feat: install gstack from Claude Code marketplace

This allows users to install and update gstack through the native Claude Code plugin system:

```
/plugin marketplace add garrytan/gstack
/plugin install gstack@gstack-marketplace
```

- Add `.claude-plugin/` marketplace and plugin manifests
- Move skills into `skills/` directory for plugin auto-discovery
- Use `${CLAUDE_SKILL_DIR}` for portable paths
- Removes (now unneeded) setup script

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

.claude-plugin/marketplace.json

@@ -0,0 +1,21 @@
+{
+  "name": "gstack-marketplace",
+  "owner": {
+    "name": "Garry Tan",
+    "email": "garry@ycombinator.com"
+  },
+  "metadata": {
+    "description": "Garry's Stack — workflow skills for Claude Code. Plan review, code review, shipping, browser automation, and retrospectives.",
+    "version": "0.0.2"
+  },
+  "plugins": [
+    {
+      "name": "gstack",
+      "description": "Complete gstack bundle with all workflow skills: /plan-ceo-review (founder mode), /plan-eng-review (eng manager), /review (paranoid engineer), /ship (release automation), /browse (headless browser QA), /retro (weekly retrospective).",
+      "version": "0.0.2",
+      "homepage": "https://github.com/garrytan/gstack",
+      "license": "MIT",
+      "source": "./"
+    }
+  ]
+}

.claude-plugin/plugin.json

@@ -0,0 +1,13 @@
+{
+  "name": "gstack",
+  "description": "Complete gstack bundle with all workflow skills: /plan-ceo-review (founder mode), /plan-eng-review (eng manager), /review (paranoid engineer), /ship (release automation), /browse (headless browser QA), /retro (weekly retrospective).",
+  "version": "0.0.2",
+  "author": {
+    "name": "Garry Tan",
+    "email": "garry@ycombinator.com"
+  },
+  "homepage": "https://github.com/garrytan/gstack",
+  "repository": "https://github.com/garrytan/gstack",
+  "license": "MIT",
+  "keywords": ["workflow", "planning", "review", "shipping", "browser", "qa", "retrospective"]
+}

.gitignore

@@ -1,5 +1,5 @@
 node_modules/
-browse/dist/
+skills/browse/dist/
 /tmp/
 *.log
 bun.lock

CLAUDE.md

@@ -6,33 +6,32 @@
 bun install          # install dependencies
 bun test             # run integration tests (browse + snapshot)
 bun run dev <cmd>    # run CLI in dev mode, e.g. bun run dev goto https://example.com
-bun run build        # compile binary to browse/dist/browse
+bun run build        # compile binary to skills/browse/dist/browse
 ```
 
 ## Project structure
 
