PhoneClaw is a local AI agent framework that runs on phones and edge devices, using on-device models to understand requests and perform mobile tasks through native skills. It is for people who want an AI assistant on an iPhone or similar device with access to functions such as calendars, reminders, contacts, health data, voice, and image understanding, while optionally using web search or a Mac Gateway for selected tasks.
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 kellyvv/PhoneClaw --skill mlx-swiftgit clone --depth 1 https://github.com/kellyvv/PhoneClawWrote 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/kellyvv/phoneclaw/mlx-swift)<a href="https://agentmods.dev/skills/kellyvv/phoneclaw/mlx-swift"><img src="https://agentmods.dev/badge/skills/kellyvv/phoneclaw/mlx-swift/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/kellyvv/phoneclaw/mlx-swift"><img src="https://agentmods.dev/badge/skills/kellyvv/phoneclaw/mlx-swift.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 | $0.00025 | $0.03118 |
| Opus 5 | $0.00013 | $0.01559 |
| Sonnet 5 | $0.00005 | $0.00624 |
| Haiku 4.5 | $0.00003 | $0.00312 |
Grade A, and why
swift-mlx 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- swift-mlx — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MLX Swift Framework
MLX Swift is Apple's high-performance machine learning framework designed specifically for Apple Silicon. It provides NumPy-like array operations with lazy evaluation, automatic differentiation, and unified CPU/GPU memory.
When to Use This Skill
- Array operations on Apple Silicon (MLXArray)
- Building neural networks (MLXNN)
- Training models with automatic differentiation
- Custom Metal kernels via MLXFast
- Performance optimization with JIT compilation
Architecture Overview
MLXOptimizers (Adam, AdamW, SGD, etc.)
↓
MLXNN (Layers, Modules, Losses)
↓
MLX (Arrays, Ops, Transforms, FFT, Linalg, Random)
↓
Cmlx (C/C++ bindings, Metal GPU)
Key File Reference
| Purpose | File Path |
|---|---|
| Core array | Source/MLX/MLXArray.swift |
| Operations | Source/MLX/Ops.swift |
| Transforms | Source/MLX/Transforms.swift |
| Factory methods | Source/MLX/Factory.swift |
| Neural layers | Source/MLXNN/*.swift |
| Optimizers | Source/MLXOptimizers/Optimizers.swift |
| Fast ops | Source/MLX/MLXFast.swift |
| Custom kernels | Source/MLX/MLXFastKernel.swift |
| Wired memory coordinator | Source/MLX/WiredMemory.swift |
| GPU working-set helper | Source/MLX/GPU+Metal.swift |
Quick Start
Basic Array Creation
import MLX
// Create arrays
let a = MLXArray([1, 2, 3, 4])
let b = MLXArray(0 ..< 12, [3, 4]) // Shape [3, 4]
let c = MLXArray.zeros([2, 3])
let d = MLXArray.ones([4, 4], dtype: .float32)
// Random arrays (use MLXRandom namespace or free functions)
let uniform = MLXRandom.uniform(0.0 ..< 1.0, [3, 3])
let normal = MLXRandom.normal([100])
Array Properties
let array = MLXArray(0 ..< 12, [3, 4])
array.shape // [3, 4]
array.ndim // 2
array.size // 12
array.dtype // .int64
array.count // 3 (first dimension)
Basic Operations
let a = MLXArray([1.0, 2.0, 3.0])
let b = MLXArray([4.0, 5.0, 6.0])
// Arithmetic (lazy - not computed until eval)
let sum = a + b
let product = a * b
let matmul = a.matmul(b.T)
// Force evaluation
eval(sum, product)
// or
sum.eval()
What ships with it
10 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.
- references/arrays.md 6.3 KB
- references/concurrency.md 7.4 KB
- references/custom-kernels.md 7.7 KB
- references/custom-layers.md 7.0 KB
- references/deprecated.md 7.8 KB
- references/neural-networks.md 8.8 KB
- references/operations.md 7.0 KB
- references/optimizers.md 6.9 KB
- references/transforms.md 6.1 KB
- references/wired-memory.md 3.5 KB
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 · 395 lines · 25 tokens per session scan A 06192f2638e4
swift-mlx is a skill published in the GitHub repository kellyvv/PhoneClaw (1,237 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 3,118 once invoked, about $0.0001 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
developing-genkit-dart
Generates code and provides documentation for the Genkit Dart SDK. Use when the user asks to build AI agents in Dart, use Genkit flows, or integrate LLMs into Dart/Flutter applications.
xcode-compilation-analyzer
Analyze Swift and mixed-language compile hotspots using build timing summaries and Swift frontend diagnostics, then produce a recommend-first source-level optimization plan. Use when a developer reports slow compilation, type-checking warnings, expensive clean-build compile phases, long CompileSwiftSources tasks…
litert-compiled-model-migration
Rapidly migrate an Android application from legacy TensorFlow Lite (TFLite) to modern LiteRT CompiledModel API v2.1.6 in Open Source GitHub repositories. Supports True Async Execution (runAsync), Zero-Copy I/O Buffers, NPU JIT compilation, and automated 2-stage verification self-testing.
compiled-model-app-scaffolding
Build a new Android app (Kotlin, Compose) around a verified LiteRT model using the CompiledModel API - the app architecture, the inference-layer lifecycle rules, model delivery, and the UI traps that masquerade as model bugs. Use when turning a converted and device-verified model into a demo or product app, when an…
build-feature
Build an iOS feature using ShipSwift components. Use when the user says "build", "create", "add a feature", or describes an iOS feature they want to implement.
ios-slim-bindings
Create iOS slim bindings for MAUI. USE FOR: slim iOS binding, Native Library Interop, Swift/Objective-C wrappers, XcodeGen project.yml, Podfile, CocoaPods static linking, BUILDLIBRARYFORDISTRIBUTION, XcodeProject MSBuild, @objc/[Export] selector crashes, async completion handlers. DO NOT USE FOR: Android bindings…