foundation-models-on-device

foundation-models-on-device is a skill for Claude Code from multiplex-ai/muggle-ai-teams. It costs 38 tokens per session (1,731 once invoked), scanned A, a copy of foundation-models-on-device, MIT.

Guidance for using Apple's FoundationModels framework to run a language model on an iPhone or other Apple device. It covers text generation, structured results, tool calls, and streamed updates in iOS 26 and later.

In plain words
What is it for?
Use it to add on-device text generation, extract structured data from text, connect model output to app tools, and stream results into an iOS interface.
Why use it?
Running the model on the device can support privacy and offline use, but apps must handle whether Apple Intelligence is available. This skill shows the supported integration patterns.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the muggle-ai-teams plugin — 111 skills, 55 commands, 30 agents, 4 hooks shipped together

Good fit Use it to add on-device text generation, extract structured data from text, connect model output to app tools, and stream results into an iOS interface.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/multiplex-ai/muggle-ai-teams/foundation-models-on-device
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 multiplex-ai/muggle-ai-teams --skill foundation-models-on-device
Clone the repo
git clone --depth 1 https://github.com/multiplex-ai/muggle-ai-teams

Made for: Claude Code.

Or install muggle-ai-teams, the plugin that ships this one along with the rest of its 111 skills, 55 commands, 30 agents, 4 hooks.

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 foundation-models-on-device

README.md
[![agentmods](https://agentmods.dev/badge/skills/multiplex-ai/muggle-ai-teams/foundation-models-on-device/github.svg)](https://agentmods.dev/skills/multiplex-ai/muggle-ai-teams/foundation-models-on-device)
Your own site
<a href="https://agentmods.dev/skills/multiplex-ai/muggle-ai-teams/foundation-models-on-device"><img src="https://agentmods.dev/badge/skills/multiplex-ai/muggle-ai-teams/foundation-models-on-device/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 foundation-models-on-device

Your own site · 80×15
<a href="https://agentmods.dev/skills/multiplex-ai/muggle-ai-teams/foundation-models-on-device"><img src="https://agentmods.dev/badge/skills/multiplex-ai/muggle-ai-teams/foundation-models-on-device.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,731 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.
Origin 100% copy Near-identical to another mod 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 $0.00038 $0.01731
Opus 5.5 $0.00015 $0.00692
Sonnet 5.5 $0.00008 $0.00346
Haiku 4.5 $0.00004 $0.00173

Measured yesterday against content hash 8efee7e392b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

foundation-models-on-device 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 yesterday.

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.

Origin

This is a copy

100% identical to foundation-models-on-device — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/foundation-models-on-device/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FoundationModels: On-Device LLM (iOS 26)

Patterns for integrating Apple's on-device language model into apps using the FoundationModels framework. Covers text generation, structured output with @Generable, custom tool calling, and snapshot streaming — all running on-device for privacy and offline support.

When to Activate

  • Building AI-powered features using Apple Intelligence on-device
  • Generating or summarizing text without cloud dependency
  • Extracting structured data from natural language input
  • Implementing custom tool calling for domain-specific AI actions
  • Streaming structured responses for real-time UI updates
  • Need privacy-preserving AI (no data leaves the device)

Core Pattern — Availability Check

Always check model availability before creating a session:

struct GenerativeView: View {
    private var model = SystemLanguageModel.default

    var body: some View {
        switch model.availability {
        case .available:
            ContentView()
        case .unavailable(.deviceNotEligible):
            Text("Device not eligible for Apple Intelligence")
        case .unavailable(.appleIntelligenceNotEnabled):
            Text("Please enable Apple Intelligence in Settings")
        case .unavailable(.modelNotReady):
            Text("Model is downloading or not ready")
        case .unavailable(let other):
            Text("Model unavailable: \(other)")
        }
    }
}

Core Pattern — Basic Session

// Single-turn: create a new session each time
let session = LanguageModelSession()
let response = try await session.respond(to: "What's a good month to visit Paris?")
print(response.content)

// Multi-turn: reuse session for conversation context
let session = LanguageModelSession(instructions: """
    You are a cooking assistant.
    Provide recipe suggestions based on ingredients.
    Keep suggestions brief and practical.
    """)

let first = try await session.respond(to: "I have chicken and rice")
let followUp = try await session.respond(to: "What about a vegetarian option?")

Read the full file on GitHub · 244 lines

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. yesterday First seen · 244 lines · 38 tokens per session scan A 8efee7e392b3

Subscribe to this mod's changes

foundation-models-on-device is a skill published in the GitHub repository multiplex-ai/muggle-ai-teams (2 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 1,731 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to foundation-models-on-device, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

using-perplexity-platform

Perplexity Sonar API development with search-augmented generation, real-time web search, citations, and OpenAI-compatible Chat Completions. Use for AI-powered applications requiring up-to-date information, research assistants, and grounded responses with sources.

FortiumPartners/ensemble · 56 tokens

visual-prompt-forge

Write model-specific image and video prompts for the shots in a storyboard or shot list (shots.json). Outputs copy-paste-ready prompts for stills (Midjourney, Flux, Ideogram, GPT Image, Nano Banana, Seedream) and motion video (Kling, Veo, Seedance, Hailuo), and a revision mode that reads critiques and re-emits prompts…

whystrohm/shotkit · 157 tokens

markitdown

A Python utility for converting various file formats (PDF, Word, Excel, PowerPoint, etc.) to Markdown. Use this skill to install and use MarkItDown for document conversion.

myths-labs/muse · 41 tokens

solo-model-shrink

A model-conversion workflow for making a trained neural network smaller and usable on devices such as phones, browsers, and other edge hardware. It covers formats such as ONNX and Core ML, plus reduced-precision formats such as int8.

fortunto2/solo-factory · 120 tokens

apple-on-device-ai

Integrate on-device AI using Foundation Models framework, Core ML, and open-source LLM runtimes on Apple Silicon. Covers Foundation Models (LanguageModelSession, @Generable, @Guide, SystemLanguageModel, structured output, tool calling), Core ML (coremltools, model conversion, quantization, palettization, pruning…

The-Artificer-of-Ciphers-LLC/skills-from-the-artificer · 127 tokens

app-store-screenshots

Use when building App Store or Google Play screenshot pages, generating exportable marketing screenshots for iOS and/or Android apps, or creating programmatic screenshot generators with Next.js. Triggers on app store, play store, screenshots, marketing assets, html-to-image, phone mockup, android screenshots, feature…

fatihkan/badi · 68 tokens