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 dotnet/maui-labs --skill maui-essentials-aigit clone --depth 1 https://github.com/dotnet/maui-labsWrote 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/dotnet/maui-labs/maui-essentials-ai)<a href="https://agentmods.dev/skills/dotnet/maui-labs/maui-essentials-ai"><img src="https://agentmods.dev/badge/skills/dotnet/maui-labs/maui-essentials-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.
<a href="https://agentmods.dev/skills/dotnet/maui-labs/maui-essentials-ai"><img src="https://agentmods.dev/badge/skills/dotnet/maui-labs/maui-essentials-ai.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 | $0.00086 | $0.01363 |
| Opus 5 | $0.00043 | $0.00681 |
| Sonnet 5 | $0.00017 | $0.00273 |
| Haiku 4.5 | $0.00009 | $0.00136 |
Grade A, and why
maui-essentials-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 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.
How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MAUI Essentials AI
Use this skill when a MAUI app should use on-device AI through
Microsoft.Maui.Essentials.AI and Microsoft.Extensions.AI abstractions.
Response Checklist
- Mention the package and primary types explicitly:
Microsoft.Maui.Essentials.AI,AppleIntelligenceChatClient,NLEmbeddingGenerator. - Keep platform support explicit (Apple chat support is iOS/macOS/Mac Catalyst 26+; embeddings have broader Apple OS coverage).
- For app tools, show
UseFunctionInvocationand route source-generated tool definitions tomaui-ai-tool-bindingswhen appropriate.
Platform Support
Chat support:
| Platform | Status |
|---|---|
| iOS 26+ | Apple Intelligence / Foundation Models |
| Mac Catalyst 26+ | Apple Intelligence |
| macOS 26+ | Apple Intelligence |
| Android | Coming soon |
| Windows | Coming soon |
Embedding support:
| Platform | Status |
|---|---|
| iOS 13+ | NaturalLanguage embeddings |
| Mac Catalyst 13.1+ | NaturalLanguage embeddings |
| macOS 10.15+ | NaturalLanguage embeddings |
| Android | Not supported |
| Windows | Not supported |
Version numbers for Apple Intelligence support reflect currently announced OS versions; verify final released platform versions before shipping.
Design fallback behavior for unsupported platforms. Do not silently route private data to a cloud model unless the user explicitly wants a cloud fallback.
Install and Register
dotnet add package Microsoft.Maui.Essentials.AI --prerelease
using Microsoft.Extensions.AI;
using Microsoft.Extensions.DependencyInjection;
using Microsoft.Maui.Essentials.AI;
#if IOS || MACCATALYST || MACOS
builder.Services.AddSingleton<NLEmbeddingGenerator>();
builder.Services.AddSingleton<IEmbeddingGenerator<string, Embedding<float>>>(sp =>
sp.GetRequiredService<NLEmbeddingGenerator>());
if (OperatingSystem.IsIOSVersionAtLeast(26) ||
OperatingSystem.IsMacCatalystVersionAtLeast(26) ||
OperatingSystem.IsMacOSVersionAtLeast(26))
{
builder.Services.AddSingleton<IChatClient>(new AppleIntelligenceChatClient());
}
else
{
// Leave IChatClient unregistered and check availability before use,
// or register an app-specific unavailable implementation.
}
#endif
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 Changed · -22 tokens per session d26eb86be6da
- 11d ago First seen · 182 lines · 108 tokens per session scan A bb7500a7a7c5
maui-essentials-ai is a skill published in the GitHub repository dotnet/maui-labs (214 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 1,363 once invoked, about $0.0004 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
apple-on-device-ai
On-device generative AI on Apple platforms (iOS 26+) — the Foundation Models framework (SystemLanguageModel.availability, LanguageModelSession, respond(to:)/streamResponse, @Generable + @Guide guided generation, the Tool protocol for tool-calling, instructions, GenerationOptions, and Guardrails), plus choosing among…
vision-framework
On-device image analysis for an iOS fintech app with Apple's Vision + VisionKit. Covers the modern Swift Vision API (iOS 18+: RecognizeTextRequest OCR, DetectFaceRectanglesRequest, DetectBarcodesRequest, DetectDocumentSegmentationRequest, GenerateForegroundInstanceMaskRequest, TrackObjectRequest, CoreMLRequest, all…
coreml
On-device ML inference with Core ML on iOS/iPadOS 26. Covers model formats (.mlmodel/.mlpackage/.mlmodelc), the Xcode auto-generated model class + Input/Output, MLModel loading (async load / compileModel), MLFeatureProvider / MLFeatureValue, MLModelConfiguration.computeUnits…
argent-device-interact
Interact with an iOS simulator, Android emulator, or Chromium (CDP) app using argent MCP tools. Use when tapping UI elements, performing gestures, scrolling/swiping, typing text, pressing hardware buttons, launching apps, opening URLs, taking screenshots, waiting for an element to appear or disappear, or checking…
argent-metro-debugger
Debug a JS runtime via CDP using argent debugger tools. Primary path is React Native via Metro (iOS / Android / Vega); a subset of the tools (debugger-connect, debugger-status, debugger-evaluate, debugger-log-registry) also drive a Chromium (CDP) app's renderer (an Electron app, or any Chromium browser exposing CDP)…
argent-settings-permissions
Grant, deny, or reset an app's runtime permissions (camera, microphone, photos, contacts, notifications, calendar, location, location-always, media-library, motion, reminders) on an iOS simulator or Android device using the argent settings-permissions tool - without navigating the system Settings UI. Use when the…