 ```
 gstack/
-├── browse/          # Headless browser CLI (Playwright)
+├── .claude-plugin/  # Plugin marketplace config
-│   ├── src/         # CLI + server + commands
+│   ├── plugin.json  # Plugin manifest
-│   ├── test/        # Integration tests + fixtures
+│   └── marketplace.json
-│   └── dist/        # Compiled binary
+├── skills/          # All skills (auto-discovered by plugin system)
-├── ship/            # Ship workflow skill
+│   ├── browse/      # Headless browser CLI (Playwright)
-├── review/          # PR review skill
+│   │   ├── src/     # CLI + server + commands
-├── plan-ceo-review/ # /plan-ceo-review skill
+│   │   ├── test/    # Integration tests + fixtures
-├── plan-eng-review/ # /plan-eng-review skill
+│   │   └── dist/    # Compiled binary
-├── retro/           # Retrospective skill
+│   ├── ship/        # Ship workflow skill
-├── setup            # One-time setup: build binary + symlink skills
+│   ├── review/      # PR review skill
-├── SKILL.md         # Browse skill (Claude discovers this)
+│   ├── plan-ceo-review/ # /plan-ceo-review skill
+│   ├── plan-eng-review/ # /plan-eng-review skill
+│   └── retro/       # Retrospective skill
 └── package.json     # Build scripts for browse
 ```
 
-## Deploying to the active skill
+## Installation
 
-The active skill lives at `~/.claude/skills/gstack/`. After making changes:
+```
-
+/plugin marketplace add garrytan/gstack
-1. Push your branch
+/plugin install gstack@gstack-marketplace
-2. Fetch and reset in the skill directory: `cd ~/.claude/skills/gstack && git fetch origin && git reset --hard origin/main`
+```
-3. Rebuild: `cd ~/.claude/skills/gstack && bun run build`
-
-Or copy the binary directly: `cp browse/dist/browse ~/.claude/skills/gstack/browse/dist/browse`

SKILL.md

@@ -1,254 +0,0 @@
----
-name: gstack
-version: 1.0.0
-description: |
-  Fast web browsing for Claude Code via persistent headless Chromium daemon. Navigate to any URL,
-  read page content, click elements, fill forms, run JavaScript, take screenshots,
-  inspect CSS/DOM, capture console/network logs, and more. ~100ms per command after
-  first call. Use when you need to check a website, verify a deployment, read docs,
-  or interact with any web page. No MCP, no Chrome extension — just fast CLI.
-allowed-tools:
-  - Bash
-  - Read
-
----
-
-# gstack: Persistent Browser for Claude Code
-
-Persistent headless Chromium daemon. First call auto-starts the server (~3s).
-Every subsequent call: ~100-200ms. Auto-shuts down after 30 min idle.
-
-## SETUP (run this check BEFORE any browse command)
-
-Before using any browse command, find the skill and check if the binary exists:
-
-```bash
-# Check project-level first, then user-level
-if test -x .claude/skills/gstack/browse/dist/browse; then
-  echo "READY_PROJECT"
-elif test -x ~/.claude/skills/gstack/browse/dist/browse; then
-  echo "READY_USER"
-else
-  echo "NEEDS_SETUP"
-fi
-```
-
-Set `B` to whichever path is READY and use it for all commands. Prefer project-level if both exist.
-
-If `NEEDS_SETUP`:
-1. Tell the user: "gstack browse needs a one-time build (~10 seconds). OK to proceed?" Then STOP and wait for their response.
-2. If they approve, determine the skill directory (project-level `.claude/skills/gstack` or user-level `~/.claude/skills/gstack`) and run:
-```bash
-cd <SKILL_DIR> && ./setup
-```
-3. If `bun` is not installed, tell the user to install it: `curl -fsSL https://bun.sh/install | bash`
-4. Verify the `.gitignore` in the skill directory contains `browse/dist/` and `node_modules/`. If either line is missing, add it.
-
-Once setup is done, it never needs to run again (the compiled binary persists).
-
-## IMPORTANT
-
-- Use the compiled binary via Bash: `.claude/skills/gstack/browse/dist/browse` (project) or `~/.claude/skills/gstack/browse/dist/browse` (user).
-- NEVER use `mcp__claude-in-chrome__*` tools. They are slow and unreliable.
-- The browser persists between calls — cookies, tabs, and state carry over.
-- The server auto-starts on first command. No setup needed.
-
-## Quick Reference
-
-```bash
-B=~/.claude/skills/gstack/browse/dist/browse
-
-# Navigate to a page
-$B goto https://example.com
-
-# Read cleaned page text
-$B text
-
-# Take a screenshot (then Read the image)
-$B screenshot /tmp/page.png
-
-# Snapshot: accessibility tree with refs
-$B snapshot -i
-
-# Click by ref (after snapshot)
-$B click @e3
-
-# Fill by ref
-$B fill @e4 "test@test.com"
-
-# Run JavaScript
-$B js "document.title"
-
-# Get all links
-$B links
