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 skills add rcosteira79/android-skills --skill kmp-boundariesgit clone --depth 1 https://github.com/rcosteira79/android-skillsWrote 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/rcosteira79/android-skills/kmp-boundaries)<a href="https://agentmods.dev/skills/rcosteira79/android-skills/kmp-boundaries"><img src="https://agentmods.dev/badge/skills/rcosteira79/android-skills/kmp-boundaries/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/skills/rcosteira79/android-skills/kmp-boundaries"><img src="https://agentmods.dev/badge/skills/rcosteira79/android-skills/kmp-boundaries.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00106 | $0.01458 |
| Opus 5 | $0.00053 | $0.00729 |
| Sonnet 5 | $0.00021 | $0.00292 |
| Haiku 4.5 | $0.00011 | $0.00146 |
Grade A, and why
kmp-boundaries 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 10d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kotlin Multiplatform Boundary Design
Core rules for any KMP boundary:
- Keep
commonMainsemantic — describe what the product needs, not Android/iOS mechanics:currentRegion(), nevercurrentRegionFromAndroidLocale(context). - Split by capability —
Clipboard,ShareSheet,Haptics,Biometricsas separate interfaces, not onePlatformgod object. - Keep actuals thin — they translate, they don't decide; a business
if/wheninside an actual belongs in common, tested with a fake. - Prefer a common
interface+ per-platform binding overexpect classwhenever you need fakes / DI / lifecycle / runtime selection. - Introduce an intermediate source set (
skikoMain,appleMain) only when two platforms genuinely share an actual.
Two boundaries get the most detail below: the Activity-owned platform-UI boundary, and the AGP-9 KMP-library constraints.
Related: android-skills:kmp-ktor (network boundary), compose/references/multiplatform.md (Compose-MP mechanics), android-skills:kotlin-coroutines (scope ownership). For the iOS↔Swift bridge — Kotlin→Swift naming, type widths (Int is 32-bit), SKIE suspend→async / Flow→AsyncSequence, sealed-class exhaustiveness, SwiftUI embedding — load references/ios-interop.md when authoring the iOS-side actual.
Platform-UI bindings are Activity-owned, not Context-owned
The single most common Android boundary mistake: passing applicationContext / LocalContext.current into a binding that actually needs an Activity, then papering over the lifecycle gap with Intent.FLAG_ACTIVITY_NEW_TASK. That flag is a smell — it hides that this is a foreground-UI operation. Hold an Activity instead.
// commonMain — semantic interface; DOCUMENT what `suspend` means
interface ShareSheet {
/** Launches the system share sheet. Returns when the sheet is PRESENTED — not when the user
* completes or cancels. (Otherwise callers write incorrect retry/confirmation logic.) */
suspend fun shareText(text: String)
}
// androidMain — thin: build the intent and launch it. Activity-owned.
class AndroidShareSheet(private val activity: Activity) : ShareSheet {
override suspend fun shareText(text: String) {
activity.startActivity(Intent.createChooser(
Intent(Intent.ACTION_SEND).setType("text/plain").putExtra(Intent.EXTRA_TEXT, text), null,
))
}
}
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 64 lines · 106 tokens per session scan A e9f884f53ad9
kmp-boundaries is a skill published in the GitHub repository rcosteira79/android-skills (136 stars, last pushed 15d ago), licensed MIT. It adds 106 tokens to every session and 1,458 once invoked, about $0.0005 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
wear-compose-m3
Expert guidance for working with Wear OS Compose Material3. Use this skill when creating, updating, or migrating Wear OS projects. This includes the androidx.wear.compose.material3, androidx.wear.compose.foundation, and androidx.wear.compose.navigation3 libraries. Also working with core components such as AppScaffold…
kotlin-specialist
Provides idiomatic Kotlin implementation patterns including coroutine concurrency, Flow stream handling, multiplatform architecture, Compose UI construction, Ktor server setup, and type-safe DSL design. Use when building Kotlin applications requiring coroutines, multiplatform development, or Android with Compose.…
build-android-binary
Compile a PAM control's Android Kotlin module into the runtime-loadable DEX for a .ppmplugin. Creates a staged Gradle build with the pinned wrapper and react-android compile dependency, verifies manifest/module/package alignment and runtime-loading constraints, builds the release AAR, then runs d8 --min-api 24. Writes…
swiftui-dev
Use this skill for SwiftUI development, architecture, structure, performance, and Apple native app profiling. It combines.
android-navigation-3
Install and migrate to Jetpack Navigation 3. Use when implementing Navigation 3 patterns including NavDisplay, NavKey routes, deep links, multiple backstacks, scenes (dialogs, bottom sheets), or migrating from Navigation 2.
mobiai-kmp
Use when working on a Kotlin Multiplatform project — shared code, expect/actual declarations, platform-specific implementations, building and testing.