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 litert-lmgit 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/litert-lm)<a href="https://agentmods.dev/skills/google-ai-edge/litert-samples/litert-lm"><img src="https://agentmods.dev/badge/skills/google-ai-edge/litert-samples/litert-lm/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/litert-lm"><img src="https://agentmods.dev/badge/skills/google-ai-edge/litert-samples/litert-lm.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 | $0.00106 | $0.02255 |
| Opus 5.5 | $0.00042 | $0.00902 |
| Sonnet 5.5 | $0.00021 | $0.00451 |
| Haiku 4.5 | $0.00011 | $0.00226 |
Grade A, and why
litert-lm 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 7d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill provides step-by-step guidance for building an Android app that runs an open text LLM through the LiteRT-LM Kotlin API (com.google.ai.edge.litertlm; guide: https://ai.google.dev/edge/litert-lm/android, sources: https://github.com/google-ai-edge/LiteRT-LM/blob/main/README.md) on the CPU or the GPU. The model is one .litertlm file. Images, audio, tool calling and NPU backends are not covered. For vision and audio models, use the litert-runtime skill: https://github.com/google-ai-edge/litert-samples/blob/main/skills/litert-runtime/SKILL.md (LiteRT: https://github.com/google-ai-edge/litert/blob/main/README.md).
Prerequisites
- A Kotlin Android project (Android Studio's Empty Activity template is enough). The litertlm-android 0.18.0 AAR declares
minSdk24. - The dependency in the app-level
build.gradle.kts:implementation("com.google.ai.edge.litertlm:litertlm-android:0.18.0")from Google Maven, which lists the newer releases. - For the GPU backend, both lines inside
<application>inAndroidManifest.xml, and<uses-permission android:name="android.permission.INTERNET"/>if the app downloads the model:
<uses-native-library android:name="libvndksupport.so" android:required="false"/>
<uses-native-library android:name="libOpenCL.so" android:required="false"/>
- The model file lives on the device's filesystem (hundreds of MB to a few GB), never in assets or in the APK.
Detailed steps
1. Pick a model from litert-community
Choose a .litertlm file at https://huggingface.co/litert-community. Start with litert-community/gemma-4-E2B-it-litert-lm (the file gemma-4-E2B-it.litertlm, 2.6 GB) or the smaller litert-community/Qwen3-0.6B (Qwen3-0.6B.litertlm, 0.6 GB); both files run on the CPU and the GPU. A SoC suffix such as _Google_Tensor_G5 or .mediatek.mt6993 marks an NPU build (not covered here). The model card names the tested backends and the size. Converting a model yourself is a separate step: get a model.
What ships with it
2 files 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.
- 7d ago Changed 00912a56cd86
- 9d ago Changed · +23 lines ef7c5ccc345d
- 15d ago First seen · 111 lines · 106 tokens per session scan A 90f4118e4982
litert-lm is a skill published in the GitHub repository google-ai-edge/litert-samples (464 stars, last pushed yesterday), licensed Apache-2.0. It adds 106 tokens to every session and 2,255 once invoked, about $0.0004 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 2026-10-02.
Other skills, from other repositories
ml-kit-genai-prompt-api
Analyzes Android codebases to implement ML Kit GenAI Prompt API. Use this skill to send natural language requests on-device to Gemini Nano, use structured output with Prompt API, implement prefix caching, optimize the current prompt, or apply best practices.".
model-authoring
Empirical rules for authoring PyTorch models for on-device execution on Apple platforms, covering energy-efficient inference, scalable compute, and correctness testing. Use this skill whenever the user is writing, debugging, or reviewing PyTorch model code intended for on-device execution — even if they don't…
working-with-coreai
Use this skill whenever the user mentions coreai-torch, TorchConverter, coreai-build, AIModel, AIProgram, .aimodel, or wants to export/compile/run a PyTorch model on Apple silicon (iPhone, iPad, Mac). Also triggers for "deploy on device", "optimize for on-device performance", onboarding new models to Core AI, or…
adversarial-ml-evasion
Craft adversarial examples that cause trained ML classifiers to misclassify at inference time — image recognition, malware detectors, IDS, spam filters.
misinformation
Hunt LLM misinformation / overreliance (OWASP LLM09:2025) — confident-but-wrong outputs that flow into downstream automated decisions, compliance reports, customer communications, or autonomous code commits without verification.
vector-and-embedding-weaknesses
Hunt vector / embedding weaknesses (OWASP LLM08:2025) — adversarial inputs against the RAG / similarity layer that cause cross-tenant leak, embedding-inversion privacy loss, semantic confusion, and retriever-driven prompt injection.