@aarwitz/tapp 0.17.0-rc.11 → 0.17.0-rc.13

package/.claude-plugin/marketplace.json

@@ -0,0 +1,34 @@
+{
+  "name": "tapp",
+  "description": "The official Tapp plugin: one agent skill and MCP tools for testing iOS, Android, and web apps on real surfaces.",
+  "owner": {
+    "name": "Aaron Horowitz",
+    "url": "https://github.com/aarwitz"
+  },
+  "plugins": [
+    {
+      "name": "tapp",
+      "source": {
+        "source": "npm",
+        "package": "@aarwitz/tapp"
+      },
+      "description": "Test real iOS, Android, and web apps with Tapp. Includes the Tapp agent skill plus MCP hands, eyes, exploration, replayable Flows, and deterministic release evidence.",
+      "author": {
+        "name": "Aaron Horowitz",
+        "url": "https://github.com/aarwitz"
+      },
+      "homepage": "https://github.com/aarwitz/tapp",
+      "license": "MIT",
+      "keywords": [
+        "ios",
+        "simulator",
+        "testing",
+        "qa",
+        "xcuitest",
+        "mcp",
+        "agent-skill",
+        "copilot"
+      ]
+    }
+  ]
+}

package/.claude-plugin/plugin.json

@@ -0,0 +1,33 @@
+{
+  "name": "tapp",
+  "description": "Test real iOS, Android, and web apps with Tapp. Includes the Tapp agent skill plus MCP hands, eyes, exploration, replayable Flows, and deterministic release evidence.",
+  "version": "0.17.0-rc.13",
+  "author": {
+    "name": "Aaron Horowitz",
+    "url": "https://github.com/aarwitz"
+  },
+  "homepage": "https://github.com/aarwitz/tapp",
+  "repository": "https://github.com/aarwitz/tapp",
+  "license": "MIT",
+  "keywords": [
+    "ios",
+    "simulator",
+    "testing",
+    "qa",
+    "xcuitest",
+    "mcp",
+    "agent-skill",
+    "copilot"
+  ],
+  "mcpServers": {
+    "tapp": {
+      "command": "npx",
+      "args": [
+        "-y",
+        "@aarwitz/tapp@0.17.0-rc.13",
+        "mcp"
+      ],
+      "cwd": "${CLAUDE_PROJECT_DIR}"
+    }
+  }
+}

package/AGENTS.md

@@ -11,14 +11,15 @@ the app already on the simulator); it also accepts a repo dir, a `path/to/App.ap
 bundle id, or (web) an http(s) URL. You never need to know a bundle id up front.
 
 ```bash
-npx -y @aarwitz/tapp explore [target]     # autonomous exploration → findings + evidence (observation, not a gate; ≈ tapp_explore)
-npx -y @aarwitz/tapp open [target]   # launch + screen summary + screenshot saved to a file (≈ tapp_open_app)
-npx -y @aarwitz/tapp tree [target]   # accessibility tree, --json for every element (≈ tapp_ui_tree)
-npx -y @aarwitz/tapp shot            # screenshot the booted sim → file path (≈ tapp_screenshot)
-npx -y @aarwitz/tapp apps            # what's installed on the simulator, with bundle ids
-npx -y @aarwitz/tapp build [dir]     # build the app in an Xcode repo + install it (≈ tapp_build)
-npx -y @aarwitz/tapp explore app.apk --platform android --app-id com.acme.app
-npx -y @aarwitz/tapp flow run .tapp/flows/smoke.yml  # committed, keyless E2E replay
+npx -y @aarwitz/tapp@latest explore [target]     # autonomous exploration → findings + evidence (observation, not a gate; ≈ tapp_explore)
+npx -y @aarwitz/tapp@latest explore https://your-app.example --watch  # web: visibly follow the same exploration
+npx -y @aarwitz/tapp@latest open [target]   # launch + screen summary + screenshot saved to a file (≈ tapp_open_app)
+npx -y @aarwitz/tapp@latest tree [target]   # accessibility tree, --json for every element (≈ tapp_ui_tree)
+npx -y @aarwitz/tapp@latest shot            # screenshot the booted sim → file path (≈ tapp_screenshot)
+npx -y @aarwitz/tapp@latest apps            # what's installed on the simulator, with bundle ids
+npx -y @aarwitz/tapp@latest build [dir]     # build the app in an Xcode repo + install it (≈ tapp_build)
+npx -y @aarwitz/tapp@latest explore app.apk --platform android --app-id com.acme.app
+npx -y @aarwitz/tapp@latest flow run .tapp/flows/smoke.yml  # committed, keyless E2E replay
 ```
 
