0 commits2026-06-27: 0 commits2026-06-28: 0 commits2026-06-29: 0 commits2026-06-30: 0 commits2026-07-01: 0 commits2026-07-02: 0 commits2026-07-03: 0 commits2026-07-04: 0 commits2026-07-05: 0 commits2026-07-06: 0 commits2026-07-07: 0 commits2026-07-08: 0 commits2026-07-09: 4 commits2026-07-10: 10 commits2026-07-11: 0 commits2026-07-12: 0 commits2026-07-13: 0 commits2026-07-14: 13 commits2026-07-15: 0 commits2026-07-16: 0 commits2026-07-17: 0 commits2026-07-18: 0 commits2026-07-19: 0 commits2026-07-20: 0 commits2026-07-21: 0 commits2026-07-22: 0 commits2026-07-23: 0 commits2026-07-24: 0 commits2026-07-25: 0 commits2026-07-26: 0 commits2026-07-27: 0 commits2026-07-28: 0 commits2026-07-29: 0 commits2026-07-30: 0 commits2026-07-31: 0 commits2026-08-01: 0 commits2026-08-02: 0 commits2026-08-03: 0 commits2026-08-04: 0 commits2026-08-05: 0 commits2026-08-06: 0 commits2026-08-07: 1 commit2026-08-08: 1 commit2026-08-09: 0 commits2026-08-10: 0 commits2026-08-11: 0 commits2026-08-12: 1 commit2026-08-13: 0 commits2026-08-14: 2 commits2026-08-15: 3 commits2026-08-16: 2 commits2026-08-17: 1 commit2026-08-18: 1 commit2026-08-19: 3 commits2026-08-20: 0 commits2026-08-21: 1 commit2026-08-22: 0 commits2026-08-23: 0 commits2026-08-24: 1 commit2026-08-25: 0 commits2026-08-26: 0 commits2026-08-27: 2 commits2026-08-28: 1 commit2026-08-29: 2 commits2026-08-30: 1 commit2026-08-31: 1 commit2026-09-01: 2 commits2026-09-02: 0 commits2026-09-03: 0 commits2026-09-04: 0 commits2026-09-05: 1 commit2026-09-06: 1 commit2026-09-07: 0 commits2026-09-08: 2 commits2026-09-09: 1 commit2026-09-10: 0 commits2026-09-11: 0 commits2026-09-12: 0 commits2026-09-13: 0 commits2026-09-14: 2 commits2026-09-15: 4 commits2026-09-16: 0 commits2026-09-17: 0 commits2026-09-18: 0 commits2026-09-19: 0 commits2026-09-20: 0 commits2026-09-21: 1 commit2026-09-22: 1 commit2026-09-23: 1 commit2026-09-24: 2 commits2026-09-25: 3 commits2026-09-26: 1 commit2026-09-27: 0 commits2026-09-28: 3 commits2026-09-29: 3 commits2026-09-30: 0 commits2026-10-01: 2 commits2026-10-02: 1 commit2026-10-03: 4 commits2026-10-04: 4 commits2026-10-05: 2 commits2026-10-06: 4 commits2026-10-07: 3 commits2026-10-08: 13 commits2026-10-09: 0 commits2026-10-10: 14 commits2026-10-11: 10 commits2026-10-12: 2 commits2026-10-13: 5 commits2026-10-14: 1 commit2026-10-15: 0 commits2026-10-16: 17 commits2026-10-17: 14 commits2026-10-18: 8 commits2026-10-19: 22 commits2026-10-20: 9 commits2026-10-21: 3 commits2026-10-22: 5 commits2026-10-23: 4 commits2026-10-24: 14 commits2026-10-25: 33 commits2026-10-26: 37 commits2026-10-27: 23 commits2026-10-28: 19 commits2026-10-29: 20 commits2026-10-30: 24 commits2026-10-31: 41 commits2026-11-01: 49 commits2026-11-02: 71 commits2026-11-03: 71 commits2026-11-04: 38 commits2026-11-05: 24 commits2026-11-06: 51 commits2026-11-07: 24 commits2026-11-08: 16 commits2026-11-09: 48 commits2026-11-10: 3 commits2026-11-11: 7 commits2026-11-12: 4 commits2026-11-13: 1 commit2026-11-14: 8 commits2026-11-15: 4 commits2026-11-16: 10 commits2026-11-17: 27 commits2026-11-18: 0 commits2026-11-19: 0 commits2026-11-20: 0 commits2026-11-21: 0 commits
1,212 commits in the last yearLessMore

Signals and awards

derived from tracked data
  • Landmark project

    142,223 stars

  • Very active

    1,212 commits in 52 weeks

  • Well documented

    High community health score

  • Permissive license

    MIT

  • Continuous integration

    Automated checks passing

  • Repeat trending

    57 trending appearances

  • Top 10% tracked

    Rank 50 of 1243

What gstack does

gstack provides a highly opinionated, pre-configured architectural template that drastically reduces the friction of starting new web projects. It wires together modern frontend frameworks with lightweight backend services, establishing secure database connections and authentication flows out of the box. The project enforces strict directory structures and styling conventions to eliminate decision fatigue during the critical early stages of development. It relies heavily on managed cloud services to minimize the need for complex local infrastructure orchestration. By standardizing the boilerplate, it allows developers to focus entirely on implementing core business logic.

Startup founders, indie hackers, and full-stack developers looking to deploy scalable web applications rapidly. General knowledge of modern JavaScript ecosystems is necessary.

  • Pre-configured boilerplate: Wires together modern frontend frameworks and backend services immediately out of the box.
  • Integrated authentication: Establishes secure user login flows without requiring complex manual setup.
  • Database connectivity: Connects seamlessly to lightweight managed databases with optimized query structures.
  • Opinionated architecture: Enforces strict directory layouts to eliminate early-stage decision fatigue completely.
  • Cloud optimization: Relies on managed infrastructure services to reduce the burden of local DevOps orchestration.

Where teams use it

Prototype web applications

Launch functional MVPs in hours rather than days by utilizing pre-configured application logic.

Standardize team setups

Ensure all developers start new projects using the exact same architectural conventions.

Deploy SaaS products

Build robust, scalable web applications focused entirely on unique business features.

Participate in hackathons

Bypass tedious boilerplate setup to focus completely on rapid feature development.

Getting started: https://github.com/garrytan/gstack

README

main branch

gstack

gstack turns Claude Code (and other coding agents) into a virtual engineering team: a CEO who rethinks the product, an eng manager who locks architecture, a designer who catches AI slop, a reviewer who finds production bugs, a QA lead who opens a real browser, a security officer who runs OWASP + STRIDE audits, and a release engineer who ships the PR. All slash commands, all Markdown, all free, MIT license.

I'm Garry Tan, President & CEO of Y Combinator. This is the open source software factory I use every day, and I'm sharing it because these tools should be available to everyone. The story, the productivity numbers and how I run ten sprints at once are in Why gstack.

Fork it. Improve it. Make it yours. And if you want to hate on free open source software — you're welcome to, but I'd rather you just try it first.

