Core AI Models is a toolkit for exporting AI models, creating model components in Python, and running exported models in macOS and iOS apps through Swift utilities. It is for developers building on-device AI applications with Core AI. Its catalogue skills and plugin help coding agents work with the model export and runtime tooling.
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 apple/coreai-models --skill model-authoringgit clone --depth 1 https://github.com/apple/coreai-modelsWrote 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/apple/coreai-models/model-authoring)<a href="https://agentmods.dev/skills/apple/coreai-models/model-authoring"><img src="https://agentmods.dev/badge/skills/apple/coreai-models/model-authoring/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/apple/coreai-models/model-authoring"><img src="https://agentmods.dev/badge/skills/apple/coreai-models/model-authoring.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 | $0.00095 | $0.02084 |
| Opus 5.5 | $0.00038 | $0.00834 |
| Sonnet 5.5 | $0.00019 | $0.00417 |
| Haiku 4.5 | $0.00010 | $0.00208 |
Grade A, and why
model-authoring 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Authoring
This skill contains the hard-won empirical knowledge for making PyTorch models compile and run correctly on Apple hardware via Core AI. The rules here are stable across Core AI releases — they reflect hardware behavior, not API shapes.
Reference material
Use these resources on-demand — do not read all files upfront. Consult the relevant reference when the user's task requires specific patterns for a target platform, or when debugging.
| Resource | When to consult |
|---|---|
neural_engine_rules.md |
Neural Engine patterns: BC1S layout, Conv2d projections, per-head attention, KV cache readonly pattern, stride/dilation/pooling rules, causal mask, RoPE, chunked prefill |
gpu_rules.md |
GPU patterns: fused QKV, native SDPA, KV cache stateful pattern, MoE (GatherMM/SwitchLinear), memory-efficient loading, RMSNorm variants |
common_issues.md |
Debugging: PSNR issues, compilation errors, runtime problems, stale flags |
| coreai-models repo | Complete working reference implementations for LLMs, vision, audio, diffusion. Explore primitives/ and models/ directories. |
coreai-models: working reference implementations
For complex models (LLMs, MoE, multimodal, diffusion), explore the coreai-models repo before writing primitives from scratch. It has complete authoring primitives for both GPU and Neural Engine, including advanced patterns like iOS embedding quantization, MoE routing, and memory-efficient weight loading for large models. If the user has a local clone, explore it directly. If not, suggest cloning it.
Online docs: coreai-torch composite ops | externalization | composite ops API
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 · 154 lines · 95 tokens per session scan A 0786578f0fd3
model-authoring is a skill published in the GitHub repository apple/coreai-models (2,194 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 95 tokens to every session and 2,084 once invoked, about $0.0004 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
ml-kit-genai-prompt-api
Analyzes Android codebases to implement ML Kit GenAI Prompt API. Use this skill to send natural language requests on-device to Gemini Nano, use structured output with Prompt API, implement prefix caching, optimize the current prompt, or apply best practices.".
litert-runtime
Configures and implements LiteRT (.tflite) on-device inference on Android in Kotlin using the CompiledModel API on CPU and GPU. Use this skill for any Android LiteRT or .tflite task, including Gradle setup, image classification or vision/audio/embedding helpers, TensorBuffer reuse, Bitmap preprocessing…
foundation-models-on-device
Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+.
axiom-ai
Use when implementing, testing, or evaluating ANY Apple Intelligence, on-device AI, or speech-to-text feature. Covers Foundation Models, @Generable, LanguageModelSession, Tool protocol, eval suites, model-as-judge scoring, SpeechTranscriber, CoreML.
litert-lm
Creates an Android app that runs an open text LLM on the device, on the CPU or the GPU, with the LiteRT-LM Kotlin API. Use this skill to build a new chat, summarization or extraction app with a .litertlm model from Hugging Face litert-community (Gemma, Qwen, Llama, Phi) - the dependency and manifest entries, getting…
litert-runtime
Creates an Android app that runs a .tflite model on the CPU or the GPU with the LiteRT CompiledModel API in Kotlin. Use this skill to build a new app around a vision, audio or embedding model, or to add on-device inference to an existing app - the dependency, where the model file goes, the inference class, the…