-
-# Click by CSS selector
-$B click "button.submit"
-
-# Fill a form by CSS selector
-$B fill "#email" "test@test.com"
-$B fill "#password" "abc123"
-$B click "button[type=submit]"
-
-# Get HTML of an element
-$B html "main"
-
-# Get computed CSS
-$B css "body" "font-family"
-
-# Get element attributes
-$B attrs "nav"
-
-# Wait for element to appear
-$B wait ".loaded"
-
-# Accessibility tree
-$B accessibility
-
-# Set viewport
-$B viewport 375x812
-
-# Set cookies / headers
-$B cookie "session=abc123"
-$B header "Authorization:Bearer token123"
-```
-
-## Command Reference
-
-### Navigation
-```
-browse goto <url>         Navigate current tab
-browse back               Go back
-browse forward            Go forward
-browse reload             Reload page
-browse url                Print current URL
-```
-
-### Content extraction
-```
-browse text               Cleaned page text (no scripts/styles)
-browse html [selector]    innerHTML of element, or full page HTML
-browse links              All links as "text → href"
-browse forms              All forms + fields as JSON
-browse accessibility      Accessibility tree snapshot (ARIA)
-```
-
-### Snapshot (ref-based element selection)
-```
-browse snapshot           Full accessibility tree with @refs
-browse snapshot -i        Interactive elements only (buttons, links, inputs)
-browse snapshot -c        Compact (no empty structural elements)
-browse snapshot -d <N>    Limit depth to N levels
-browse snapshot -s <sel>  Scope to CSS selector
-```
-
-After snapshot, use @refs as selectors in any command:
-```
-browse click @e3          Click the element assigned ref @e3
-browse fill @e4 "value"   Fill the input assigned ref @e4
-browse hover @e1          Hover the element assigned ref @e1
-browse html @e2           Get innerHTML of ref @e2
-browse css @e5 "color"    Get computed CSS of ref @e5
-browse attrs @e6          Get attributes of ref @e6
-```
-
-Refs are invalidated on navigation — run `snapshot` again after `goto`.
-
-### Interaction
-```
-browse click <selector>        Click element (CSS selector or @ref)
-browse fill <selector> <value> Fill input field
-browse select <selector> <val> Select dropdown value
-browse hover <selector>        Hover over element
-browse type <text>             Type into focused element
-browse press <key>             Press key (Enter, Tab, Escape, etc.)
-browse scroll [selector]       Scroll element into view, or page bottom
-browse wait <selector>         Wait for element to appear (max 10s)
-browse viewport <WxH>          Set viewport size (e.g. 375x812)
-```
-
-### Inspection
-```
-browse js <expression>         Run JS, print result
-browse eval <js-file>          Run JS file against page
-browse css <selector> <prop>   Get computed CSS property
-browse attrs <selector>        Get element attributes as JSON
-browse console                 Dump captured console messages
-browse console --clear         Clear console buffer
-browse network                 Dump captured network requests
-browse network --clear         Clear network buffer
-browse cookies                 Dump all cookies as JSON
-browse storage                 localStorage + sessionStorage as JSON
-browse storage set <key> <val> Set localStorage value
-browse perf                    Page load performance timings
-```
-
-### Visual
-```
-browse screenshot [path]       Screenshot (default: /tmp/browse-screenshot.png)
-browse pdf [path]              Save as PDF
-browse responsive [prefix]     Screenshots at mobile/tablet/desktop
-```
-
-### Compare
-```
-browse diff <url1> <url2>      Text diff between two pages
-```
-
-### Multi-step (chain)
-```
-echo '[["goto","https://example.com"],["snapshot","-i"],["click","@e1"],["screenshot","/tmp/result.png"]]' | browse chain
-```
-
-### Tabs
-```
-browse tabs                    List tabs (id, url, title)
-browse tab <id>                Switch to tab
-browse newtab [url]            Open new tab
-browse closetab [id]           Close tab
-```
-
-### Server management
-```
-browse status                  Server health, uptime, tab count
-browse stop                    Shutdown server
-browse restart                 Kill + restart server
-```
-
-## Speed Rules
-
-1. **Navigate once, query many times.** `goto` loads the page; then `text`, `js`, `css`, `screenshot` all run against the loaded page instantly.
-2. **Use `snapshot -i` for interaction.** Get refs for all interactive elements, then click/fill by ref. No need to guess CSS selectors.