Who this is for:

  • Founders and CEOs — especially technical ones who still want to ship
  • First-time Claude Code users — structured roles instead of a blank prompt
  • Tech leads and staff engineers — rigorous review, QA, and release automation on every PR

What gstack is for

  • A whole team's judgment for one builder. Product, design, engineering, QA, security and release reviews, each from a specialist role.
  • Catch what CI misses. Find the bugs that pass tests but break in production, before they ship.
  • AI-written changes you can trust. Every change carries its tests, its review and the evidence for both, so you can merge without rereading every line.
  • Free, open and portable. MIT-licensed, and it runs on Claude Code and the other major coding agents.

Quick start

  1. Install gstack (two pastes, about 30 seconds of setup; see below).
  2. Run /office-hours and describe what you're building. It pushes back on your framing and writes a design doc the other skills read.
  3. Run /review on any branch with changes. It finds the bugs that pass CI but break in production, and fixes the obvious ones.
  4. Run /qa on your staging URL, or on an isolated local API, CLI, job or webhook. It opens a real browser, reproduces bugs and fixes them.

Stop there. You'll know if this is for you. When you want the whole sprint, /autoplan reviews a plan end to end and /ship runs tests, review and the PR.

Install — about 30 seconds

Requirements: Claude Code, Git, Bun v1.4.2+ (the tested version; setup refuses Bun older than 1.3.3, which would let compiled tools read a project's .env), and Node.js on Windows. Recommended on macOS: the Aside browser (macOS 15+), which the browser skills, /make-pdf and /diagram drive first with your real logged-in sessions; without it, ./setup builds gstack's own bundled browser. /cso needs a native toolchain as well; setup says so and leaves it unavailable when the toolchain is absent. Timing, the /cso prerequisites and the hooks setup registers: docs/install.md.

Step 1: Install on your machine

Open Claude Code and paste this. Claude does the rest.

Install gstack: run git clone --single-branch --depth 1 https://github.com/garrytan/gstack.git ~/.claude/skills/gstack && cd ~/.claude/skills/gstack && ./setup then add a "gstack" section to CLAUDE.md that says to use the /browse skill from gstack for all web browsing and never use mcp__claude-in-chrome__* tools. Claude Code lists the installed skills itself, so the section needs no skill list. Then ask the user if they also want to add gstack to the current project so teammates get it.

Which updates you get: a new install follows the stable channel, the tagged release (Monday and Thursday at most once every 72 hours, an important fix within about a day, never more than a week stale, plus verified security and regression fixes), instead of every merge to main. ./setup records this the first time it runs on a machine and prints it. The clone itself starts at main's latest commit, and the updater never moves a checkout backwards, so it moves onto releases at the next cut that passes it (within a few days). A gstack contributor's checkout (marked by bin/dev-setup, on a branch other than origin's default main, or carrying local commits) and a Capy crew machine (its installer records main) follow main instead, and an install set up before stable became the default keeps following main. To switch, run ~/.claude/skills/gstack/bin/gstack-config set update_channel main (every merge) or ~/.claude/skills/gstack/bin/gstack-config set update_channel stable (releases only). Details: docs/releases.md.

Step 2: Team mode — auto-update for shared repos (recommended)

From inside your repo, paste this. Switches you to team mode, bootstraps the repo so teammates get gstack automatically, and commits the change:

(cd ~/.claude/skills/gstack && ./setup --team) && ~/.claude/skills/gstack/bin/gstack-team-init required && git add .claude/ CLAUDE.md && git commit -m "require gstack for AI-assisted work"

No vendored files in your repo, no version drift, no manual upgrades. Every Claude Code session starts with a fast auto-update check (throttled to once/hour, network-failure-safe, completely silent). Team mode follows the stable channel while update_channel is auto (so also on an install from before stable became the default): the tagged release (Monday and Thursday at most once every 72 hours, an important fix within about a day, never more than a week stale, plus verified security and regression fixes), not every merge to main. gstack-config set update_channel main follows every merge instead; see docs/releases.md.

Swap required for optional if you'd rather nudge teammates than block them.

Team mode's required hook runs on Node.js, so every teammate needs Node.js on PATH (details). To remove gstack later: docs/uninstall.md.

Other AI Agents

gstack runs on more agents than Claude. Bare ./setup installs for Claude Code only (run inside OpenClaw, Hermes or a Dot, it also registers gstack's skills with that harness: docs/hosts.md). Pick another agent with --host <name>, or install for every agent setup detects on this machine with --host auto:

git clone --single-branch --depth 1 https://github.com/garrytan/gstack.git ~/gstack
cd ~/gstack && ./setup --host auto      # or: ./setup --host codex
./setup --status                         # one row per install: host, tier, scope, version, path

An explicit --host X installs for X only and never changes another agent's install. /gstack-upgrade refreshes every install it registered, one row per host, and says which ones failed.

Tiers: full is certified by a real workflow run (see Certify your host); experimental installs and passes the conformance tests but has no certification run yet; instruction-only installs nothing: setup prints what to copy.

Agent Tier Install First invocation Safety skills Outside review needs Repair
Claude Code full --host claude (default) /office-hours enforced (hooks block) Codex CLI, signed in ./setup --host claude
OpenAI Codex CLI experimental --host codex → ${CODEX_HOME:-~/.codex}/skills/gstack-*/ ask for gstack-office-hours advisory, not blocked Claude Code CLI, signed in ./setup --host codex
OpenCode experimental --host opencode → ~/.config/opencode/skills/gstack-*/ + /gstack-* commands /gstack-office-hours advisory, not blocked Codex CLI, signed in ./setup --host opencode
Cursor experimental --host cursor → ~/.cursor/skills/gstack-*/ ask for gstack-office-hours advisory, not blocked Codex CLI, signed in ./setup --host cursor
Factory Droid experimental --host factory → ~/.factory/skills/gstack-*/ ask for gstack-office-hours advisory, not blocked Codex CLI, signed in ./setup --host factory
Kiro experimental --host kiro → ~/.kiro/skills/gstack-*/ ask for gstack-office-hours advisory, not blocked Codex CLI, signed in ./setup --host kiro
GitHub Copilot CLI experimental --host copilot → ~/.copilot/skills/gstack-*/ /gstack-office-hours advisory, not blocked Codex CLI, signed in ./setup --host copilot
Antigravity CLI experimental --host agy (or --host antigravity) → ~/.gemini/antigravity-cli/skills/gstack-*/ /gstack-office-hours advisory, not blocked Codex CLI, signed in ./setup --host agy
Gemini CLI experimental --host gemini (or --host gemini-cli) → ~/.gemini/skills/gstack-*/ ask for gstack-office-hours advisory, not blocked Codex CLI, signed in ./setup --host gemini
Slate instruction-only --host slate (points at the Claude install; Slate reads .claude/skills) /office-hours via the Claude install advisory, not blocked — ./setup --host claude
OpenClaw experimental --host openclaw (five task skills and one gstack router skill in OpenClaw's skills folder; automatic when setup runs inside OpenClaw; ACP route in docs/OPENCLAW.md) ask for the task; the agent opens the matching task skill or the gstack router advisory, not blocked — ./setup --host openclaw
Hermes experimental --host hermes (every skill in $HERMES_HOME/skills/gstack; automatic when setup runs inside Hermes) ask for the task, or /gstack-review advisory, not blocked — ./setup --host hermes
GBrain (mod) instruction-only --host gbrain (brain-aware variants ship from the GBrain repo) — advisory, not blocked — —

Per-host notes (agent harnesses, Copilot, Antigravity, Gemini CLI, OpenClaw and ClawHub, the Codex behavioral profile and model tiers, outside-review providers, the design binary's models) are in docs/hosts.md. Any rules-reading agent (Zed, Amp, Jules) can use the 2KB agents digest with no install. Adding a host: docs/ADDING_A_HOST.md.

