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 gongyijie85/dsh-ecc --skill foundation-models-on-devicegit clone --depth 1 https://github.com/gongyijie85/dsh-eccWrote 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/gongyijie85/dsh-ecc/foundation-models-on-device)<a href="https://agentmods.dev/skills/gongyijie85/dsh-ecc/foundation-models-on-device"><img src="https://agentmods.dev/badge/skills/gongyijie85/dsh-ecc/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.
<a href="https://agentmods.dev/skills/gongyijie85/dsh-ecc/foundation-models-on-device"><img src="https://agentmods.dev/badge/skills/gongyijie85/dsh-ecc/foundation-models-on-device.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 | $0.00056 | $0.01749 |
| Opus 5 | $0.00028 | $0.00874 |
| Sonnet 5 | $0.00011 | $0.00350 |
| Haiku 4.5 | $0.00006 | $0.00175 |
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 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.
This is a copy
91% identical to foundation-models-on-device — 23 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.
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?")
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 First seen · 244 lines · 56 tokens per session scan A 4f239588e43f
foundation-models-on-device is a skill published in the GitHub repository gongyijie85/dsh-ecc (7 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 1,749 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to foundation-models-on-device, differing in 23 lines, and is treated as a copy.
Other skills, from other repositories
manage-taskboard
Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…
bio-workbench
A set of rules for running reproducible bioinformatics analyses, which study biological data with software. It uses small self-contained scripts, recorded inputs and outputs, environment details, and version history so results can be repeated.
visionary-cli
Analyze images with DeepSeek's vision model via the visionary-server CLI. Use this whenever the user provides an image, photo, screenshot, or document with images - run vision to look at it rather than guessing.
cvqnn
Skill for understanding, using, and implementing the Continuous Variable Quantum Neural Network (CVQNN) for binary classification via the CVQNNAlgorithm class, CVSimulator, and CVClassifier. Skill-first for covered code generation, runnable examples, execution, debugging, validation, and fixed workflows.
vqc
Skill for understanding, using, and implementing the Variational Quantum Classifier (VQC) for Iris dataset classification with data re-uploading and Parameter Shift Rule via the VQCAlgorithm class. Skill-first for covered code generation, runnable examples, execution, debugging, validation, and fixed workflows.
pennylane
PennyLane - A versatile quantum machine learning library that supports hybrid quantum-classical computations.