-3. **Use `js` for precision.** `js "document.querySelector('.price').textContent"` is faster than parsing full page text.
-4. **Use `links` to survey.** Faster than `text` when you just need navigation structure.
-5. **Use `chain` for multi-step flows.** Avoids CLI overhead per step.
-6. **Use `responsive` for layout checks.** One command = 3 viewport screenshots.
-
-## When to Use What
-
-| Task | Commands |
-|------|----------|
-| Read a page | `goto <url>` then `text` |
-| Interact with elements | `snapshot -i` then `click @e3` |
-| Check if element exists | `js "!!document.querySelector('.thing')"` |
-| Extract specific data | `js "document.querySelector('.price').textContent"` |
-| Visual check | `screenshot /tmp/x.png` then Read the image |
-| Fill and submit form | `snapshot -i` → `fill @e4 "val"` → `click @e5` → `screenshot` |
-| Check CSS | `css "selector" "property"` or `css @e3 "property"` |
-| Inspect DOM | `html "selector"` or `attrs @e3` |
-| Debug console errors | `console` |
-| Check network requests | `network` |
-| Check local dev | `goto http://127.0.0.1:3000` |
-| Compare two pages | `diff <url1> <url2>` |
-| Mobile layout check | `responsive /tmp/prefix` |
-| Multi-step flow | `echo '[...]' \| browse chain` |
-
-## Architecture
-
-- Persistent Chromium daemon on localhost (port 9400-9410)
-- Bearer token auth per session
-- State file: `/tmp/browse-server.json`
-- Console log: `/tmp/browse-console.log`
-- Network log: `/tmp/browse-network.log`
-- Auto-shutdown after 30 min idle
-- Chromium crash → server exits → auto-restarts on next command

package.json

@@ -5,14 +5,14 @@
   "license": "MIT",
   "type": "module",
   "bin": {
-    "browse": "./browse/dist/browse"
+    "browse": "./skills/browse/dist/browse"
   },
   "scripts": {
-    "build": "bun build --compile browse/src/cli.ts --outfile browse/dist/browse",
+    "build": "bun build --compile skills/browse/src/cli.ts --outfile skills/browse/dist/browse",
-    "dev": "bun run browse/src/cli.ts",
+    "dev": "bun run skills/browse/src/cli.ts",
-    "server": "bun run browse/src/server.ts",
+    "server": "bun run skills/browse/src/server.ts",
     "test": "bun test",
-    "start": "bun run browse/src/server.ts"
+    "start": "bun run skills/browse/src/server.ts"
   },
   "dependencies": {
     "playwright": "^1.58.2",

setup

@@ -1,62 +0,0 @@
-#!/usr/bin/env bash
-# gstack setup — build browser binary + register all skills with Claude Code
-set -e
-
-GSTACK_DIR="$(cd "$(dirname "$0")" && pwd)"
-SKILLS_DIR="$(dirname "$GSTACK_DIR")"
-BROWSE_BIN="$GSTACK_DIR/browse/dist/browse"
-
-# 1. Build browse binary if needed
-NEEDS_BUILD=0
-if [ ! -x "$BROWSE_BIN" ]; then
-  NEEDS_BUILD=1
-elif [ -n "$(find "$GSTACK_DIR/browse/src" -type f -newer "$BROWSE_BIN" -print -quit 2>/dev/null)" ]; then
-  NEEDS_BUILD=1
-elif [ "$GSTACK_DIR/package.json" -nt "$BROWSE_BIN" ]; then
-  NEEDS_BUILD=1
-elif [ -f "$GSTACK_DIR/bun.lock" ] && [ "$GSTACK_DIR/bun.lock" -nt "$BROWSE_BIN" ]; then
-  NEEDS_BUILD=1
-fi
-
-if [ "$NEEDS_BUILD" -eq 1 ]; then
-  echo "Building browse binary..."
-  (
-    cd "$GSTACK_DIR"
-    bun install
-    bun run build
-  )
-fi
-
-if [ ! -x "$BROWSE_BIN" ]; then
-  echo "gstack setup failed: browse binary missing at $BROWSE_BIN" >&2
-  exit 1
-fi
-
-# 2. Only create skill symlinks if we're inside a .claude/skills directory
-SKILLS_BASENAME="$(basename "$SKILLS_DIR")"
-if [ "$SKILLS_BASENAME" = "skills" ]; then
-  linked=()
-  for skill_dir in "$GSTACK_DIR"/*/; do
-    if [ -f "$skill_dir/SKILL.md" ]; then
-      skill_name="$(basename "$skill_dir")"
-      # Skip node_modules
-      [ "$skill_name" = "node_modules" ] && continue
-      target="$SKILLS_DIR/$skill_name"
-      # Create or update symlink; skip if a real file/directory exists
-      if [ -L "$target" ] || [ ! -e "$target" ]; then
-        ln -snf "gstack/$skill_name" "$target"
-        linked+=("$skill_name")
-      fi
-    fi
-  done
-
-  echo "gstack ready."
-  echo "  browse: $BROWSE_BIN"
-  if [ ${#linked[@]} -gt 0 ]; then
-    echo "  linked skills: ${linked[*]}"
-  fi
-else
-  echo "gstack ready."
-  echo "  browse: $BROWSE_BIN"
-  echo "  (skipped skill symlinks — not inside .claude/skills/)"
-fi

skills/browse/SKILL.md

@@ -20,35 +20,31 @@ Every subsequent call: ~100-200ms. Auto-shuts down after 30 min idle.
 
 ## SETUP (run this check BEFORE any browse command)
 
-Before using any browse command, find the skill and check if the binary exists:
+Before using any browse command, check if the binary exists:
 