 If repository onboarding detects multiple application targets, target detection is deterministic but
@@ -43,7 +44,9 @@ that IS the screen. If you cannot (Cursor, VS Code Copilot), connect the MCP ser
 instead: its tool results carry the screenshot inline. Screen *recordings* are for the
 human: on **iOS**, `tapp explore` records the full exploration and embeds it in the report.html
 evidence page (Android does not currently record video) — tell the user the report path so they can
-watch it.
+watch it. On **web**, explicit `--watch` opens the isolated Playwright Chromium window and overlays
+Tapp's current action and pointer; the overlay is omitted from evidence screenshots. It does not
+drive the person's existing/default browser profile.
 
 The interactive session/record loop is MCP-only (it needs a long-lived process). Flow replay is
 also available in the CLI. The rest of this playbook assumes the `tapp_*` MCP tools are connected. With

package/README.md

@@ -4,8 +4,10 @@
 [![npm](https://img.shields.io/npm/v/%40aarwitz%2Ftapp?color=cb3837&label=npm)](https://www.npmjs.com/package/@aarwitz/tapp)
 [![npm downloads](https://img.shields.io/npm/dw/%40aarwitz%2Ftapp?label=downloads)](https://www.npmjs.com/package/@aarwitz/tapp)
 [![license](https://img.shields.io/badge/license-MIT-blue)](./LICENSE)
-[![Install in Cursor](https://img.shields.io/badge/Cursor-Install_MCP-000000)](cursor://anysphere.cursor-deeplink/mcp/install?name=tapp&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBhYXJ3aXR6L3RhcHAiLCJtY3AiXX0=)
-[![Install in VS Code](https://img.shields.io/badge/VS_Code-Install_MCP-0098FF)](https://insiders.vscode.dev/redirect/mcp/install?name=tapp&config=%7B%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40aarwitz%2Ftapp%22%2C%22mcp%22%5D%7D)
+[![Agent Skill](https://img.shields.io/badge/Agent_Skill-install-6b5cff)](https://skills.sh/aarwitz/tapp)
+[![VS Code extension](https://img.shields.io/badge/VS_Code-extension-0098FF)](https://marketplace.visualstudio.com/items?itemName=lidi-solutions.tapp)
+[![Install in Cursor](https://img.shields.io/badge/Cursor-Install_MCP-000000)](cursor://anysphere.cursor-deeplink/mcp/install?name=tapp&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBhYXJ3aXR6L3RhcHBAbGF0ZXN0IiwibWNwIl19)
+[![VS Code MCP](https://img.shields.io/badge/VS_Code-Install_MCP-0098FF)](https://insiders.vscode.dev/redirect/mcp/install?name=tapp&config=%7B%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40aarwitz%2Ftapp%40latest%22%2C%22mcp%22%5D%7D)
 
 **Tapp is the release-contract and evidence layer for teams shipping agent-authored applications.**
 It turns a repository and real product into an observed UI Map, a compact reviewed deterministic
@@ -31,6 +33,47 @@ Three platforms, one observe-and-gate engine:
   autonomous exploration, the deterministic detectors (uncaught exceptions, failed requests,
   dead buttons, broken links, placeholder `href="#"` links, error pages), and the same gate.
 
