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.
git clone --depth 1 https://github.com/ArisGuimera/MobiAI-CoreWrote 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/plugins/arisguimera/mobiai-core/android)<a href="https://agentmods.dev/plugins/arisguimera/mobiai-core/android"><img src="https://agentmods.dev/badge/plugins/arisguimera/mobiai-core/android/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.
<a href="https://agentmods.dev/plugins/arisguimera/mobiai-core/android"><img src="https://agentmods.dev/badge/plugins/arisguimera/mobiai-core/android.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
android 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 yesterday.
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.
What it actually says
{
"name": "android",
"description": "MobiAI for Android — device, build, testing, and architecture skills, plus integration with the official Google skills (Apache 2.0)",
"version": "2.4.0",
"author": {
"name": "Matias Rosenstein",
"url": "https://github.com/ArisGuimera/MobiAI-Core"
},
"homepage": "https://github.com/ArisGuimera/MobiAI-Core",
"repository": "https://github.com/ArisGuimera/MobiAI-Core",
"license": "MIT",
"keywords": ["android", "kotlin", "adb", "gradle", "mobile"],
"dependencies": ["core"],
"skills": [
"./skills/",
"./skills/google/"
]
}
What it installs
The manifest is a name and a version. 35 skills travel with it, and installing the plugin installs all of them — 2,748 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill wear-compose-m3 A 91 tokens
- Skill adaptive A 155 tokens
- Skill edge-to-edge A 67 tokens
- Skill mobiai-android-architecture A 36 tokens
- Skill mobiai-android-device A 34 tokens
- Skill mobiai-android-testing A 30 tokens
- Skill testing-setup A 42 tokens
- Skill android-profiler A 157 tokens
- Skill mobiai-android-build C 28 tokens
- Skill android-intent-security A 53 tokens
- Skill wear-widgets A 144 tokens
- Skill verified-email A 60 tokens
- Skill jetpack-compose-performance A 41 tokens
- Skill leanback-to-compose-tv-migration A 151 tokens
- Skill android-permissions-security A 57 tokens
- Skill camerax A 47 tokens
- Skill glance-canonical-layouts A 56 tokens
- Skill android-for-cars-parked-apps A 150 tokens
- Skill navigation-event A 64 tokens
- Skill litert-runtime A 127 tokens
- Skill styles A 70 tokens
- Skill ml-kit-genai-prompt-api A 57 tokens
- Skill display-glasses-with-jetpack-compose-glimmer A 112 tokens
- Skill play-billing-library-version-upgrade A 39 tokens
- Skill migrate-xml-views-to-jetpack-compose A 98 tokens
- Skill navigation-3 A 80 tokens
- Skill agp-9-upgrade A 48 tokens
- Skill engage-sdk-integration A 44 tokens
- Skill litert-lm A 179 tokens
- Skill media3-cast-integration A 68 tokens
- Skill play-policy-insights A 66 tokens
- Skill anr-audit-and-fix A 65 tokens
- Skill projected-hardware A 71 tokens
- Skill android-cli E 86 tokens
- Skill restore-credentials C 75 tokens
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.
- yesterday Changed 10de7edeeede
- 1mo ago Changed · +10 lines 918f246c8434
- 1mo ago First seen · 9 lines scan A 646657657de9
android is a plugin published in the GitHub repository ArisGuimera/MobiAI-Core (489 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
swift-performance-pro
Performance: Instruments, SwiftUI render cost, memory and retain cycles, launch time, lists.
eternal-pose
Build and evolve map-first, mobile-first travel sites from real itinerary material.
safe-android-reverser
Sandboxed Android reverse engineering with semantic program indexing, XREF/CFG queries and structured network evidence through MCP.
react-native
Guides for Expo Modules API and NativeWind styling.
airtap
Run Airtap tasks from Claude Code to control Android devices in the cloud or on physical receivers.
apple-craft
A collection of skills for Apple-platform development, including implementation, debugging, code review, long-running projects, App Store delivery, Xcode integration, and Pencil design work. Xcode is Apple's tool for building its apps, and the App Store is Apple's software marketplace.