 ```bash
-# Check project-level first, then user-level
+if test -x "${CLAUDE_SKILL_DIR}/dist/browse"; then
-if test -x .claude/skills/gstack/browse/dist/browse; then
+  echo "READY"
-  echo "READY_PROJECT"
-elif test -x ~/.claude/skills/gstack/browse/dist/browse; then
-  echo "READY_USER"
 else
-  echo "NEEDS_SETUP"
+  echo "NEEDS_BUILD"
 fi
 ```
 
-Set `B` to whichever path is READY and use it for all commands. Prefer project-level if both exist.
+Set `B` to the binary path: `B="${CLAUDE_SKILL_DIR}/dist/browse"`
 
-If `NEEDS_SETUP`:
+If `NEEDS_BUILD`:
 1. Tell the user: "gstack browse needs a one-time build (~10 seconds). OK to proceed?" Then STOP and wait for their response.
-2. If they approve, determine the skill directory (project-level `.claude/skills/gstack` or user-level `~/.claude/skills/gstack`) and run:
+2. If they approve, run:
 ```bash
-cd <SKILL_DIR> && ./setup
+cd "${CLAUDE_SKILL_DIR}" && bun install && bun build --compile src/cli.ts --outfile dist/browse
 ```
 3. If `bun` is not installed, tell the user to install it: `curl -fsSL https://bun.sh/install | bash`
-4. Verify the `.gitignore` in the skill directory contains `browse/dist/` and `node_modules/`. If either line is missing, add it.
 
-Once setup is done, it never needs to run again (the compiled binary persists).
+Once built, the compiled binary persists across sessions.
 
 ## IMPORTANT
 
-- Use the compiled binary via Bash: `.claude/skills/gstack/browse/dist/browse` (project) or `~/.claude/skills/gstack/browse/dist/browse` (user).
+- Use the compiled binary via Bash: `${CLAUDE_SKILL_DIR}/dist/browse`
 - NEVER use `mcp__claude-in-chrome__*` tools. They are slow and unreliable.
 - The browser persists between calls — cookies, tabs, and state carry over.
 - The server auto-starts on first command. No setup needed.
@@ -56,7 +52,7 @@ Once setup is done, it never needs to run again (the compiled binary persists).
 ## Quick Reference
 
 ```bash
-B=~/.claude/skills/gstack/browse/dist/browse
+B="${CLAUDE_SKILL_DIR}/dist/browse"
 
 # Navigate to a page
 $B goto https://example.com

skills/review/SKILL.md

@@ -30,7 +30,7 @@ You are running the `/review` workflow. Analyze the current branch's diff agains
 
 ## Step 2: Read the checklist
 
-Read `.claude/skills/review/checklist.md`.
+Read `${CLAUDE_SKILL_DIR}/checklist.md`.
 
 **If the file cannot be read, STOP and report the error.** Do not proceed without the checklist.
 

skills/ship/SKILL.md

@@ -145,7 +145,7 @@ If multiple suites need to run, run them sequentially (each needs a test lane).
 
 Review the diff for structural issues that tests don't catch.
 
-1. Read `.claude/skills/review/checklist.md`. If the file cannot be read, **STOP** and report the error.
+1. Read `${CLAUDE_SKILL_DIR}/../review/checklist.md`. If the file cannot be read, **STOP** and report the error.
 
 2. Run `git diff origin/main` to get the full diff (scoped to feature changes against the freshly-fetched remote main).