arkit-hand-tracking-provider

arkit-hand-tracking-provider is a skill for Codex from tomkrikorian/visionOSAgents. It costs 54 tokens per session (490 once invoked), scanned A, original, MIT.

A set of instructions for building and troubleshooting visionOS 27 apps that read hand positions and joint movements through Apple’s ARKit HandTrackingProvider. It covers hand anchors, gestures, visualizations, permissions, and provider lifecycle.

In plain words
What is it for?
Use it to request hand-tracking access, read joint transforms, recognize custom gestures, drive SwiftUI or RealityKit interactions, visualize hands, and manage tracking sessions.
Why use it?
It helps handle device support, privacy authorization, update processing, and cleanup correctly when an app relies on raw hand-tracking data.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to request hand-tracking access, read joint transforms, recognize custom gestures, drive SwiftUI or RealityKit interactions, visualize hands, and manage tracking sessions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tomkrikorian/visionosagents/arkit-hand-tracking-provider
Install

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.

Any agent
npx skills add tomkrikorian/visionOSAgents --skill arkit-hand-tracking-provider
Clone the repo
git clone --depth 1 https://github.com/tomkrikorian/visionOSAgents

Made for: Codex.

Wrote 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.

agentmods badge for arkit-hand-tracking-provider

README.md
[![agentmods](https://agentmods.dev/badge/skills/tomkrikorian/visionosagents/arkit-hand-tracking-provider/github.svg)](https://agentmods.dev/skills/tomkrikorian/visionosagents/arkit-hand-tracking-provider)
Your own site
<a href="https://agentmods.dev/skills/tomkrikorian/visionosagents/arkit-hand-tracking-provider"><img src="https://agentmods.dev/badge/skills/tomkrikorian/visionosagents/arkit-hand-tracking-provider/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.

agentmods 80×15 button for arkit-hand-tracking-provider

Your own site · 80×15
<a href="https://agentmods.dev/skills/tomkrikorian/visionosagents/arkit-hand-tracking-provider"><img src="https://agentmods.dev/badge/skills/tomkrikorian/visionosagents/arkit-hand-tracking-provider.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 490 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.00490
Opus 5 $0.00027 $0.00245
Sonnet 5 $0.00011 $0.00098
Haiku 4.5 $0.00005 $0.00049

Measured 12d ago against content hash aee52acd1b20, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

arkit-hand-tracking-provider 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 12d 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.

skills/arkit-hand-tracking-provider/SKILL.md · 49 lines

What it actually says

ARKit Hand Tracking Provider

Quick Start

  1. Confirm the task needs raw hand/joint data; use SwiftUI or RealityKit gestures when high-level interaction is enough.
  2. Load the shared session guidance and the hand provider reference.
  3. Add hands privacy text and request the provider's required authorizations.
  4. Keep joint processing in a model layer, then bridge to SwiftUI or RealityKit only where needed.

Load References When

Reference When to Use
session-basics.md When setting up ARKitSession, authorization, event handling, or teardown.
hand-tracking-provider.md When using HandTrackingProvider, HandAnchor, or joint transforms.
anchor-processing.md When reconciling hand anchor updates into app state.
realitykit-bridge.md When visualizing hands or driving RealityKit entities.

Workflow

  1. Check HandTrackingProvider.isSupported.
  2. Request HandTrackingProvider.requiredAuthorizations.
  3. Run the provider in a long-lived ARKitSession.
  4. Process update sequences off the SwiftUI body path.
  5. Cancel the update task and stop the session on teardown.

Guardrails

  • Do not use raw hand tracking for ordinary taps, drags, or gaze-targeted UI that platform gestures already handle.
  • Do not assume both hands or every joint are always tracked.
  • Treat hand-tracking denial as a feature-level unavailable state, not as an app launch failure.

Output Expectations

Provide:

  • whether raw hand tracking is actually required
  • which hand provider references were used
  • the authorization and unsupported-device behavior
  • the joint processing and rendering path
Files

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.

Changes

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.

  1. 12d ago First seen · 49 lines · 54 tokens per session scan A aee52acd1b20

Subscribe to this mod's changes

arkit-hand-tracking-provider is a skill published in the GitHub repository tomkrikorian/visionOSAgents (61 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 490 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

orca-emulator-android

Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…

stablyai/orca · 102 tokens

android-tombstone-symbolication

Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…

dotnet/skills · 176 tokens

dogfood

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.

callstack/agent-device · 55 tokens

winapp-maui

Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.

microsoft/winappCli · 71 tokens

react-native-ease-refactor

Scan for Animated/Reanimated code and migrate to EaseView.

appandflow/react-native-ease · 18 tokens

apple-search-ads

When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…

Eronred/aso-skills · 127 tokens