foundation-models-on-device

foundation-models-on-device is a skill for Claude Code, Codex from x-cmd/skill. It costs 38 tokens per session (1,731 once invoked), scanned A, original, Apache-2.0.

A guide to Apple's FoundationModels framework for running a language model directly on supported iOS 26 devices. It covers text generation, structured responses, custom tool calls, and streamed updates.

In plain words
What is it for?
Checking model availability, generating or summarizing text, extracting structured data, calling app-specific tools, and streaming responses into an iOS interface.
Why use it?
It helps build AI features that can work privately on the device and, where supported, without a cloud connection.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/x-cmd/skill/foundation-models-on-device
Any agent
npx skills add x-cmd/skill --skill foundation-models-on-device
Clone the repo
git clone --depth 1 https://github.com/x-cmd/skill

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 foundation-models-on-device

README.md
[![agentmods](https://agentmods.dev/badge/skills/x-cmd/skill/foundation-models-on-device.svg)](https://agentmods.dev/skills/x-cmd/skill/foundation-models-on-device)
Your own site
<a href="https://agentmods.dev/skills/x-cmd/skill/foundation-models-on-device"><img src="https://agentmods.dev/badge/skills/x-cmd/skill/foundation-models-on-device.svg" alt="Measured on agentmods" 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. Scan, not verified.
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 $0.00038 $0.01731
Opus 5 $0.00019 $0.00865
Sonnet 5 $0.00008 $0.00346
Haiku 4.5 $0.00004 $0.00173

Measured 4d ago against content hash 8efee7e392b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

data/affaanmustafa/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. 4d ago 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 x-cmd/skill (26 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,731 once invoked, about $0.0002 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

android-accessibility

Use when building or reviewing Android UI for accessibility. Covers TalkBack, content descriptions, touch targets, Compose semantics, focus order, and Accessibility Scanner testing.

GuillemRoca/agent-skills-android · 35 tokens

android-device-testing

Use when writing or debugging instrumented tests (Espresso, UI Automator, Compose test rules), using ADB, managing emulators, or inspecting UI with Layout Inspector.

GuillemRoca/agent-skills-android · 39 tokens

android-ui-engineering

Use when building UI with Jetpack Compose. Covers component design, state hoisting, recomposition optimization, Material 3 theming, Navigation 3, adaptive layouts for large screens, previews, screenshot verification, and XML interop.

GuillemRoca/agent-skills-android · 52 tokens

android-data-persistence

Use when implementing local data storage with Room, DataStore, or offline-first patterns. Covers entities, DAOs, migrations, Paging3, and the repository pattern for data management.

GuillemRoca/agent-skills-android · 41 tokens

ci-cd-and-automation

Use when setting up or improving CI/CD pipelines for Android. Covers sequential quality gates, Gradle caching, emulator testing in CI, feature flags, and automated deployment to Play Store.

GuillemRoca/agent-skills-android · 43 tokens

security-and-hardening

Use when handling sensitive data, authentication, network communication, or before shipping to the Play Store. Three-tier framework (Always Do, Ask First, Never Do) with Android-specific security patterns.

GuillemRoca/agent-skills-android · 43 tokens