+## Give Tapp to your coding agent
+
+After setup, the whole user prompt is:
+
+> Use Tapp to test this app.
+
+The official skill teaches the agent to choose the smallest useful operation, handle repositories
+with multiple app targets, inspect visual evidence, and keep exploration observations separate from
+release judgment.
+
+**Claude Code — skill and MCP tools together:**
+
+```bash
+claude plugin marketplace add aarwitz/tapp
+claude plugin install tapp@tapp
+```
+
+Restart Claude Code after installation, open the application repository, and use the short prompt
+above. The plugin installs the `tapp` Agent Skill and launches the matching version of Tapp's stdio
+MCP server through npm; no additional prompt block, MCP configuration, or bundle id is required.
+
+**Claude, Codex, Cursor, Copilot, and other Agent Skills clients — skill only:**
+
+```bash
+npx -y skills add aarwitz/tapp --skill tapp
+```
+
+This installs the open Agent Skills version of the same instructions into the current project and
+lets the agent fall back to the npm CLI when MCP is not connected. Add `-g` for a user-wide install,
+or `--agent claude-code`, `--agent codex`, and similar selectors to constrain the clients.
+
+**No agent integration:** run the npm package directly from an app repository:
+
+```bash
+npx -y @aarwitz/tapp@latest init . --explore
+```
+
+**VS Code:** install [Tapp from the Marketplace](https://marketplace.visualstudio.com/items?itemName=lidi-solutions.tapp).
+It contributes the same cross-platform Agent Skill to Copilot plus focused iOS simulator tools and a
+live simulator panel. Android and web remain available through the skill's CLI/MCP workflow.
+
 ```
 you:    "Add a logout button to the settings screen"
 agent:  *writes the Swift*
@@ -38,7 +81,7 @@ agent:  *tapp: builds, opens the app, navigates to Settings, screenshots it*
 agent:  "Done — and here it is working on the simulator: [screenshot]"
 ```
 
-## Quickstart for coding agents
+## npm CLI quickstart
 
 Requirements: **Node ≥ 18**. iOS needs **macOS + Xcode**; Android needs `adb` plus a connected
 emulator/device; web needs Playwright + Chromium.
@@ -46,8 +89,8 @@ emulator/device; web needs Playwright + Chromium.
 From the app repository, let the agent see the current screen and then explore it:
 
 ```bash
-npx -y @aarwitz/tapp open   # builds/launches as needed; prints a screenshot path + screen summary
-npx -y @aarwitz/tapp explore     # explores the real app; prints findings + evidence (an observation, not a gate)
+npx -y @aarwitz/tapp@latest open   # builds/launches as needed; prints a screenshot path + screen summary
+npx -y @aarwitz/tapp@latest explore     # explores the real app; prints findings + evidence (an observation, not a gate)
 ```
 
 Claude Code can read the saved image with its file-reading tool; Codex can open it with
@@ -62,22 +105,22 @@ To bootstrap maintained release infrastructure, preview the repository model and
 before Tapp writes anything:
 
 ```bash
-npx -y @aarwitz/tapp init . --dry-run --json-out /tmp/tapp-init.json
+npx -y @aarwitz/tapp@latest init . --dry-run --json-out /tmp/tapp-init.json
 # Build/start the detected web target, ground the first UI Map, then stop it.
-npx -y @aarwitz/tapp init . --explore --platform web
+npx -y @aarwitz/tapp@latest init . --explore --platform web
 # Or build/install the detected Xcode target, ground the map, and persist the validated scheme.
-npx -y @aarwitz/tapp init . --explore --platform ios --target .
+npx -y @aarwitz/tapp@latest init . --explore --platform ios --target .
 # Or connect to an already-running owned URL:
-npx -y @aarwitz/tapp init . --explore --platform web --url http://127.0.0.1:4173
+npx -y @aarwitz/tapp@latest init . --explore --platform web --url http://127.0.0.1:4173
 # If the app has roles/accounts, bind names once; values stay in local/CI secrets.
-npx -y @aarwitz/tapp actor set alice . --role member --session isolated \
+npx -y @aarwitz/tapp@latest actor set alice . --role member --session isolated \
   --credential email=ALICE_EMAIL --credential password=ALICE_PASSWORD
 # Review-only path: tapp init . → tapp plan show → tapp plan review --approve ...
 
 # After approved drafts replay and are promoted, establish the selected target's baseline
 # through the ordinary full gate, then generate the reviewable GitHub workflow.
-npx -y @aarwitz/tapp baseline create . --platform web
-npx -y @aarwitz/tapp ci install .
+npx -y @aarwitz/tapp@latest baseline create . --platform web
+npx -y @aarwitz/tapp@latest ci install .
 ```
 
