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 prasad-vennam/Awesome-Android-AI-Agent-Skills --skill android-kmp-platform-channelsgit clone --depth 1 https://github.com/prasad-vennam/Awesome-Android-AI-Agent-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/prasad-vennam/awesome-android-ai-agent-skills/android-kmp-platform-channels)<a href="https://agentmods.dev/skills/prasad-vennam/awesome-android-ai-agent-skills/android-kmp-platform-channels"><img src="https://agentmods.dev/badge/skills/prasad-vennam/awesome-android-ai-agent-skills/android-kmp-platform-channels/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/prasad-vennam/awesome-android-ai-agent-skills/android-kmp-platform-channels"><img src="https://agentmods.dev/badge/skills/prasad-vennam/awesome-android-ai-agent-skills/android-kmp-platform-channels.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00021 | $0.00407 |
| Opus 5.5 | $0.00008 | $0.00163 |
| Sonnet 5.5 | $0.00004 | $0.00081 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
android-kmp-platform-channels 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.
What it actually says
Kotlin Multiplatform Native Bridging 🌉
When the common Kotlin standard library falls short, you must write native platform bridges to access raw iOS Foundation or Android Context APIs.
⚡ When to Use
- When integrating platform-specific hardware, Push Notifications, or third-party proprietary SDKs that lack a KMP wrapper.
🏗️ Core Rules / Pillars
1. The Expect/Actual Paradigm
- Pattern: Avoid trying to pass
Context(Android) orUIViewController(iOS) around in common code via genericAnytypes. - Implementation: Define an
expectclass or interface incommonMain, and provideactualimplementations withinandroidMainandiosMain. Use constructor injection for dependencies if using Koin or Kotlin-Inject.
2. Bridging Coroutines to Swift (iOS)
- Pattern: By default, Kotlin
StateFlowandsuspendfunctions compile to Swift with generic clunkySkieorCompletionHandlersignatures. - Implementation: Rely on libraries like Touchlab's SKIE to seamlessly map Kotlin Coroutines into native Swift Async/Await to provide iOS developers a world-class API.
🚧 Critical Anti-Hallucination Guards
- Trap: Do not attempt to use
java.util.UUIDorjava.timeanywhere incommonMain! Native Java libraries simply DO NOT compile to iOS and will immediately break the KMP build. Instead usekotlinx.datetimeanduuidlibraries.
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 · 34 lines · 21 tokens per session scan A f0a75498c089
android-kmp-platform-channels is a skill published in the GitHub repository prasad-vennam/Awesome-Android-AI-Agent-Skills (11 stars, last pushed 7mo ago), licensed MIT. It adds 21 tokens to every session and 407 once invoked, about $0.0001 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.
android-kmp-platform-channels compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| android-kmp-platform-channelsprasad-vennam/Awesome-Android-AI-Agent-Skills | Skill | 11 | 7mo ago | MIT | A | 21 | Claude Code, Codex |
| compose-multiplatformericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 80 | Claude Code, Codex |
| using-xtool2389-research/xtool | Skill | 5 | 4d ago | MIT | A | 100 | Claude Code |
| wear-compose-m3android/skills | Skill | 10k | yesterday | Apache-2.0 | A | 91 | Claude Code |
| ink-custom-brush-builderandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 159 | Claude Code |
| kotlin-specialistJeffallan/claude-skills | Skill | 12k | 7d ago | MIT | A | 86 | Claude Code |
| swiftui-devOrkas-AI/Orkas | Skill | 9.0k | yesterday | MIT | A | 3 | Claude Code, Codex |