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 skills/zvadaadam/deus-machine/device-usenpx skills add zvadaadam/deus-machine --skill device-usegit clone --depth 1 https://github.com/zvadaadam/deus-machineWrote 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/skills/zvadaadam/deus-machine/device-use)<a href="https://agentmods.dev/skills/zvadaadam/deus-machine/device-use"><img src="https://agentmods.dev/badge/skills/zvadaadam/deus-machine/device-use.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 | $0.00045 | $0.02320 |
| Opus 5 | $0.00023 | $0.01160 |
| Sonnet 5 | $0.00009 | $0.00464 |
| Haiku 4.5 | $0.00005 | $0.00232 |
Grade A, and why
device-use 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 5d 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
device-use
iOS Simulator automation CLI. Observe, interact, and stream iOS apps through structured commands.
Commands
Simulator Lifecycle
device-use list # List available simulators
device-use list --booted # List only booted simulators
device-use boot "iPhone 17 Pro" # Boot a simulator by name
device-use boot <UDID> # Boot by UDID
device-use shutdown "iPhone 17 Pro" # Shutdown specific simulator
device-use shutdown --all # Shutdown all simulators
device-use open # Open Simulator.app window
Apps
device-use apps # All installed apps with bundle IDs
device-use apps --user # Only user-installed apps
device-use apps --system # Only built-in Apple apps
device-use appstate com.apple.Preferences # Is it installed / running / pid
device-use launch com.apple.Maps # Launch an app
device-use launch com.apple.Maps --relaunch # Terminate first, then launch
device-use terminate com.apple.Maps # Kill a running app
Permissions
Pre-grant system permissions so authorization dialogs don't block your flow.
device-use permission grant location com.apple.Maps
device-use permission grant photos ai.deus.machine
device-use permission revoke microphone com.example.app
device-use permission reset all com.example.app # Reset only this app
device-use permission reset all # Reset every app
Services: calendar, contacts, contacts-limited, location, location-always,
photos, photos-add, media-library, microphone, motion, reminders, siri, all.
Actions: grant, revoke, reset.
Observe the Screen
device-use snapshot # Full tree with structural context
device-use snapshot -i # Only branches containing interactive refs
device-use snapshot -i --flat # One line per ref, no hierarchy
device-use snapshot -i --diff # Include diff vs previous snapshot
device-use snapshot -i --hidden # Include off-screen interactive nodes
device-use screenshot # Capture to stdout (base64 when piped)
device-use screenshot output.png # Capture to file
device-use screenshot output.png --annotate # Draw @ref boxes on the screenshot
device-use screenshot --base64 # Explicit base64 output
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.
- 5d ago First seen · 257 lines · 45 tokens per session scan A 412807ac6058
device-use is a skill published in the GitHub repository zvadaadam/deus-machine (24 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 2,320 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orca-emulator-android
Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
winapp-maui
Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.
apple-search-ads
When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.