A collection of tools and instructions for inspecting and controlling running Livtet Android or iOS apps through accessibility information and device interactions.

Use it to check screens, take screenshots, tap, swipe, type, navigate, investigate crashes, and inspect connected devices.

It gives the agent a consistent way to test and debug mobile apps without needing separate Android and iOS procedures.

How olamaelcu/livtet-mobile configures OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to olamaelcu/livtet-mobile. 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/olamaelcu/livtet-mobile/main/.opencode/skill/mobile-mcp/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/olamaelcu/livtet-mobile

Made for: OpenCode.

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/olamaelcu/livtet-mobile/mobile-mcp/github.svg)](https://agentmods.dev/skills/olamaelcu/livtet-mobile/mobile-mcp)

Your own site

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

Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 660 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.

Model	Per session	Once invoked
Fable 5.1	$0.00098	$0.00660
Opus 5.5	$0.00039	$0.00264
Sonnet 5.5	$0.00020	$0.00132
Haiku 4.5	$0.00010	$0.00066

Measured 2mo ago against content hash 56b280df8df7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mobile-mcp 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 2mo 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.

.opencode/skill/mobile-mcp/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mobile MCP

When to use

Use mobile-mcp tools when the user asks you to interact with or inspect a running Livtet Android or iOS app. The server provides platform-agnostic accessibility-tree snapshots and coordinate-based interactions, so you don't need separate Android/iOS expertise.

Always run mobile_list_available_devices first to confirm a target is connected before issuing any other mobile_* tool.

Device requirements

Android: emulator booted via mise run android-emulator --start phone (or the apk alias), or a real device attached via USB with adb devices showing it. Do NOT start or kill an emulator yourself — the guardrails in android/AGENTS.md forbid it. Ask the user or suggest the mise alias.
iOS (macOS only): Xcode + a booted simulator (xcrun simctl list devices booted). Same guardrail — never boot or shut down a simulator without asking. See ios/AGENTS.md.
On Linux, iOS tools return an empty device list because xcrun is absent. That's expected — don't retry or loop.

Tool categories

Device management: mobile_list_available_devices, mobile_get_screen_size, mobile_get_orientation, mobile_set_orientation
App management: mobile_list_apps, mobile_launch_app (package: net.olamaelcu.livtet), mobile_terminate_app, mobile_install_app, mobile_uninstall_app
Screen interaction: mobile_take_screenshot, mobile_save_screenshot, mobile_list_elements_on_screen, mobile_click_on_screen_at_coordinates, mobile_double_tap_on_screen, mobile_long_press_on_screen_at_coordinates, mobile_swipe_on_screen
Input & navigation: mobile_type_keys, mobile_press_button, mobile_open_url
Crash reports: mobile_list_crashes, mobile_get_crash

Always prefer mobile_list_elements_on_screen over coordinate-based taps when possible — the accessibility snapshot is deterministic and cheaper.

Build artifacts on the device

The Livtet app must already be installed and running on the target device. To install:

Android: mise run android-build && mise run android-install (ask the user first)
iOS: mise run ios-build && mise run ios-run-simulator (macOS only, ask first)

Read the full file on GitHub · 56 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.

2mo ago First seen · 56 lines · 98 tokens per session scan A 56b280df8df7

Subscribe to this mod's changes

mobile-mcp is a skill published in the GitHub repository olamaelcu/livtet-mobile (2 stars, last pushed today), licensed MPL-2.0. It adds 98 tokens to every session and 660 once invoked, about $0.0004 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 2026-08-31.

Debugging Mobile android ios ios-swift kotlin kotlin-android swift

mobile-mcp next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mobile-mcpolamaelcu/livtet-mobile	Skill	2	today	MPL-2.0	A	98	OpenCode
m3-expressiveahmed3elshaer/everything-claude-code-mobile	Skill	66	4mo ago	MIT	A	41	Claude Code
liquid-glassahmed3elshaer/everything-claude-code-mobile	Skill	66	4mo ago	MIT	A	40	Claude Code
feature-builderahmed3elshaer/everything-claude-code-mobile	Skill	66	4mo ago	MIT	A	62	Claude Code
app-lifecycleahmed3elshaer/everything-claude-code-mobile	Skill	66	4mo ago	MIT	A	29	Claude Code
image-loadingahmed3elshaer/everything-claude-code-mobile	Skill	66	4mo ago	MIT	A	33	Claude Code
navigation-composeahmed3elshaer/everything-claude-code-mobile	Skill	66	4mo ago	MIT	A	31	Claude Code

livtet-mobile: Skill for OpenCode