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 aospbooks/aosp-internal-book --skill ai-and-devicesgit clone --depth 1 https://github.com/aospbooks/aosp-internal-bookWrote 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/aospbooks/aosp-internal-book/ai-and-devices)<a href="https://agentmods.dev/skills/aospbooks/aosp-internal-book/ai-and-devices"><img src="https://agentmods.dev/badge/skills/aospbooks/aosp-internal-book/ai-and-devices/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/aospbooks/aosp-internal-book/ai-and-devices"><img src="https://agentmods.dev/badge/skills/aospbooks/aosp-internal-book/ai-and-devices.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 | $0.00107 | $0.00393 |
| Opus 5 | $0.00053 | $0.00197 |
| Sonnet 5 | $0.00021 | $0.00079 |
| Haiku 4.5 | $0.00011 | $0.00039 |
Grade A, and why
aosp-ai-and-devices 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 12d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- aosp-ai-and-devices — 100% identical, 0 lines differ
What it actually says
AOSP Part XII — AI & Devices
Newer cross-device and assistant-oriented surfaces: on-device ML wiring and the companion-device / virtual-device frameworks.
Chapters in this Part
51-ai-appfunctions.md— on-device ML in AOSP, NNAPI, AppFunctions framework for assistant integration, Computer Control52-companion-virtual-device.md— CompanionDeviceManager, virtual displays/inputs/cameras, cross-device experiences53-npu-manager.md— the NpuManager mainline module for on-device neural accelerators: model-load admission control (budget/turn-taking policies, priorities), the Rust NDK ANpuBuffer/INpuAllocator, the android.hardware.npu HAL, and libwrapfd buffer protection
When to load which chapter
- Question mentions NNAPI, AppFunctions, on-device ML, Computer Control →
51-ai-appfunctions.md - Question mentions CompanionDeviceManager, virtual display, virtual camera, virtual input →
52-companion-virtual-device.md - Question mentions NPU, neural accelerator, NpuManager, ANpuBuffer, model-load scheduling →
53-npu-manager.md
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.
- 12d ago First seen · 33 lines · 107 tokens per session scan A 5f058b37ce17
aosp-ai-and-devices is a skill published in the GitHub repository aospbooks/aosp-internal-book (131 stars, last pushed 13d ago), licensed Apache-2.0. It adds 107 tokens to every session and 393 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
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…
axiom-ai
Use when implementing, testing, or evaluating ANY Apple Intelligence, on-device AI, or speech-to-text feature. Covers Foundation Models, @Generable, LanguageModelSession, Tool protocol, eval suites, model-as-judge scoring, SpeechTranscriber, CoreML.
firebase-ai
Use when setting up firebaseai, generating text/chat with Gemini, streaming AI output, building multimodal prompts, or handling AI errors.
frontend-a11y
Accessibility patterns for React and Next.js — semantic HTML, ARIA attributes, form labeling, keyboard navigation, focus management, and screen reader support. Use when building any interactive UI component or form.