What is mobile-verify?

An end-to-end verification procedure for a Band iOS app using an iPhone simulator and a real Band hub. End-to-end testing checks a complete user flow across the app and its connected service.

Use it to build and install the app in an iOS simulator, run Maestro acceptance flows from the mobile project, and verify them against a real hub.

It tests the app in a controlled temporary environment without changing the user's real hub, home directory, or desktop app. It also saves screenshots and a report from the tested flows.

How band-app/band configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to band-app/band. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/band-app/band/main/.claude/skills/mobile-verify/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/band-app/band

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/band-app/band/mobile-verify/github.svg)](https://agentmods.dev/skills/band-app/band/mobile-verify)

Your own site

<a href="https://agentmods.dev/skills/band-app/band/mobile-verify"><img src="https://agentmods.dev/badge/skills/band-app/band/mobile-verify/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/band-app/band/mobile-verify"><img src="https://agentmods.dev/badge/skills/band-app/band/mobile-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,148 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00129	$0.05148
Opus 5.5	$0.00052	$0.02059
Sonnet 5.5	$0.00026	$0.01030
Haiku 4.5	$0.00013	$0.00515

Measured today against content hash 114c58e1059e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

mobile-verify scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf /tmp/band-ios-sim.lock

.claude/skills/mobile-verify/SKILL.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mobile-verify

Runs the mobile app's acceptance flows on the iOS simulator against a real Band hub, from a worktree, without touching the real ~/.band, the user's running hub or the desktop app.

Everything below runs from the worktree root unless a step says otherwise.

One-time setup on a Mac

Check each tool first and install only what is missing. All of it is user space (Homebrew).

Xcode with an iOS simulator runtime: xcodebuild -version and xcrun simctl list devices available | grep iPhone must both print something. Installing Xcode is a manual step; stop and tell the user if it is missing.
CocoaPods: pod --version, else brew install cocoapods.
Java 17 for Maestro: /opt/homebrew/opt/openjdk@17/bin/java -version, else brew install openjdk@17. The verify script puts it on PATH itself, so no shell profile change is needed.
Maestro: PATH="/opt/homebrew/opt/openjdk@17/bin:$PATH" maestro --version (the script also looks in ~/.maestro/bin), else brew tap mobile-dev-inc/tap && brew install mobile-dev-inc/tap/maestro. Without Java 17 on PATH, a bare maestro --version fails with "Unable to locate a Java Runtime" even when Maestro is installed.
Node 24 (.nvmrc): node --version must print v24. If it doesn't, put a Node 24 first on PATH for every command below (for example ~/.nvm/versions/node/v24.*/bin).
The workspace installed: pnpm install. On a fresh worktree this is the longest step (about 15 minutes with a cold pnpm store).
Disk: a build needs about 2.5 GB in the worktree (apps/mobile/build about 1.9 GB, the generated apps/mobile/ios about 650 MB). Check df -h . first.

Every run

Build the hub bundle once per worktree (the throwaway hub runs it):
```
pnpm build:web
```
Skip this when apps/hub/dist/start-server.mjs already exists and the change touches only apps/mobile.
Run the flows:
```
node apps/mobile/scripts/verify.mjs
```

Read the full file on GitHub · 212 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

today Changed · +1 lines 114c58e1059e
9d ago Changed · +2 lines 94d9fbd716f8
11d ago Changed · +7 lines be31d4ec3f8b
12d ago Changed · +25 lines scan A → C ff17c5f53577
13d ago Changed · +6 lines 175648967b16
14d ago First seen · 171 lines · 129 tokens per session scan A 28cffe24a27d

Subscribe to this mod's changes

mobile-verify is a skill published in the GitHub repository band-app/band (5 stars, last pushed today), licensed MIT. It adds 129 tokens to every session and 5,148 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-15.

E2E testing Mobile Testing

android-ui-journey-testing

XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.

sickn33/agentic-awesome-skills · 27 tokens

android_ui_verification

Automated end-to-end UI testing and verification on an Android Emulator using ADB.

sickn33/agentic-awesome-skills · 22 tokens

solopi-ai

A command-line framework for testing Android apps and devices with SoloPi, including on-device or cloud AI decision models. It manages devices, test cases, recorded interactions, replays, performance history, and evidence.

alipay/SoloPi · 82 tokens

eas-simulator

Run and control a user's app on a remote iOS/Android simulator hosted on EAS cloud. Read before running any eas simulator: commands - it has the current syntax for this experimental API. Use whenever the user needs a simulator they can't run locally - 'run my app on a cloud simulator', 'use eas simulator to…

expo/skills · 243 tokens

dogfood

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.

callstack/agent-device · 55 tokens

test-native-extension

Validate a third-party control repo across four automated layers plus one printed manual recipe. Layer 1 asserts native-source structure (Android getName() and iOS +moduleName to manifest nativeModule; @ReactMethod / RCTEXPORTMETHOD to methods; no @ReactModule) plus load/init readiness (ReactPackage public no-arg…

microsoft/power-platform-skills · 211 tokens

band: Skill for Claude Code