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 google-ai-edge/litert-samples --skill compiled-model-app-scaffoldinggit clone --depth 1 https://github.com/google-ai-edge/litert-samplesWrote 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/google-ai-edge/litert-samples/compiled-model-app-scaffolding)<a href="https://agentmods.dev/skills/google-ai-edge/litert-samples/compiled-model-app-scaffolding"><img src="https://agentmods.dev/badge/skills/google-ai-edge/litert-samples/compiled-model-app-scaffolding/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/google-ai-edge/litert-samples/compiled-model-app-scaffolding"><img src="https://agentmods.dev/badge/skills/google-ai-edge/litert-samples/compiled-model-app-scaffolding.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 | $0.00098 | $0.01923 |
| Opus 5 | $0.00049 | $0.00962 |
| Sonnet 5 | $0.00020 | $0.00385 |
| Haiku 4.5 | $0.00010 | $0.00192 |
Grade A, and why
compiled-model-app-scaffolding 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 9d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CompiledModel app scaffolding
An app around a verified model is done when three things hold, in this order:
- the app reproduces the model recipe's verification numbers on the accelerator the recipe verified — before any UI exists,
- inference is confined and leak-free: one dispatcher owns the model, every buffer is closed, benchmarks include the readback,
- the inference code is liftable — another app could take the helper file unchanged.
Scope: this scaffolds a new app from a model recipe. Migrating an
existing TFLite Interpreter app to CompiledModel is a different task with
its own skill. LM models are consumed through the LiteRT-LM Engine rather
than raw CompiledModel — samples/litert/text_to_speech_lm is the
reference for that lane; everything below is the non-LM CompiledModel app.
Step 0: prove parity before building UI
The first milestone has no UI: a bare harness that loads the .tflite,
runs the recipe's verification input on the target accelerator, and
reproduces the numbers recorded in the recipe README (correlation,
residency). If they do not reproduce, stop — that is an
on-device-verification problem, and no amount of app code fixes it.
Only then build the ViewModel and the screen.
The shape
One sample = one standalone Gradle project, four layers:
app/src/main/java/<pkg>/
<Task>Helper.kt inference infra: owns the CompiledModel and its
buffers; pre/post-processing; NO Android UI types
MainViewModel.kt state machine: drives the helper on a confined
dispatcher, exposes UiState
UiState.kt one immutable data class
MainActivity.kt ComponentActivity + setContent, nothing else
view/ Screen.kt, Theme.kt, Color.kt — Compose only
app/src/main/res/values/ strings.xml etc. — no UI strings in Kotlin
The worked example of the full shape is
samples/litert/image_segmentation/kotlin_cpu_gpu/android. The layer
boundary that matters most is the helper's: pre/post-processing is part of
the model contract (it must match what the recipe exported against), so it
lives with the model, not in the screen. Reusable inference code is worth
more than UI polish — a reader will lift <Task>Helper.kt and delete the
rest.
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.
- 9d ago First seen · 160 lines · 98 tokens per session scan A 1c5002f6bcea
compiled-model-app-scaffolding is a skill published in the GitHub repository google-ai-edge/litert-samples (425 stars, last pushed 5d ago), licensed Apache-2.0. It adds 98 tokens to every session and 1,923 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
kotlin-expert
Expert-level Kotlin development, Android, coroutines, and multiplatform. Use when the user mentions Android, coroutines, multiplatform, or JVM, or when the task involves Kotlin Fundamentals, Android Development, Kotlin Multiplatform, or Kotlin Style.
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.