See it work

You:    I want to build a daily briefing app for my calendar.
You:    /office-hours
Claude: [asks about the pain — specific examples, not hypotheticals]

You:    Multiple Google calendars, events with stale info, wrong locations.
        Prep takes forever and the results aren't good enough...

Claude: 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 — 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 — start with
        the daily briefing that actually works.
        [writes design doc → 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 → you approve fix.

You:    /qa https://staging.myapp.com
        [opens real browser, clicks through flows, finds and fixes a bug]

You:    /ship
        Tests: 42 → 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" — because it listened to your pain, not your feature request. Eight commands, end to end. That is not a copilot. That is a team.

The sprint

gstack is a process, not a collection of tools. The skills run in the order a sprint runs:

Think → Plan → Build → Review → Test → Ship → 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 — one AskUserQuestion per design choice.
/plan-devex-review Developer Experience Lead Interactive DX review: explores developer personas, benchmarks against competitors' TTHW, designs your magical moment, traces friction points step by step. Scores error messages for the agents that read them (agent-ready errors). Three modes: DX EXPANSION, DX POLISH, DX TRIAGE. 20-45 forcing questions.
/design-consultation Design Partner Build a complete design system from scratch. Researches the landscape, proposes creative risks, generates realistic product mockups. Writes DESIGN.md in the open DESIGN.md format, so impeccable, Google Stitch, and any tool that reads it share one file.
/review Staff Engineer Find the bugs that pass CI but blow up in production. Auto-fixes the obvious ones. Flags completeness gaps and gate integrity: every weakened test, timeout, snapshot or suppression reaches a human by name. Advisory simplification lens flags over-built code — never blocks, never auto-applies.
/deslop-shared-libs Shared Code Reviewer Find worthwhile shared-code extractions in recent work. Compares up to five opportunities and recommends the best three, with source evidence, reliability gains, and total code savings. Recommendations only.
/write-skill Skill Editor Write a new agent skill or improve one without bloat. A five-step edit ladder (fix the tool first, add nothing the model already does, edit the line instead of appending, lowest level that reaches the agent, rule not story), gstack-skill-bill for size per level and growth since the last diet, a drift check that every gstack command and flag a skill names still exists, and full diets proven by a before/after/no-skill test.
/test-audit Test Auditor Sweep existing tests for ones that cost more than they protect: source greps, duplicates, assertion-free probes, test-only exports. Every candidate carries an evidence card; report-only unless you approve a batch.
/verify Build Loop Run the repo's own checks (typecheck, lint, build) and the tests /ship's pre-gate would pick for your change, fix what breaks, repeat until green, then hand off to /ship. Asks once before running repo commands; never calls a change green when no test covers it.
/design-review Designer Who Codes Same audit as /plan-design-review, then fixes what it finds. Atomic commits, before/after screenshots. If you have impeccable installed, its engine runs first and every mechanical finding arrives tagged with its rule id.
/devex-review DX Tester Live developer experience audit. Actually tests your onboarding: navigates docs, tries the getting started flow, times TTHW, triggers CLI errors the way an agent meets them (gstack-error-capture: no terminal, contained, redacted). Compares against /plan-devex-review scores — the boomerang that shows if your plan matched reality.
/design-shotgun Design Explorer "Show me options." Generates 4-6 AI mockup variants, opens a comparison board in your browser, collects your feedback, and iterates. Taste memory learns what you like. Repeat until you love something, then hand it to /design-html.
/design-html Design Engineer Turn a mockup into production HTML that actually works. Pretext computed layout: text reflows, heights adjust, layouts are dynamic. 30KB, zero deps. Detects React/Svelte/Vue. Smart API routing per design type (landing page vs dashboard vs form). One slop-gate pass through the impeccable engine when you have it. The output is shippable, not a demo.
/design-motion Motion Designer Turn an approved mockup, a finalized page or a URL into a showcase loop. Rebuilds the exact frame, loads it from empty, gives each visual one story, records deterministic frames on a fake clock, and exports an MP4 for X, a website GIF and an 800×500 GIF once the seam, empty-beat, rest and overflow checks pass. Needs ffmpeg.
/qa QA Lead Explore browser, API, CLI, job and webhook behavior. Reproduce bugs, write failing regressions, fix the cause and re-verify before committing.
/qa-only QA Reporter Explore and report with replayable evidence. Suggest regression cases without changing product code or tests.
/pair-agent Multi-Agent Coordinator Share gstack's own browser with any AI agent. One command, one paste, connected. Works with OpenClaw, Hermes, Codex, Cursor, or anything that can curl. Each agent gets its own tab. Auto-launches headed mode so you watch everything. Auto-starts ngrok tunnel for remote agents. Scoped tokens, tab isolation, rate limiting, activity attribution. (Runs on the bundled browser — the fallback engine; agents driving Aside just open their own tabs.)
/cso Chief Security Officer Security audit with an application model, supported findings, independent challenge, and explicit coverage. Static assessment remains available without catalog profiles. With matching qualified profiles, comprehensive mode adds contained runtime/scanner execution and reviewable repair candidates for Node/Bun, Python, and Rails. Qualified runtime and scanner images are published for linux/amd64 and linux/arm64. Without Docker, audits run static assessment only. Runtime-tested bundles authenticate separate external assertions. Project-test completion remains self_reported because target code controls the test process; tested is reserved for a future target-independent completion witness.
/ship Release Engineer Sync main, run tests, explore changed behavior, audit coverage, gate integrity and docs, then verify, push and open a PR whose body opens with three plain lines (how gstack writes PRs and commits).
/land-and-deploy Release Engineer Merge the PR, wait for CI and deploy, verify production health. One command from "approved" to "verified in production."
/modernize Stale-PR Maintainer Bring an aging PR onto its current base and say whether it should still exist: MODERNIZE (rebase, git range-diff proof, push with a lease pinned to the observed head), REWORK (the problem stands, the diff does not) or CLOSE (recommended, never done without permission). Reads the base's moved range for conflicts in meaning, not only in text.
/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.
/ubicloud Remote Runner Run a heavy suite, build or eval on an ephemeral 16-vCPU Ubicloud VM: owner- and TTL-named VMs with a reaper, quota preflight, a hang watchdog, and one committed verify per repository.
/runaway-stopper Spend Warden Find runaway agent threads and subagents on Capy (a standing thread past 500M own tokens or 3 days, a subagent past 100M, empty wakes, endless review rounds), stop them at a clean point, rotate standing threads through a handoff (a crew thread keeps its PR until it merges or closes), and set the defaults that keep them from coming back. gstack-runaway scan reads the host's own thread data and never acts.
/eval-plan Eval Planner Preregister a paid eval before the first priced call: bars, arms, decoys and stop rules, a $0 stub-model dry run over the real inputs, and a three-item priced pilot whose extrapolation and spend table gate the approval.
/document-release Technical Writer Audit changed behavior against project docs on every ship, before final verification and publication. Also runs standalone. Shows updated, reviewed/current or blocked docs and any remaining gaps.
/document-generate Documentation Author Generate missing docs from scratch using the Diataxis framework. Researches the codebase first, then writes reference / how-to / tutorial / explanation docs that actually match the code. Invokable standalone or chained from /document-release when the coverage map finds gaps. Learn more: tutorial • how-to • why Diataxis.
/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, Kimi Code, OMP, Antigravity).
/browse QA Engineer Give the agent eyes. Drives your Aside browser first — your real sessions, real clicks, real screenshots — through deterministic aside repl scripts. No Aside? It falls back to gstack's own Chromium: real clicks, ~100ms per command, and /open-gstack-browser shows it headed with sidebar, anti-bot stealth, and auto model routing. Every other browser skill stands on it.
/scrape Data Extractor Pull structured data off a web page — tables, lists, prices — in your Aside browser with the page's real logged-in state. On the fallback browser, /skillify turns the flow into a permanent browser-skill that runs in ~200ms next time.
/setup-browser-cookies Session Manager Copy selected cookies from Chrome, Chromium, Brave, Edge, Windows-only Opera and Opera GX, or macOS-only Comet and Arc into gstack's bundled browser. Choose your profile and domains; copying and sign-in verification are separate. Only needed on the fallback path — Aside already has your sessions.
/autoplan Review Pipeline One command, reviewed plan. In an interactive session it runs CEO → design → DX → eng review from each skill's own method (eng always last, so the shipping gate reviews the final amended plan) with encoded decision principles, and surfaces only taste decisions for your approval. A run driven by gstack-autoplan (the Capy default) gives its reviewers short checklists instead of those methods: the lean run is one reviewer, --full one per phase (what each run loads).
/spec Spec Author Turn vague intent into a precise, executable spec in five phases (why, scope, technical with mandatory code-reading, draft, file). Outside-review quality gate before filing (Claude Code on Codex; Codex on other harnesses; blocks below 7/10), fail-closed secret redaction, dedupe against existing issues, archive to $GSTACK_STATE_ROOT/projects/$SLUG/specs/ for team-corpus recall. --execute spawns claude -p in a fresh worktree; /ship auto-closes the source issue on merge. Plan-mode aware.
/learn Memory Manage what gstack learned across sessions. Review, search, prune, and export project-specific patterns, pitfalls, and preferences. Learnings compound across sessions so gstack gets smarter on your codebase over time.
/make-pdf Publisher Markdown in, publication-quality document out. Mermaid and excalidraw fences render as vector diagrams, fully offline. Images scale to the page and never truncate; wide diagrams get their own landscape page. --to html emits one self-contained file, --to docx a Word doc.
/diagram Diagram Maker English in, editable diagram out. Emits a triplet: mermaid source, .excalidraw you can open and edit on excalidraw.com (hand-drawn style), and rendered SVG/PNG. Zero network. Embed the source in markdown and /make-pdf renders it.

