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 TalissonVitorino/kmp-ios-skills --skill coremlgit clone --depth 1 https://github.com/TalissonVitorino/kmp-ios-skillsWrote 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/talissonvitorino/kmp-ios-skills/coreml)<a href="https://agentmods.dev/skills/talissonvitorino/kmp-ios-skills/coreml"><img src="https://agentmods.dev/badge/skills/talissonvitorino/kmp-ios-skills/coreml/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/talissonvitorino/kmp-ios-skills/coreml"><img src="https://agentmods.dev/badge/skills/talissonvitorino/kmp-ios-skills/coreml.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 | $0.00255 | $0.04144 |
| Opus 5 | $0.00128 | $0.02072 |
| Sonnet 5 | $0.00051 | $0.00829 |
| Haiku 4.5 | $0.00026 | $0.00414 |
Grade A, and why
coreml 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 10d 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core ML (on-device inference, iOS 26)
Load and run trained ML models on device with the Neural Engine / GPU / CPU. Core ML is the inference & fine-tune runtime — it does not convert or train models from scratch.
- Runtime choice / model conversion: picking Core ML vs Foundation Models vs MLX, or converting a PyTorch/TF model with
coremltools→apple-on-device-ai. - Image analysis (OCR, barcodes, faces, saliency): Vision's own requests →
vision-framework. Use Core ML directly only for your custom model. - KMP boundary: keep the model + prediction in
iosMain; expose acommonMain interface Classifierand bind anactual. Marshal plain types (arrays, floats) across — never a Core ML object. Seeexpect-actual,kmp-ios-integration.
Contents
- Model formats
- Add a model & the generated class
- Loading MLModel
- Compute units
- Predictions (generated class vs raw MLFeatureProvider)
- Async & batch prediction
- Images & MLFeatureValue
- MLTensor (iOS 18+)
- Stateful models (MLState)
- Profiling with MLComputePlan
- Downloaded models & on-device personalization
- Correctness checklist
- References:
references/predictions-and-batching.md,references/vision-and-images.md,references/profiling-and-personalization.md
Model formats
| Extension | What it is | Where it comes from |
|---|---|---|
.mlmodel |
Legacy neural-network / tree / pipeline source model | coremltools convert (older) |
.mlpackage |
ML Program package (weights + spec); the modern default, needed for float16 weights, compression, iOS-18 features | coremltools convert (convert_to="mlprogram") |
.mlmodelc |
Compiled model directory the runtime actually loads | Xcode build, or MLModel.compileModel(at:) at runtime |
- Drop
.mlmodel/.mlpackageinto the Xcode project → Xcode compiles it to.mlmodelcat build time and generates a Swift class. - A model downloaded at runtime arrives as
.mlmodel/.mlpackageand must be compiled on-device before use (see below). .mlmodelcis a folder, not a file — copy the whole directory when moving it.
What ships with it
3 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.
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.
- 10d ago First seen · 277 lines · 255 tokens per session scan A cbe4934167db
coreml is a skill published in the GitHub repository TalissonVitorino/kmp-ios-skills (12 stars, last pushed 15d ago), licensed MIT. It adds 255 tokens to every session and 4,144 once invoked, about $0.0013 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
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…
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…
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…
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…
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…
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).…