 In a repository containing multiple apps (for example, iOS plus web),
@@ -101,40 +144,42 @@ Every verb takes whatever you have: nothing (auto-detects the repo you're in, or
 already on the simulator), a repo directory, a `path/to/App.app`, or a bundle id:
 
 ```bash
-npx -y @aarwitz/tapp open [target]   # launch the app → screen summary + screenshot file
-npx -y @aarwitz/tapp tree [target]   # accessibility tree of the current screen
-npx -y @aarwitz/tapp shot            # screenshot the booted simulator
-npx -y @aarwitz/tapp apps            # what's installed on the simulator (names + bundle ids)
-npx -y @aarwitz/tapp build [dir]     # just build + install (scheme auto-detected)
+npx -y @aarwitz/tapp@latest open [target]   # launch the app → screen summary + screenshot file
+npx -y @aarwitz/tapp@latest tree [target]   # accessibility tree of the current screen
+npx -y @aarwitz/tapp@latest shot            # screenshot the booted simulator
+npx -y @aarwitz/tapp@latest apps            # what's installed on the simulator (names + bundle ids)
+npx -y @aarwitz/tapp@latest build [dir]     # just build + install (scheme auto-detected)
 ```
 
-Web (beta): `npx -y @aarwitz/tapp explore http://localhost:3000` *(one-time setup:
-`npm i -g playwright && npx playwright install chromium`)*
+Web (beta): `npx -y @aarwitz/tapp@latest explore http://localhost:3000` *(one-time setup:
+`npm i -g playwright && npx playwright install chromium`)*. Add `--watch` to open Tapp's controlled,
+isolated Chromium window and follow its clicks with an on-page pointer/action label. Tapp hides that
+watch UI from saved evidence screenshots and does not automate your personal/default browser profile.
 
 Focused web inspection waits briefly for loading states to settle. If a consent or location modal
 blocks the screen, dismiss it and wait for the content you care about in the same package-only call:
 
 ```bash
-npx -y @aarwitz/tapp open https://example.com --tap "Not now" --wait-for "Dashboard"
-npx -y @aarwitz/tapp tree https://example.com --tap "Not now" --wait-for "Dashboard" --json
+npx -y @aarwitz/tapp@latest open https://example.com --tap "Not now" --wait-for "Dashboard"
+npx -y @aarwitz/tapp@latest tree https://example.com --tap "Not now" --wait-for "Dashboard" --json
 ```
 
 Android:
 
 ```bash
-npx -y @aarwitz/tapp explore path/to/app-debug.apk --platform android --app-id com.acme.app
-npx -y @aarwitz/tapp open com.acme.app --platform android
+npx -y @aarwitz/tapp@latest explore path/to/app-debug.apk --platform android --app-id com.acme.app
+npx -y @aarwitz/tapp@latest open com.acme.app --platform android
 ```
 
 Optional but recommended (prebuilds the test harness so the first run is fast):
 ```bash
-npx -y @aarwitz/tapp install    # ~2 min, one time
-npx -y @aarwitz/tapp doctor     # verify Xcode / simulators / toolchain
+npx -y @aarwitz/tapp@latest install    # ~2 min, one time
+npx -y @aarwitz/tapp@latest doctor     # verify Xcode / simulators / toolchain
 ```
 
 ### Optional browser workspace
 
-`npx -y @aarwitz/tapp app .` opens a local Release Studio for people who want visual repository
+`npx -y @aarwitz/tapp@latest app .` opens a local Release Studio for people who want visual repository
 onboarding, release-plan review, and CI preparation. It is not required for the coding-agent
 `open`/`explore` workflow.
 
@@ -146,14 +191,14 @@ context** (the model literally sees the screen) and the **interactive session lo
 
 **Claude Code:**
 ```bash
-claude mcp add tapp -- npx -y @aarwitz/tapp mcp
+claude mcp add tapp -- npx -y @aarwitz/tapp@latest mcp
 ```
 
 **Cursor / VS Code (Copilot)** — add to `~/.cursor/mcp.json` (Cursor) or `.vscode/mcp.json` (VS Code):
 ```json
 {
   "servers": {
-    "tapp": { "type": "stdio", "command": "npx", "args": ["-y", "@aarwitz/tapp", "mcp"] }
+    "tapp": { "type": "stdio", "command": "npx", "args": ["-y", "@aarwitz/tapp@latest", "mcp"] }
   }
 }
 ```
@@ -162,10 +207,10 @@ claude mcp add tapp -- npx -y @aarwitz/tapp mcp
 ```toml
 [mcp_servers.tapp]
 command = "npx"
-args = ["-y", "@aarwitz/tapp", "mcp"]
+args = ["-y", "@aarwitz/tapp@latest", "mcp"]
 ```
 
-**Any other MCP client:** stdio command `npx -y @aarwitz/tapp mcp`.
+**Any other MCP client:** stdio command `npx -y @aarwitz/tapp@latest mcp`.
 