The same /qa and /qa-only commands test CLIs, APIs, jobs, workers and webhooks with no browser: QA without a webpage.

Which review should I use?

Building for... Plan stage (before code) Live audit (after shipping)
End users (UI, web app, mobile) /plan-design-review /design-review
Developers (API, CLI, SDK, docs) /plan-devex-review /devex-review
Architecture (data flow, perf, tests) /plan-eng-review /review
All of the above /autoplan (runs CEO → design → DX → eng, auto-detects which apply; eng always last) —

Power tools

Skill What it does
/codex Second Opinion — independent code review from OpenAI Codex CLI. Review, challenge, and consult modes. Available on every harness except Codex.
/claude-code Second Opinion — independent code review from Claude Code. Review, challenge, and consult modes, with session continuity for consultation. Available on every harness except Claude Code.
/careful Safety Guardrails — warns before destructive commands (rm -rf, DROP TABLE, force-push). Say "be careful" to activate. Override any MEDIUM warning; root/home recursive deletes and default-branch force-pushes are hard-denied.
/freeze Edit Lock — restrict file edits to one directory. Prevents accidental changes outside scope while debugging.
/guard Full Safety — /careful + /freeze in one command. Maximum safety for prod work.
/unfreeze Unlock — remove the /freeze boundary.
/open-gstack-browser GStack Browser — launch gstack's own browser headed, with sidebar, anti-bot stealth, auto model routing (Sonnet for actions, Opus for analysis), one-click cookie import, and Claude Code integration. Clean up pages, take smart screenshots, edit CSS, and pass info back to your terminal. The visible face of the fallback engine; with Aside open you watch the agent's tabs there instead.
/setup-deploy Deploy Configurator — one-time setup for /land-and-deploy. Detects your platform, production URL, and deploy commands.
/setup-gbrain GBrain Onboarding — from zero to running gbrain in under 5 minutes. PGLite local, Supabase existing URL, or auto-provision a new Supabase project via Management API. MCP registration for Claude Code + per-repo trust triad (read-write/read-only/deny). Full guide.
/sync-gbrain Keep Brain Current — re-index this repo's code into gbrain via gbrain sources add + gbrain sync --strategy code, refresh the ## GBrain Search Guidance block in CLAUDE.md, and auto-remove guidance when the capability check fails. --incremental (default), --full, --dry-run. Idempotent; safe to re-run.
/gstack-upgrade Self-Updater — upgrade gstack to latest. Detects global vs vendored install, syncs both, shows what changed.
/captain Crew Controller (Capy only: gstack on Capy) — run many coding agents from one controller: lanes send a READY block and never merge, the controller merges through trains (stamp on call, verify, merge with the expected head), keeps the digest, relays approvals in a fixed shape and runs a daily flaky-fix pass. Also answers to /crew. Team guide.
/ios-qa iOS Live-Device QA (v1.43.0.0+) — drive a real iPhone or iPad over USB CoreDevice via an embedded StateServer in the app. Read Swift source, codegen typed @Observable accessors, run the agent loop. Optional --tailnet flag exposes the device to OpenClaw or any HTTP-capable agent on your Tailscale tailnet so remote agents can run iOS QA without ever touching the hardware. Capability-tier allowlist (observe/interact/mutate/restore), per-device session lock, audit log.
/ios-fix, /ios-design-review, /ios-clean, /ios-sync iOS bug-fix loop, designer's-eye HIG audit, debug-bridge cleanup, and accessor resync. See docs/skills.md. End-to-end walkthrough: docs/howto-ios-testing-with-gstack.md.

Beyond the slash commands, gstack ships standalone CLIs (gstack-egress, gstack-context-bill, gstack-model-benchmark, gstack-pr-wait, the review and evidence ledgers, the iOS QA daemon): docs/standalone-binaries.md. The fallback browser's per-site domain skills and raw CDP escape hatch, and the voice-input aliases many skills carry, have their own pages.

