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 sunnat629/android-media-pack --skill media3-ads-imagit clone --depth 1 https://github.com/sunnat629/android-media-packWrote 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/sunnat629/android-media-pack/media3-ads-ima)<a href="https://agentmods.dev/skills/sunnat629/android-media-pack/media3-ads-ima"><img src="https://agentmods.dev/badge/skills/sunnat629/android-media-pack/media3-ads-ima/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/sunnat629/android-media-pack/media3-ads-ima"><img src="https://agentmods.dev/badge/skills/sunnat629/android-media-pack/media3-ads-ima.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 | $0.00033 | $0.00361 |
| Opus 5 | $0.00016 | $0.00180 |
| Sonnet 5 | $0.00007 | $0.00072 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
media3-ads-ima 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.
What it actually says
Trigger
Use for IMA ads, CSAI, SSAI/DAI, ad view placement, companion ads, and ad/content error separation.
Rules
- Start with
streaming-media-architecturefor ownership, KMP split, preload window, and telemetry. - Pin Media3 to
1.10.1through the version catalog. - Keep Media3 APIs in Android source sets; expose KMP-safe state/events upward.
- Choose CSAI or SSAI per playback session.
- Ad UI must be provided by an
AdViewProviderattached to the playback surface. - Separate ad telemetry from content telemetry but correlate by session.
- A playlist MUST NOT contain more than one IMA SSAI stream. One SSAI stream may be combined with other non-SSAI media items.
Example
media3-exoplayer-ima = { module = "androidx.media3:media3-exoplayer-ima", version.ref = "media3" }
Related
media3-video-playbackmedia3-analytics-telemetry
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 · 45 lines · 33 tokens per session scan A 4e59da48e189
media3-ads-ima is a skill published in the GitHub repository sunnat629/android-media-pack (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 361 once invoked, about $0.0002 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
argent-screen-recording
Record a video of an iOS simulator or Android emulator/device screen using argent MCP tools. Use when the user asks to record the screen, capture a video of a flow, interaction, or animation, produce a screen recording, or document app behavior as a video clip.
swift-architecture
Choose and migrate an Apple-platform app architecture for a fintech iOS app (iOS 26 era). Covers MV with Observation (@Observable, @Environment injection, @Bindable), MVVM, hand-rolled MVI/unidirectional store+reducer, The Composable Architecture (@Reducer, @ObservableState, StoreOf, Effect.run, @Dependency…
media3-custom-audio-processor
Write a custom audio processor for a Media3/ExoPlayer audio pipeline — a filter, a fade, a gain stage — that is toggled at runtime and shared across several concurrent players. Use when a processor you added does nothing until the next track, when playback wedges with no error, when put(ByteBuffer) throws on your own…
nowplaying-pager-no-feedback-loop
A now-playing artwork pager that both follows the player and drives it, without the two writing to each other in a loop — the in-progress-scroll flag covers programmatic animation as well as drags, the seek is dispatched from the settled page only, and the page-difference decision is a pure function outside the UI…
react-native-docs
Comprehensive React Native reference covering core components, APIs, styling, flexbox, navigation, networking, animations, platform-specific code, debugging, performance, TypeScript integration, Fast Refresh, environment setup, React fundamentals, running on devices, and the New Architecture (Fabric, JSI…
kappmaker-mascot
Generate an AI mascot for a KAppMaker app and its emotional states — a character that boosts engagement, virality and growth. Pick from 16 concepts, then render the chosen mascot in 16 app-UI states (happy, loading, error, celebrating...), backgrounds auto-removed; selected states can be animated into short looping…