 Then ask your agent:
 > "Explore my app and show me what breaks."
@@ -194,7 +239,9 @@ Then ask your agent:
 | 📱 | `tapp_list_simulators` / `boot_simulator` / `install_app` | Simulator + app management. |
 | 🩺 | `tapp_health`, `tapp_capture*`, `tapp_parse_markers` | Diagnostics and capture history. |
 
-Full agent playbook: [AGENTS.md](./AGENTS.md) — ships inside the package so agents can read it too.
+Canonical installable skill: [`skills/tapp/SKILL.md`](skills/tapp/SKILL.md). Full low-level tool
+reference: [AGENTS.md](./AGENTS.md). Both ship inside the npm package; installing the Claude plugin
+or Agent Skill is what makes the workflow discoverable without pasting instructions.
 Application-model and import contract: [`docs/application-model.md`](docs/application-model.md).
 The desktop Coverage view reads the same `.tapp/application-model.json`,
 `.tapp/release-plan.json`, and `.tapp/ui-map.json`, including explicit proposal review; it
@@ -306,7 +353,7 @@ accepts that `.app`, detects its bundle id, writes report artifacts, and exits n
 gate fails:
 
 ```bash
-npx -y @aarwitz/tapp ci --app path/to/MyApp.app \
+npx -y @aarwitz/tapp@latest ci --app path/to/MyApp.app \
   --project-dir . --pr-base origin/main --pr-head HEAD \
   --target-key target_ios_myapp \
   --pr-plan-out tapp-pr-plan.json \
@@ -354,9 +401,9 @@ your agent proves its UI work instead of claiming it:
 ```markdown
 ## Verifying UI changes
 This repo uses tapp (https://github.com/aarwitz/tapp) to verify UI work on a real app surface
-(iOS simulator, Android emulator/device, or a browser for web). After any UI change, run `npx -y @aarwitz/tapp open` from the
+(iOS simulator, Android emulator/device, or a browser for web). After any UI change, run `npx -y @aarwitz/tapp@latest open` from the
 repo root (it finds and builds the Xcode project itself) and look at the screenshot it saves as
-proof. Before declaring a feature done, run `npx -y @aarwitz/tapp explore` (or `explore <url>` for web)
+proof. Before declaring a feature done, run `npx -y @aarwitz/tapp@latest explore` (or `explore <url>` for web)
 and report the findings + evidence. A change is not "done" until it has been seen working.
 (If the tapp MCP server is connected, the tapp_* tools do the same with inline screenshots —
 tapp_build builds + installs the app and returns the bundle id for tapp_explore.)