Deep dives with examples and philosophy for every skill →

GBrain — persistent knowledge for your coding agent

GBrain is a persistent knowledge base for AI agents — think of it as the memory your agent actually keeps between sessions. GStack gives you a one-command path from zero to "it's running, my agent can call it."

/setup-gbrain

The four setup paths, the per-repo trust policy and memory sync, in brief: docs/gbrain-quick-tour.md. Full monty — every scenario, every flag, every bin helper, every troubleshooting step: USING_GBRAIN_WITH_GSTACK.md

Other references: docs/gbrain-sync.md (sync-specific guide) • docs/gbrain-sync-errors.md (error index)

gstack on Capy

On a Capy machine, ./setup also loads gstack's crew tools: /captain to run many agent threads from one controller, a merge queue that lands verified pull requests, receipts that tie each merge to the head that was reviewed and tested, and spend caps for /ship and /autoplan. They live in crew/ and load only on Capy, so any other install is unchanged by them.

Platform notes

macOS and Linux get full support. Windows and Gemini models get minimal support: install and the core skills work, and nothing more is promised. See support tiers.

macOS: everything runs. With the Aside browser (macOS 15+) open and signed in, the browser skills, /make-pdf and /diagram use it and your real sessions; otherwise they use the bundled browser ./setup builds. gstack never installs Aside.

Linux: everything runs on the bundled browser; Aside is macOS-only, so the readiness probe says NEEDS_ASIDE: Linux once and the skills use gstack's own Chromium. If Chromium installs but cannot launch because the host blocks unprivileged user namespaces (Ubuntu 24.04+ AppArmor default), set GSTACK_CHROMIUM_NO_SANDBOX=1.

Windows users: gstack works on Windows 11 via Git Bash or WSL. Aside is macOS-only, so on Windows (and Linux) the browser skills, /make-pdf, and /diagram always use gstack's bundled browser. Node.js is required in addition to Bun — Bun has a known bug with Playwright's pipe transport on Windows (bun#4253). The browse server automatically falls back to Node.js. Make sure both bun and node are on your PATH. Native /cso additionally requires PowerShell (PowerShell 7 pwsh is preferred; Windows PowerShell 5.1 is the fallback) and Visual Studio 2022 Build Tools with the Desktop development with C++ workload; setup leaves that skill explicitly unavailable when they are absent. /cso is optional: if its native helper fails to build or publish, setup still finishes, says which step failed with the log path and retry command, and keeps an earlier helper when it has one (GSTACK_STRICT_BUILD=1 makes that failure fatal, as CI does).

Known issue: Windows Smart App Control (#2595). gstack's compiled binaries (browse, find-browse, design, pdf, gstack-global-discover) are built on your machine and unsigned, so Windows 11 with Smart App Control on refuses to start them; Git Bash shows Permission denied. setup detects this, names the blocked binaries and the skills that need them, and gstack-doctor reports them as blocked. Today's workarounds are running gstack inside WSL, or turning Smart App Control off. Details: troubleshooting. The sidebar terminal uses Consolas on Windows, so its text no longer renders spaced out.

From PowerShell, .\setup.ps1 (same arguments as ./setup) checks that Git for Windows, Bun and Node.js are on PATH, prints the winget command for any that are missing, and otherwise runs ./setup in Git Bash.

On Windows without Developer Mode (MSYS2 / Git Bash), setup falls back to file copies instead of symlinks because ln -snf produces frozen copies that don't refresh on git pull. Re-run cd ~/.claude/skills/gstack && ./setup after every git pull so your skill files match the repo. setup prints a one-line note reminding you. Unix and WSL keep symlinks and don't need the re-run.

Docs

Doc What it covers
Skill Deep Dives Philosophy, examples, and workflow for every skill (includes review-bot triage for Greptile, CodeRabbit and other bots)
The recommended harness gstack + Capy from zero to the first merged train: install, the Captain and its Drive, trains, the daily flaky pass, the twice-weekly release, the factory scorecard, what is Capy-specific, known Capy limits
gstack + Capy: the software factory What we built with Capy Captains and gstack, how the pieces fit, the measured before/after, tips, and how Garry uses it
Why gstack The story, the productivity numbers and their caveats, Karpathy's failure modes, parallel sprints
Install details Setup timing, requirements in detail, team mode, the hooks setup registers, agent harness registration
Other agents Agent harnesses (OpenClaw, Hermes, dots, QM, Muse Code, Grok, any other), OpenClaw and ClawHub, per-host notes, the Codex profile and model tiers, outside-review providers, the design binary's models
QA without a webpage /qa and /qa-only on CLIs, APIs, jobs, workers and webhooks
Standalone binaries The standalone gstack-* CLIs (egress auditor, context bill, model benchmark, the review and evidence ledgers, the iOS QA daemon), and the CSO evaluation producer contract
Privacy & Telemetry What is sent, what never is, the update check, outside reviews, egress receipts
Uninstall The uninstall script and manual removal
Diagrams & Document Formats Mermaid/excalidraw fences in PDFs, image sizing and safety defaults, --to html|docx, /diagram triplets
Preview a frontend The loopback preview with canned API answers that /design-review --build checks, its fixtures, the state inventory, and the gstack-design-build receipt
First Production Deploy What to do when /setup-deploy says nothing is deployed yet: hosting, env and secrets, DNS, checking it works, then back to /setup-deploy
Land a fix in someone else's repo Read their rules, search for the same fix, run every guard their CI runs before opening, keep it small, answer each review point in a new commit
Run a human playtest Ask about moments and where people would stop, and why a back-to-back pick between two builds measures the order, not the build
Builder Ethos Builder philosophy: Boil the Ocean, Search Before Building, three layers of knowledge
GBrain quick tour The four setup paths, MCP registration, the per-repo trust policy, memory sync, Conductor env vars
Using GBrain with GStack Every path, flag, bin helper, and troubleshooting step for /setup-gbrain
GBrain Sync Cross-machine memory setup, privacy modes, troubleshooting
Architecture Design decisions and system internals
Browser How gstack drives Aside first (the contract, the cookbook, rendering, research), when the fallback engine kicks in, and the fallback's full $B command reference
Contributing Dev setup, testing, contributor mode, and dev mode
Memorable recall bridge Opt-in third-party workflow memory through gstack: two consents, what gstack hands over and can attest, removal, troubleshooting
Troubleshooting Every not run / unavailable message, what it means, and the fix
Running a Captain crew One controller, many lanes on Capy: the drive layout, CREW.md, the READY contract, merge trains, approvals, the digest and the daily flaky pass, with templates
Changelog What's new in every version

Privacy & Telemetry

gstack sends nothing about how you use it unless you opt in. Telemetry is off by default and asked about once; the update check (two or three GitHub requests: a git ls-remote, a fetch of VERSION and, when that version equals yours but main has moved, a compare-API call; with telemetry on it also reports your gstack version and OS; on by default) turns off with gstack-config set update_check false; outside reviews (on by default; the first one prints a notice) send code to Codex or Claude Code under your own login and turn off with gstack-config set codex_reviews disabled. Every off-machine send writes a receipt you can audit with gstack-egress list. The full account, including the exact fields telemetry carries and the local state that is not telemetry: docs/privacy.md.

