auto-mobile-usage

auto-mobile-usage is a skill for Claude Code, Codex from kaeawc/auto-mobile. It costs 55 tokens per session (946 once invoked), scanned A, original, Apache-2.0.

A set of instructions for controlling Android and iOS devices through AutoMobile MCP tools. MCP is a way for an agent to call external tools; these instructions cover obtaining a device session, observing its screen, and acting on the latest observation.

In plain words
What is it for?
Use it to acquire phones or tablets, inspect their screens, tap or swipe on them, and recover when a device is busy, unavailable, or out of capacity.
Why use it?
It prevents actions from being sent to the wrong device or based on an outdated screen, and explains how to handle device-session errors.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to acquire phones or tablets, inspect their screens, tap or swipe on them, and recover when a device is busy, unavailable, or out of capacity.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kaeawc/auto-mobile/auto-mobile-usage
Install

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.

Any agent
npx skills add kaeawc/auto-mobile --skill auto-mobile-usage
Clone the repo
git clone --depth 1 https://github.com/kaeawc/auto-mobile

Made for: Claude Code, Codex.

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.

agentmods badge for auto-mobile-usage

README.md
[![agentmods](https://agentmods.dev/badge/skills/kaeawc/auto-mobile/auto-mobile-usage/github.svg)](https://agentmods.dev/skills/kaeawc/auto-mobile/auto-mobile-usage)
Your own site
<a href="https://agentmods.dev/skills/kaeawc/auto-mobile/auto-mobile-usage"><img src="https://agentmods.dev/badge/skills/kaeawc/auto-mobile/auto-mobile-usage/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.

agentmods 80×15 button for auto-mobile-usage

Your own site · 80×15
<a href="https://agentmods.dev/skills/kaeawc/auto-mobile/auto-mobile-usage"><img src="https://agentmods.dev/badge/skills/kaeawc/auto-mobile/auto-mobile-usage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 946 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.00946
Opus 5.5 $0.00022 $0.00378
Sonnet 5.5 $0.00011 $0.00189
Haiku 4.5 $0.00006 $0.00095

Measured 2d ago against content hash bcae03c7d85e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

auto-mobile-usage 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 2d 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.

mcp-skills/auto-mobile-usage/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Driving devices with AutoMobile

1. Get a session first

  • Acquire a device with getAndroid or getApple. It finds or boots one and returns a sessionUuid.
  • A connection that acquired a device is bound to it, so later calls route to that session without repeating it. A different connection, or a CLI call, passes sessionUuid on every call.
  • A device that a session holds takes control calls only from that session (device_owned_by_other_session otherwise). Naming someone else's sessionUuid never takes the device over.
  • setActiveDevice and acquisition are the only calls that change which session an untargeted call uses. With several sessions, pass sessionUuid or deviceId (ambiguous_session_selector).
  • session_ownership_lost and no_active_device_session are permanent for that session: acquire a new one.

2. Observe before you act

  • Call observe before the first action and again after each action that can change the screen. Coordinates and Android synthetic s2- element ids are valid only for the observation that returned them.
  • Act on what observe returned: tapOn takes a selector (text, elementId, testTag), swipeOn scrolls the screen or a container (lookFor scrolls until an element appears), tapAt takes coordinates, sendKeys types into the focused field. Do not guess coordinates.
  • skeleton lists only rows you can act on. Static text (a status label, a validation error, a result message) is in context; read it there to verify a result. waitFor with text or textAny, or for: "appear"/"textEquals" with only text, matches text in either array.
  • Ask observe for a screenshot only when the hierarchy is not enough; images are the largest part of a result.

3. Resources versus tools

  • Tools act or run a computation. Resources (automobile: URIs) are cheap read-only state: automobile:tools lists every tool and whether it is enabled, automobile:devices/booted lists booted devices, automobile:observation/latest is the latest observation.
  • Read a resource instead of calling a tool when you only need state. A sessionless read never takes a held device.
  • A tool that is gated off does not appear in tools/list. Enable it with setToolEnabled or the enableTools argument of getAndroid and getApple.

Read the full file on GitHub · 46 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.

  1. 2d ago Changed · +1 lines bcae03c7d85e
  2. 11d ago First seen · 45 lines · 55 tokens per session scan A 82907be4a57e

Subscribe to this mod's changes

auto-mobile-usage is a skill published in the GitHub repository kaeawc/auto-mobile (55 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 946 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-28.

Related

auto-mobile-usage compared with skills from other repositories

auto-mobile-usage next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
auto-mobile-usagekaeawc/auto-mobileSkill55todayApache-2.0A55Claude Code, Codex
orca-emulator-androidstablyai/orcaSkill119ktodayMITA102Claude Code, Codex
glance-canonical-layoutsandroid/skillsSkill10k2d agoApache-2.0A56Claude Code
android-tombstone-symbolicationdotnet/skillsSkill5.8ktodayMITA176Claude Code
dogfoodcallstack/agent-deviceSkill5.3ktodayMITA55Claude Code
winapp-mauimicrosoft/winappCliSkill1.4ktodayMITA68Claude Code
app_remixrome-os/romeSkill894todayMITA50Claude Code, Codex