Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/ofcskn/mobile-automation-plugin/msd-screenshotsgit clone --depth 1 https://github.com/ofcskn/mobile-automation-pluginWrote 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.
[](https://agentmods.dev/commands/ofcskn/mobile-automation-plugin/msd-screenshots)<a href="https://agentmods.dev/commands/ofcskn/mobile-automation-plugin/msd-screenshots"><img src="https://agentmods.dev/badge/commands/ofcskn/mobile-automation-plugin/msd-screenshots.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00021 | $0.02732 |
| Opus 5 | $0.00010 | $0.01366 |
| Sonnet 5 | $0.00004 | $0.00546 |
| Haiku 4.5 | $0.00002 | $0.00273 |
Grade A, and why
msd-screenshots scanned grade A with 0 findings 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 4d ago.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate store screenshots for the specified app.
Ask: app ID, platform (ios / android / both), which locales.
Step 0 — Detect simulators and ask mode
# iOS
xcrun simctl list devices booted 2>/dev/null
# Android
adb devices 2>/dev/null
Ask the user:
"Which screenshot mode?
- Lightweight (default) — use the simulator that's already running. One device size, no extra installs.
- Full — capture all required device sizes (needs iPhone 16 Pro Max, iPhone 11 Pro Max, iPad Pro 13" simulators installed).
If they choose Lightweight: skip multi-device loops below. Capture only from the currently booted device. Detect its name and resolution from xcrun simctl list devices booted --json (iOS) or adb shell wm size (Android), and name the output folder accordingly.
Step 1 — Check prerequisites
Run every detection command below. If anything is missing, stop and tell the user before continuing.
iOS prerequisites
# Xcode installed?
xcode-select -p
# Xcode version (need 15+ for iPhone 16 Pro Max)
xcodebuild -version
# Any available simulator?
xcrun simctl list devices available | grep -E "iPhone|iPad"
# Simulator already booted?
xcrun simctl list devices booted
If no simulator is booted, boot the required device:
# Find UDID for iPhone 16 Pro Max (required from 2026)
xcrun simctl list devices available | grep "iPhone 16 Pro Max"
# Boot it
xcrun simctl boot <UDID>
open -a Simulator
Ask the user: "Do you have an Apple Developer account and is your app registered in App Store Connect?" — note the answer, continue either way (captures work without it).
Android prerequisites
# ADB available?
adb --version
# SDK path set?
echo $ANDROID_HOME
# Any AVD (virtual device) available?
emulator -list-avds
# Emulator already running?
adb devices
If no emulator is running, launch one:
emulator -avd <AVD_NAME> -no-snapshot-load
adb wait-for-device
Ask the user: "Do you have a Google Play Developer account?" — note the answer, continue either way.
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.
- 4d ago First seen · 293 lines · 21 tokens per session scan A a25ea409a820
msd-screenshots is a command published in the GitHub repository ofcskn/mobile-automation-plugin (2 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 2,732 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
mobile-verify
Run automated verification loops with pass@k metrics for mobile testing. Executes tests multiple times to detect flakiness.
preflight
Run pre-submission checks — automated gates + manual checklist.
feature-build
Build a complete mobile feature from description to running code with E2E tests. Orchestrates 6 phases - planning, implementation, testing, build-fix, quality gate, and verification. Auto-detects platform.
android-build
Build Android project with Gradle, fix errors, generate APK/AAB. Invokes android-build-resolver for issues.
compose-test
Run Compose UI tests with Espresso. Verify critical user flows.
decompile
Decompile an Android APK/XAPK/AAB/DEX/JAR/AAR and analyze its structure.