Troubleshooting

Not sure what's wrong? Run the doctor: ~/.claude/skills/gstack/bin/gstack-doctor (on other hosts, ./setup --status in your gstack checkout ends with the doctor's absolute path). Without starting a skill or spending anything, it prints one row per check (install, state root, Bun, hooks, Codex and its cached model probe, artifacts sync, the browse bundle, the other compiled binaries, the /cso native helper, Claude Code, your largest session journal and recent /autoplan guard codes), each ok, warn, not configured or fail with the command that fixes it. It exits non-zero only on fail. --live also runs the paid Codex model check (one short call). Paste its output into bug reports.

A message says not run, unavailable or names a fix? Look it up in docs/troubleshooting.md: every gate message gstack prints, what it means, what was kept, and the command that fixes it.

Claude says it can't see the skills? Check that they are installed (ls ~/.claude/skills) and restart Claude Code; it lists every installed skill with its description, so CLAUDE.md does not need to enumerate them (a pasted list goes stale with each release). Your project's CLAUDE.md only needs the browsing rule:

## gstack
Use /browse from gstack for all web browsing. Never use mcp__claude-in-chrome__* tools.

If an older install prompt left an "Available skills:" line in your CLAUDE.md, delete it.

Skill not showing up, stale install, Codex skill descriptions, prefix modes, disabling skills, Chromium install problems: quick answers.


Free, MIT licensed, open source. No premium tier, no waitlist.

I open sourced how I build software. You can fork it and make it your own.

We're hiring. Want to ship real products at AI-coding speed and help harden gstack? Come work at YC — ycombinator.com/software Extremely competitive salary and equity. San Francisco, Dogpatch District.

License

MIT. Free forever. Go build something.

View on GitHub

Recent activity

commits and pull requests

Releases and announcements

13 total
  1. gstack v1.100.0.0v1.100.0.0Nov 17, 2026

    # gstack v1.100.0.0 This release fixes five security advisories in a dependency, makes gstack's shell locks safe on Ubuntu 26.04, and changes how /ship writes and reviews pull requests. One optional hook check is removed. ## Fixes - Security: hono is pinned to 4.13.16, which fixes five advisories (GHSA-3gg2-335m-rxc6, GHSA-46wx-v44x-9hh2, GHSA-4h7h-rv7c-7m2v, GHSA-4m76-xfj5-7975, GHSA-h7mg-cq63-vhpq) found in 4.13.13. hono reaches gstack only through its development and test tools, and gstack's own code never uses it, so none of the five was reachable; contributors get the fix on their next `bun install`. (#4408) - gstack's shell locks admit exactly one holder again on Ubuntu 26.04 and GitHub's current `ubuntu-latest`, whose Rust `mkdir` reports success even when another process created the directory first. Before this, two updates could move one checkout at once, or two `gstack-config set` calls could drop each other's keys. (#4262) - /ship's documentation check no longer wastes one of its two attempts when the checking model writes text after its result line; it is asked once, for free, to resend the result alone. (#4285) - Once any result line in that documentation check says

  2. gstack v1.99.5.0v1.99.5.0Nov 16, 2026

    ## gstack v1.99.5.0 The standalone /plan-eng-review command is back, plus a clearer error from `gstack-redact` and a plain guide to how outside contributions land. ### What's new - `/plan-eng-review` is back as its own command on every host that had it, including Claude Code, Codex and OpenClaw, and requests like "review the architecture" route to it again. /autoplan works exactly as before [#4375](https://github.com/garrytan/gstack/pull/4375). ### Fixes - `gstack-redact` now says up front that input over 16 MiB is always refused: `--help` and both "too large" errors name the limit, say `--max-bytes` can't raise it, and suggest splitting the input. Reported by @exGeni and first fixed by @ElNeMeR70 [#4373](https://github.com/garrytan/gstack/pull/4373). ### Changes for maintainers - CONTRIBUTING.md now explains how outside reports and PRs land: the three paths a PR can take, the 48-hour first-reply goal, and the open-PR limit, which never applies to anyone with a PR taken in the last 90 days [#4374](https://github.com/garrytan/gstack/pull/4374). **Upgrade:** if an earlier upgrade removed `/plan-eng-review`, run `./setup` (or upgrade gstack) and it comes back. [Compare v1.99.

  3. gstack v1.99.4.0v1.99.4.0Nov 15, 2026

    ## gstack v1.99.4.0 Mostly /ship, gstack's command that reviews, tests and opens a pull request for you: its second-model review now survives a provider refusal, and gbrain users with a custom brain folder get the right brain again. ### What's new - When OpenAI refuses /ship's second-model review as a cyber-security risk, /ship on Capy now retries it once on GPT-6 Astra with a read-only correctness brief, then on Gemini 4 Carbon, and says plainly in the PR when the second read is still missing [#4350](https://github.com/garrytan/gstack/pull/4350). ### Fixes - gbrain setup and restore no longer write to the wrong brain when `GBRAIN_HOME` points at one brain and `~/.gbrain` holds another, and the start-of-skill sync hint now appears when your only config is under `GBRAIN_HOME` [#4343](https://github.com/garrytan/gstack/pull/4343). - /health and the other gbrain checks now read gbrain's config from `GBRAIN_HOME`, trimmed the way gbrain trims it, instead of only from `~/.gbrain` [#4344](https://github.com/garrytan/gstack/pull/4344). - /ship now runs test files in hidden folders such as `.github/scripts/` instead of failing on them as "no tests found" [#4348](https://github.com/gar

  4. gstack v1.99.3.0v1.99.3.0Nov 13, 2026

    ## gstack v1.99.3.0 Two fixes to /ship, gstack's command that reviews, tests and opens a pull request for you. ### Fixes - /ship's documentation check no longer refuses Next.js and SvelteKit route files whose paths hold square brackets, such as `app/api/items/[id]/route.ts` or `[...slug]`, so file-routed projects ship normally again [#4321](https://github.com/garrytan/gstack/pull/4321). - A pull request that changes only tests now gets one reviewer in /ship. Before, it got none, and /ship carried on as if the change had been reviewed [#4318](https://github.com/garrytan/gstack/pull/4318). ### Changes for maintainers - The brain-sync transcript tests no longer time out on a plain local `bun test`; they now use the same 30-second limit CI uses [#4322](https://github.com/garrytan/gstack/pull/4322). [Compare v1.99.2.0...v1.99.3.0](https://github.com/garrytan/gstack/compare/v1.99.2.0...v1.99.3.0) · [Full changelog](https://github.com/garrytan/gstack/blob/v1.99.3.0/CHANGELOG.md)

