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/hanamizuki/solopreneurWrote 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/hanamizuki/solopreneur/android-dev)<a href="https://agentmods.dev/plugins/hanamizuki/solopreneur/android-dev"><img src="https://agentmods.dev/badge/plugins/hanamizuki/solopreneur/android-dev/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/hanamizuki/solopreneur/android-dev"><img src="https://agentmods.dev/badge/plugins/hanamizuki/solopreneur/android-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
android-dev 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 1mo 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.
What it actually says
{
"name": "android-dev",
"version": "0.4.13",
"description": "Android/Kotlin expertise. Ships the android-dev agent, android-patterns, and 37 vendored third-party skills (Compose / architecture / Gradle + 16 gplay-* Google Play Console CLI + 6 official Android team skills).",
"license": "MIT",
"dependencies": [
{
"name": "solopreneur",
"version": ">=0.5.1"
}
]
}
What it installs
The manifest is a name and a version. 36 skills, 1 agent travel with it, and installing the plugin installs all of them — 1,654 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill gplay-ppp-pricing A 40 tokens
- Skill gplay-iap-setup A 51 tokens
- Skill gplay-submission-checks A 45 tokens
- Skill gplay-purchase-verification A 32 tokens
- Skill gplay-release-flow A 49 tokens
- Skill gplay-reports-download A 49 tokens
- Skill jetpack-compose A 31 tokens
- Skill gplay-cli-usage A 51 tokens
- Skill gplay-metadata-sync A 37 tokens
- Skill gplay-review-management A 25 tokens
- Skill gplay-rollout-management A 25 tokens
- Skill gplay-user-management A 42 tokens
- Skill gplay-vitals-monitoring A 92 tokens
- Skill gplay-gradle-build A 43 tokens
- Skill gplay-migrate-fastlane A 50 tokens
- Skill gplay-screenshot-automation A 55 tokens
- Skill gplay-testers-orchestration A 44 tokens
- Skill mobile-android-design A 38 tokens
- Skill r8-analyzer A 60 tokens
- Skill android-patterns A 69 tokens
- Skill edge-to-edge A 67 tokens
- Skill coroutines A 28 tokens
- Skill xml-to-compose-migration A 41 tokens
- Skill gradle-build-performance A 37 tokens
- Skill viewmodel A 36 tokens
- Skill compose-performance-audit A 42 tokens
- Skill data-layer A 28 tokens
- Skill kotlin-concurrency-expert A 44 tokens
- Skill compose-ui A 39 tokens
- Skill testing A 18 tokens
- Skill play-billing-library-version-upgrade A 39 tokens
- Skill migrate-xml-views-to-jetpack-compose A 98 tokens
- Skill agp-9-upgrade A 48 tokens
- Skill architecture A 36 tokens
- Skill navigation-3 A 80 tokens
- Skill accessibility A 21 tokens
- Agent android-dev A 24 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.
- 1mo ago First seen · 13 lines scan A fb172d5afe9c
android-dev is a plugin published in the GitHub repository hanamizuki/solopreneur (154 stars, last pushed 3d ago), 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
android-skills
Android and KMP development skills for Claude Code — architecture, Compose, coroutines, flows, networking (Retrofit, Ktor), persistent storage (Room, DataStore), pagination, dependency injection (Hilt, Koin), testing, debugging, Gradle, and Material Design 3.
ios-developer
iOS and Swift development with SwiftUI views and models.
app-intents
Reviews and writes Swift App Intents code, exposing app actions and data to Siri, Shortcuts, Spotlight, and Apple Intelligence.
mwdat-ios
Git-native DAT SDK guidance for ios development, covering setup, camera streaming, display access, MockDeviceKit, session lifecycle, permissions, debugging, and sample app patterns.
swift-engineer
Elite iOS and macOS development expertise with automatic skill activation for Swift, UIKit, AppKit, SwiftUI, Xcode, and Apple frameworks plus code formatting tools.
swift-performance-pro
Performance: Instruments, SwiftUI render cost, memory and retain cycles, launch time, lists.