apple-on-device-ai

apple-on-device-ai is a skill for Claude Code, Codex from TalissonVitorino/kmp-ios-skills. It costs 188 tokens per session (3,972 once invoked), scanned A, original, MIT.

A guide to running generative AI directly on Apple devices such as iPhones, iPads, and Macs. It covers Apple's Foundation Models framework and related local machine-learning runtimes.

In plain words
What is it for?
Use it to build local text generation, structured responses, tool calls, OCR, image analysis, language processing, translation, and Apple Intelligence integrations.
Why use it?
It helps developers choose an on-device approach while keeping prompts and user data on the device and handling availability, safety, and generation limits.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to build local text generation, structured responses, tool calls, OCR, image analysis, language processing, translation, and Apple Intelligence integrations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/talissonvitorino/kmp-ios-skills/apple-on-device-ai
Install

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.

Any agent
npx skills add TalissonVitorino/kmp-ios-skills --skill apple-on-device-ai
Clone the repo
git clone --depth 1 https://github.com/TalissonVitorino/kmp-ios-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for apple-on-device-ai

README.md
[![agentmods](https://agentmods.dev/badge/skills/talissonvitorino/kmp-ios-skills/apple-on-device-ai/github.svg)](https://agentmods.dev/skills/talissonvitorino/kmp-ios-skills/apple-on-device-ai)
Your own site
<a href="https://agentmods.dev/skills/talissonvitorino/kmp-ios-skills/apple-on-device-ai"><img src="https://agentmods.dev/badge/skills/talissonvitorino/kmp-ios-skills/apple-on-device-ai/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.

agentmods 80×15 button for apple-on-device-ai

Your own site · 80×15
<a href="https://agentmods.dev/skills/talissonvitorino/kmp-ios-skills/apple-on-device-ai"><img src="https://agentmods.dev/badge/skills/talissonvitorino/kmp-ios-skills/apple-on-device-ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 188 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,972 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00188 $0.03972
Opus 5 $0.00094 $0.01986
Sonnet 5 $0.00038 $0.00794
Haiku 4.5 $0.00019 $0.00397

Measured 12d ago against content hash 3353569534a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

apple-on-device-ai 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.

ios/apple-on-device-ai/SKILL.md · 307 lines

How it starts

The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Apple on-device AI (iOS 26+)

Private, no-network generative AI on iPhone/iPad/Mac. This skill routes between the four local runtimes and covers the Foundation Models framework in depth.

  • Core ML model loading/prediction, compute units, MLTensor, .mlpackagecoreml.
  • OCR, barcode/face/text detection, image segmentationvision-framework.
  • Tokenization, POS/NER tagging, sentiment, word embeddings, on-device translationnatural-language.
  • Expose app actions/entities to Siri, Spotlight, and Apple Intelligenceapp-intents.
  • Fintech note: the system model runs fully on-device — no prompt or user data leaves the phone, which is what makes it usable for balances/transactions. Still treat model output as untrusted (see Safety).

Contents

Choosing a runtime

Runtime Model Best for Cost / caveats
Foundation Models Apple's built-in ~3B on-device LLM (powers Apple Intelligence) Chat, summarize, classify, extract, tool-calling — general language tasks with zero model download and guided/structured output Apple-Intelligence devices only (see availability); not customizable beyond instructions + optional LoRA adapters; text-focused
Core ML Your converted model (.mlpackage) Shipping a specific trained model — vision, audio, tabular, or a custom/quantized LLM — with Neural Engine acceleration You convert & bundle the model; you own updates/size. See coreml.
MLX Swift Any MLX/HF LLM you load Running larger or newer open LLMs (Llama/Qwen/Mistral/Phi) on Apple Silicon, research, fine-tuning, custom sampling GPU-heavy; large downloads; iPhone RAM limits model size; you manage weights
llama.cpp GGUF quantized models Max portability / a mature C++ stack, aggressive quantization (Q4/Q5), reuse across platforms C/Obj-C++ bridging; you manage the binary, weights, and Metal build

Read the full file on GitHub · 307 lines

Files

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.

Changes

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.

  1. 12d ago First seen · 307 lines · 188 tokens per session scan A 3353569534a1

Subscribe to this mod's changes

apple-on-device-ai is a skill published in the GitHub repository TalissonVitorino/kmp-ios-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 188 tokens to every session and 3,972 once invoked, about $0.0009 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.

Related

Other skills, from other repositories

compose-multiplatform

Use when building one shared Compose UI in Kotlin across Android, iOS, and desktop — commonMain @Composables, expect/actual, source-set placement, native interop, multiplatform ViewModel/navigation/Koin. NOT a single-platform native build (that is kotlin-android / swift-ios), and NOT Dart/Flutter cross-platform UI…

ericrisco/rsc-harness · 80 tokens

cmp-new

Scaffold a new MOBILE app — Android + iOS from one Kotlin/Compose Multiplatform codebase — from a bare "create a mobile app" to a green, verified build. Guardrails first: if the user already chose a different framework (React Native, Expo, Flutter, SwiftUI, native), do NOT redirect them here; if they only asked a…

kvdm-co-pilot/create-cmp · 478 tokens

cmp-firebase-connect

Wire a freshly scaffolded CMP/KMP app to its OWN real Firebase project — the #1 post-scaffold manual step. Use this when the user wants to connect their app to Firebase, or asks "connect my app to firebase", "set up google-services.json", "wire firebase", "create a firebase project for this app", "replace the…

kvdm-co-pilot/create-cmp · 170 tokens

add-feature

Add a new conforming vertical-slice feature (Screen + ViewModel + UseCase + Repository + spec + tests + golden tree + nav route + DI wiring) to this Compose Multiplatform app, cloned deterministically from the project's configured exemplar feature (qa/approvals.json's exemplarFeature — home by default). Use this when…

kvdm-co-pilot/create-cmp · 169 tokens

cmp-audit

Adversarial audit of one subsystem of a Kotlin/Compose Multiplatform app against its spec AND against platform semantics — the class of defect desktop-tier tests cannot see (alarms, notifications, PendingIntents, reboot, process death, DST). Use this when the user says "audit the notifications", "double check X for…

kvdm-co-pilot/create-cmp · 157 tokens

add-screen

Add a presentation-only slice — Screen + ViewModel + tests + golden tree + spec + nav route — for an EXISTING entity/repository in this Compose Multiplatform app, cloned deterministically from the project's configured exemplar feature's presentation layer (qa/approvals.json's exemplarFeature — home by default).…

kvdm-co-pilot/create-cmp · 202 tokens