  5. gstack v1.99.2.0v1.99.2.0Nov 12, 2026

    ## gstack v1.99.2.0 Browser skills work again from non-Claude hosts, and the pre-push check for sealed test outputs now handles pull requests of any size. ### What's new - A repository can keep test folders that only run under a separate test tier (such as `tests/live/**`) out of /ship's local test run by declaring `[]` for that folder in `.gstack/pregate.json` [#4305](https://github.com/garrytan/gstack/pull/4305). ### Fixes - Browser skills and question preferences work again from Codex, Cursor and the other non-Claude hosts' gstack folders, instead of reporting that Playwright or a script is missing (thanks @SatriaSuriaAriffin, who found and reported both) [#4292](https://github.com/garrytan/gstack/pull/4292). - The pre-push hook's guard against publishing sealed test outputs now checks pull requests of any size instead of refusing very large ones, and its git error messages now say how git failed [#4300](https://github.com/garrytan/gstack/pull/4300). ### Changes for maintainers - An unattended /ship can now finish a PR whose gate change the owner approved, and the merge step must accept each such approval before it merges [#4304](https://github.com/garrytan/gstack/pull/43

Code frequency

additions and deletions
+168.4K-168.4KWeek of 2026-03-08: +24,615 linesWeek of 2026-03-08: -2,507 linesWeek of 2026-03-15: +56,032 linesWeek of 2026-03-15: -9,206 linesWeek of 2026-03-22: +56,112 linesWeek of 2026-03-22: -32,171 linesWeek of 2026-03-29: +65,504 linesWeek of 2026-03-29: -27,444 linesWeek of 2026-04-05: +18,636 linesWeek of 2026-04-05: -1,209 linesWeek of 2026-04-12: +22,142 linesWeek of 2026-04-12: -1,260 linesWeek of 2026-04-19: +75,493 linesWeek of 2026-04-19: -14,725 linesWeek of 2026-04-26: +29,638 linesWeek of 2026-04-26: -19,645 linesWeek of 2026-05-03: +18,289 linesWeek of 2026-05-03: -3,028 linesWeek of 2026-05-10: +12,621 linesWeek of 2026-05-10: -1,236 linesWeek of 2026-05-17: +22,582 linesWeek of 2026-05-17: -513 linesWeek of 2026-05-24: +45,997 linesWeek of 2026-05-24: -10,102 linesWeek of 2026-05-31: +8,057 linesWeek of 2026-05-31: -6,889 linesWeek of 2026-06-07: +23,537 linesWeek of 2026-06-07: -2,983 linesWeek of 2026-06-14: +3,937 linesWeek of 2026-06-14: -359 linesWeek of 2026-06-21: +4,673 linesWeek of 2026-06-21: -1,015 linesWeek of 2026-06-28: +0 linesWeek of 2026-06-28: -0 linesWeek of 2026-07-05: +917 linesWeek of 2026-07-05: -145 linesWeek of 2026-07-12: +6,326 linesWeek of 2026-07-12: -734 linesWeek of 2026-07-19: +0 linesWeek of 2026-07-19: -0 linesWeek of 2026-07-26: +0 linesWeek of 2026-07-26: -0 linesWeek of 2026-08-02: +1,759 linesWeek of 2026-08-02: -241 linesWeek of 2026-08-09: +38,405 linesWeek of 2026-08-09: -35,783 linesWeek of 2026-08-16: +29,134 linesWeek of 2026-08-16: -3,576 linesWeek of 2026-08-23: +32,771 linesWeek of 2026-08-23: -36,344 linesWeek of 2026-08-30: +16,662 linesWeek of 2026-08-30: -5,448 linesWeek of 2026-09-06: +27,531 linesWeek of 2026-09-06: -6,819 linesWeek of 2026-09-13: +153,959 linesWeek of 2026-09-13: -6,525 linesWeek of 2026-09-20: +164,438 linesWeek of 2026-09-20: -20,303 linesWeek of 2026-09-27: +168,422 linesWeek of 2026-09-27: -149,086 linesWeek of 2026-10-04: +140,535 linesWeek of 2026-10-04: -30,961 linesWeek of 2026-10-11: +60,640 linesWeek of 2026-10-11: -7,500 linesWeek of 2026-10-18: +34,905 linesWeek of 2026-10-18: -5,912 linesWeek of 2026-10-25: +142,454 linesWeek of 2026-10-25: -32,788 linesWeek of 2026-11-01: +119,265 linesWeek of 2026-11-01: -32,131 linesWeek of 2026-11-08: +40,523 linesWeek of 2026-11-08: -25,931 linesWeek of 2026-11-15: +9,406 linesWeek of 2026-11-15: -3,946 linesMar 8, 2026Nov 15, 2026
+1.7M lines added, -538.5K removed over the last year.

Commits per week

last 52 weeks
3280Week of 2025-11-23: 0 commitsWeek of 2025-11-30: 0 commitsWeek of 2025-12-07: 0 commitsWeek of 2025-12-14: 0 commitsWeek of 2025-12-21: 0 commitsWeek of 2025-12-28: 0 commitsWeek of 2026-01-04: 0 commitsWeek of 2026-01-11: 0 commitsWeek of 2026-01-18: 0 commitsWeek of 2026-01-25: 0 commitsWeek of 2026-02-01: 0 commitsWeek of 2026-02-08: 0 commitsWeek of 2026-02-15: 0 commitsWeek of 2026-02-22: 0 commitsWeek of 2026-03-01: 0 commitsWeek of 2026-03-08: 46 commitsWeek of 2026-03-15: 56 commitsWeek of 2026-03-22: 53 commitsWeek of 2026-03-29: 31 commitsWeek of 2026-04-05: 21 commitsWeek of 2026-04-12: 14 commitsWeek of 2026-04-19: 20 commitsWeek of 2026-04-26: 10 commitsWeek of 2026-05-03: 11 commitsWeek of 2026-05-10: 15 commitsWeek of 2026-05-17: 9 commitsWeek of 2026-05-24: 15 commitsWeek of 2026-05-31: 2 commitsWeek of 2026-06-07: 12 commitsWeek of 2026-06-14: 2 commitsWeek of 2026-06-21: 2 commitsWeek of 2026-06-28: 0 commitsWeek of 2026-07-05: 14 commitsWeek of 2026-07-12: 13 commitsWeek of 2026-07-19: 0 commitsWeek of 2026-07-26: 0 commitsWeek of 2026-08-02: 2 commitsWeek of 2026-08-09: 6 commitsWeek of 2026-08-16: 8 commitsWeek of 2026-08-23: 6 commitsWeek of 2026-08-30: 5 commitsWeek of 2026-09-06: 4 commitsWeek of 2026-09-13: 6 commitsWeek of 2026-09-20: 9 commitsWeek of 2026-09-27: 13 commitsWeek of 2026-10-04: 40 commitsWeek of 2026-10-11: 49 commitsWeek of 2026-10-18: 65 commitsWeek of 2026-10-25: 197 commitsWeek of 2026-11-01: 328 commitsWeek of 2026-11-08: 87 commitsWeek of 2026-11-15: 41 commitsNov 23, 2025Nov 15, 2026
1.2K commits in the last 52 weeks.

