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 5.5 | $0.00102 | $0.01658 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 (16 stars, last pushed 2mo ago), licensed MIT. It adds 255 tokens to every session and 4,144 once invoked, about $0.0010 per session on Opus 5.5. 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-firebase-connect
Add Firebase to a create-cmp app and wire it to its OWN real Firebase project. Use this when the user wants Firebase in their app, or asks "add firebase", "connect my app to firebase", "set up google-services.json", "wire firebase", "create a firebase project for this app", "replace the mock firebase config", "get 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…
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).…
add-repository
Add a data/domain slice ONLY — model, repository interface + impl, use case, and a hand-written fake — to this Compose Multiplatform app, cloned deterministically from the project's configured exemplar feature's data layer (qa/approvals.json's exemplarFeature — home by default). No screen, no ViewModel, no nav route…