package/bin/tapp.js

@@ -240,8 +240,8 @@ async function resolveTargetOrExit(engine, input) {
 
 function safeCommandUsage(verb) {
   const usage = {
-    explore: "tapp explore [target] [--platform ios|android|web] [--actions N] [--timeout SEC] [--email VALUE] [--password VALUE] [--baseline FILE] [--json FILE]\n  iOS launch configuration: [--launch-arg VALUE ...] [--launch-env '{\"KEY\":\"VALUE\"}']\n  Android: [--app-id ID] [--apk FILE] [--serial ID] [--keep-data]",
-    init: "tapp init [repo] [--explore] [--refresh] [--platform PLATFORM] [--target NAME] [--url URL] [--dry-run]",
+    explore: "tapp explore [target] [--platform ios|android|web] [--actions N] [--timeout SEC] [--email VALUE] [--password VALUE] [--baseline FILE] [--json FILE]\n  Web: [--watch] opens Tapp's controlled browser and shows its actions\n  iOS launch configuration: [--launch-arg VALUE ...] [--launch-env '{\"KEY\":\"VALUE\"}']\n  Android: [--app-id ID] [--apk FILE] [--serial ID] [--keep-data]",
+    init: "tapp init [repo] [--explore] [--refresh] [--platform PLATFORM] [--target NAME] [--url URL] [--watch] [--dry-run]",
     open: "tapp open [target] [--platform ios|android|web] [--out FILE] [--tap TEXT] [--wait-for TEXT]",
     tree: "tapp tree [target] [--platform ios|android|web] [--json] [--tap TEXT] [--wait-for TEXT]",
     shot: "tapp shot [--out FILE]",
@@ -346,6 +346,7 @@ switch (command) {
       timeout,
       testEmail: typeof flags.email === "string" ? flags.email : undefined,
       testPassword: typeof flags.password === "string" ? flags.password : undefined,
+      watch: flags.watch === true,
       runExploration: engine?.runInitExploration,
       onProgress: (progress) => {
         const activePlatform = progress.platform || platform;
@@ -557,6 +558,7 @@ switch (command) {
           testPassword: flags.password,
           ...launchOptions,
           baselineFindings,
+          watch: flags.watch === true,
           surface: "cli",
           onProgress,
           onStatus: (t) => console.error(`ℹ️  ${t}`),
@@ -577,6 +579,10 @@ switch (command) {
       process.exit(2);
     }
     if (platform === "ios") requireMacFor("iOS testing");
+    if (flags.watch === true && platform !== "web") {
+      console.error("❌ --watch is currently available for web exploration only");
+      process.exit(2);
+    }
     if (platform !== "ios" && Object.keys(launchOptions).length) {
       console.error("❌ --launch-arg and --launch-env apply only to iOS targets");
       process.exit(2);
@@ -598,6 +604,7 @@ switch (command) {
           testEmail: flags.email,
           testPassword: flags.password,
           baselineFindings,
+          watch: flags.watch === true,
           surface: "cli",
           onProgress,
         })
@@ -1249,7 +1256,7 @@ switch (command) {
 
     console.log(`\n  Home: ${tappHome}`);
     console.log(healthy
-      ? "\nReady. Start with:\n  npx -y @aarwitz/tapp open [target]\n  npx -y @aarwitz/tapp explore [target]"
+      ? "\nReady. Start with:\n  npx -y @aarwitz/tapp@latest open [target]\n  npx -y @aarwitz/tapp@latest explore [target]"
       : "\nFix the ❌ items above, then re-run: tapp doctor");
     process.exit(healthy ? 0 : 1);
   }
@@ -1569,7 +1576,7 @@ switch (command) {
 Core — explore, prove, gate (agents and humans can just run these — no server, no setup):
   tapp explore [target]    Autonomous exploration → findings + evidence (an observation, NOT a
                            release decision — run 'tapp ci' to gate a merge)
-                           (--platform ios|android|web · --app-id ID · --apk FILE · --actions N)
+                           (web: --watch · all: --platform ios|android|web · --actions N)
   tapp contract run FILE   Replay a business-level release contract — the guarantees that must hold
   tapp ci ...              Merge-blocking release gate — explore + suites + baseline → pass/fail/inconclusive
                            (see: tapp ci --help)
@@ -1629,10 +1636,15 @@ Setup:
   tapp doctor     Check Xcode / simulators / toolchain
   tapp mcp        Start the MCP server on stdio (adds inline screenshots + interactive sessions)
 
+Agent Skill (optional — so a short “Use Tapp to test this app” prompt is enough):
+  Any supported agent: npx -y skills add aarwitz/tapp --skill tapp
+  Claude skill + MCP:  claude plugin marketplace add aarwitz/tapp
+                       claude plugin install tapp@tapp
+
 MCP hookup (optional — for inline screenshots and the tap/type/inspect session loop):
-  Claude Code:   claude mcp add tapp -- npx -y @aarwitz/tapp mcp
+  Claude Code:   claude mcp add tapp -- npx -y @aarwitz/tapp@latest mcp
   Cursor/VS Code (mcp.json):
-    { "servers": { "tapp": { "type": "stdio", "command": "npx", "args": ["-y", "@aarwitz/tapp", "mcp"] } } }
+    { "servers": { "tapp": { "type": "stdio", "command": "npx", "args": ["-y", "@aarwitz/tapp@latest", "mcp"] } } }
 
 Then ask your agent things like:
   "Explore com.mycompany.app and show me what breaks"

package/docs/BROWSER-PRODUCT.md

@@ -12,7 +12,7 @@ in [`PRODUCT-ENGINE.md`](PRODUCT-ENGINE.md).
 ## Start locally
 
 ```bash
-npx -y @aarwitz/tapp app
+npx -y @aarwitz/tapp@latest app
 ```
 
 Tapp prints an authenticated one-time launch URL and opens it in the default browser. Use