When work happens

weekday and hour
SunMonTueWedThuFriSat036912151821Sun 0:00 — 8 commitsSun 1:00 — 5 commitsSun 2:00 — 7 commitsSun 3:00 — 5 commitsSun 4:00 — 2 commitsSun 5:00 — 8 commitsSun 6:00 — 5 commitsSun 7:00 — 5 commitsSun 8:00 — 12 commitsSun 9:00 — 12 commitsSun 10:00 — 7 commitsSun 11:00 — 6 commitsSun 12:00 — 7 commitsSun 13:00 — 7 commitsSun 14:00 — 5 commitsSun 15:00 — 5 commitsSun 16:00 — 4 commitsSun 17:00 — 12 commitsSun 18:00 — 3 commitsSun 19:00 — 10 commitsSun 20:00 — 8 commitsSun 21:00 — 14 commitsSun 22:00 — 6 commitsSun 23:00 — 9 commitsMon 0:00 — 12 commitsMon 1:00 — 9 commitsMon 2:00 — 7 commitsMon 3:00 — 12 commitsMon 4:00 — 7 commitsMon 5:00 — 8 commitsMon 6:00 — 11 commitsMon 7:00 — 9 commitsMon 8:00 — 8 commitsMon 9:00 — 8 commitsMon 10:00 — 20 commitsMon 11:00 — 9 commitsMon 12:00 — 7 commitsMon 13:00 — 19 commitsMon 14:00 — 9 commitsMon 15:00 — 14 commitsMon 16:00 — 12 commitsMon 17:00 — 9 commitsMon 18:00 — 11 commitsMon 19:00 — 8 commitsMon 20:00 — 11 commitsMon 21:00 — 9 commitsMon 22:00 — 14 commitsMon 23:00 — 6 commitsTue 0:00 — 5 commitsTue 1:00 — 3 commitsTue 2:00 — 5 commitsTue 3:00 — 3 commitsTue 4:00 — 2 commitsTue 5:00 — 0 commitsTue 6:00 — 7 commitsTue 7:00 — 9 commitsTue 8:00 — 10 commitsTue 9:00 — 3 commitsTue 10:00 — 11 commitsTue 11:00 — 9 commitsTue 12:00 — 16 commitsTue 13:00 — 6 commitsTue 14:00 — 10 commitsTue 15:00 — 6 commitsTue 16:00 — 18 commitsTue 17:00 — 22 commitsTue 18:00 — 9 commitsTue 19:00 — 16 commitsTue 20:00 — 14 commitsTue 21:00 — 11 commitsTue 22:00 — 11 commitsTue 23:00 — 3 commitsWed 0:00 — 4 commitsWed 1:00 — 3 commitsWed 2:00 — 2 commitsWed 3:00 — 1 commitsWed 4:00 — 0 commitsWed 5:00 — 0 commitsWed 6:00 — 3 commitsWed 7:00 — 2 commitsWed 8:00 — 5 commitsWed 9:00 — 4 commitsWed 10:00 — 2 commitsWed 11:00 — 6 commitsWed 12:00 — 5 commitsWed 13:00 — 1 commitsWed 14:00 — 2 commitsWed 15:00 — 7 commitsWed 16:00 — 13 commitsWed 17:00 — 6 commitsWed 18:00 — 4 commitsWed 19:00 — 6 commitsWed 20:00 — 5 commitsWed 21:00 — 8 commitsWed 22:00 — 6 commitsWed 23:00 — 7 commitsThu 0:00 — 9 commitsThu 1:00 — 11 commitsThu 2:00 — 2 commitsThu 3:00 — 4 commitsThu 4:00 — 1 commitsThu 5:00 — 0 commitsThu 6:00 — 3 commitsThu 7:00 — 5 commitsThu 8:00 — 6 commitsThu 9:00 — 8 commitsThu 10:00 — 5 commitsThu 11:00 — 7 commitsThu 12:00 — 8 commitsThu 13:00 — 6 commitsThu 14:00 — 1 commitsThu 15:00 — 2 commitsThu 16:00 — 2 commitsThu 17:00 — 8 commitsThu 18:00 — 11 commitsThu 19:00 — 0 commitsThu 20:00 — 6 commitsThu 21:00 — 6 commitsThu 22:00 — 8 commitsThu 23:00 — 13 commitsFri 0:00 — 7 commitsFri 1:00 — 1 commitsFri 2:00 — 3 commitsFri 3:00 — 3 commitsFri 4:00 — 3 commitsFri 5:00 — 7 commitsFri 6:00 — 4 commitsFri 7:00 — 10 commitsFri 8:00 — 8 commitsFri 9:00 — 11 commitsFri 10:00 — 4 commitsFri 11:00 — 8 commitsFri 12:00 — 8 commitsFri 13:00 — 7 commitsFri 14:00 — 4 commitsFri 15:00 — 6 commitsFri 16:00 — 5 commitsFri 17:00 — 9 commitsFri 18:00 — 6 commitsFri 19:00 — 8 commitsFri 20:00 — 3 commitsFri 21:00 — 5 commitsFri 22:00 — 17 commitsFri 23:00 — 5 commitsSat 0:00 — 8 commitsSat 1:00 — 7 commitsSat 2:00 — 4 commitsSat 3:00 — 6 commitsSat 4:00 — 5 commitsSat 5:00 — 5 commitsSat 6:00 — 4 commitsSat 7:00 — 10 commitsSat 8:00 — 10 commitsSat 9:00 — 8 commitsSat 10:00 — 11 commitsSat 11:00 — 14 commitsSat 12:00 — 13 commitsSat 13:00 — 2 commitsSat 14:00 — 12 commitsSat 15:00 — 7 commitsSat 16:00 — 9 commitsSat 17:00 — 9 commitsSat 18:00 — 15 commitsSat 19:00 — 7 commitsSat 20:00 — 4 commitsSat 21:00 — 2 commitsSat 22:00 — 16 commitsSat 23:00 — 9 commits
Commit volume by weekday and hour (UTC). Larger dots mean more commits.

Who is committing

last 52 weeks
Maintainer commits1,151 (96%)
Community commits48 (4%)

1,199 commits in total over the last year.

DateListRankStars gained
Nov 6, 2026daily#2+608
Nov 5, 2026daily#2+608
Nov 4, 2026daily#7+285
Oct 5, 2026daily#10+121
Oct 4, 2026daily#10+121
Jun 24, 2026daily#19+16
Jun 23, 2026daily#20+7
Jun 20, 2026daily#23+22
May 26, 2026daily#14+64
May 25, 2026daily#23+47
May 17, 2026daily#24+83
May 15, 2026daily#18+66
May 14, 2026daily#18+58
May 13, 2026daily#17+63
May 11, 2026daily#18+112
  • morluto/rea

    Reverse engineer anything with agents, from app behavior down to native binaries.

    471.6K stars · TypeScript

  • freeCodeCamp/freeCodeCamp

    freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.

    459.4K stars · TypeScript

  • openclaw/openclaw

    The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

    394.9K stars · TypeScript

  • anomalyco/opencode

    The open source coding agent.

    228.3K stars · TypeScript

  • n8n-io/n8n

    Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

    211.6K stars · TypeScript

  • firecrawl/firecrawl

    Knowledge infrastructure to make your agents smarter. Search, scrape and access 550+ data providers through one API.

    205.3K stars · TypeScript