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 tomkrikorian/visionOSAgents --skill arkit-visionos-developergit clone --depth 1 https://github.com/tomkrikorian/visionOSAgentsWrote 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/tomkrikorian/visionosagents/arkit-visionos-developer)<a href="https://agentmods.dev/skills/tomkrikorian/visionosagents/arkit-visionos-developer"><img src="https://agentmods.dev/badge/skills/tomkrikorian/visionosagents/arkit-visionos-developer.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00067 | $0.00716 |
| Opus 5 | $0.00034 | $0.00358 |
| Sonnet 5 | $0.00013 | $0.00143 |
| Haiku 4.5 | $0.00007 | $0.00072 |
Grade A, and why
arkit-visionos-developer 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 8d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ARKit visionOS Developer
Quick Start
- If the task names a specific provider family, switch to the matching provider-focused skill below.
- If the task spans provider families, load the provider index plus shared session and anchor references first.
- Add only the usage strings, entitlements, and authorizations required by the providers you actually use.
- Keep anchor state in a model layer, and bridge into RealityKit only when you have a rendering target.
- If the issue is app launch, test flow, simulator behavior, or signing,
switch to
build-run-debugorsigning-entitlements.
Provider-Focused Skills
| Skill | When to Use |
|---|---|
$arkit-spatial-tracking-providers |
World tracking, plane detection, scene reconstruction, room tracking, or shared coordinate spaces. |
$arkit-hand-tracking-provider |
Hand anchors, joint transforms, custom hand gestures, or hand visualizations. |
$arkit-reference-tracking-providers |
Known image tracking, object tracking, barcode detection, or accessory tracking. |
$arkit-camera-access-providers |
Camera frame streams or region-scoped camera content. |
$arkit-rendering-context-providers |
Environment lighting, stereo properties, device fit, or foveated field-of-view tuning. |
Load Shared References When
| Reference | When to Use |
|---|---|
references/provider-index.md |
When you need the provider map and routing guidance. |
references/session-basics.md |
When setting up ARKitSession, authorization, or shared lifecycle rules. |
references/anchor-processing.md |
When reconciling anchorUpdates, IDs, and model-layer state. |
references/realitykit-bridge.md |
When ARKit data needs to become visible RealityKit scene content. |
Workflow
- Choose the provider family or focused skill.
- Load the shared session and lifecycle guidance first.
- Add only the provider references that match the task.
- Keep anchor reconciliation in a model layer.
- Bridge into RealityKit only after the model layer has stable state.
What ships with it
22 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.
- agents/openai.yaml 389 B
- assets/studio-meije-logo-small.png 4.2 KB
- assets/studio-meije-logo.png 42 KB
- references/accessory-tracking-provider.md 2.9 KB
- references/anchor-processing.md 1.3 KB
- references/barcode-detection-provider.md 2.1 KB
- references/camera-frame-provider.md 1.9 KB
- references/camera-region-provider.md 2.2 KB
- references/environment-light-estimation-provider.md 1.7 KB
- references/hand-tracking-provider.md 1.7 KB
- references/image-tracking-provider.md 2.0 KB
- references/object-tracking-provider.md 3.0 KB
- references/plane-detection-provider.md 2.0 KB
- references/provider-index.md 5.5 KB
- references/realitykit-bridge.md 841 B
- references/room-tracking-provider.md 1.7 KB
- references/scene-reconstruction-provider.md 1.7 KB
- references/session-basics.md 2.4 KB
- references/shared-coordinate-space-provider.md 1.9 KB
- references/stereo-properties-provider.md 1.7 KB
- references/visual-fidelity-provider.md 3.9 KB
- references/world-tracking-provider.md 2.1 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.
- 8d ago First seen · 67 lines · 67 tokens per session scan A 462f36892919
arkit-visionos-developer is a skill published in the GitHub repository tomkrikorian/visionOSAgents (60 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 716 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.
Other skills, from other repositories
developer-device-platform-basics
Provides guidance and instructions on managing remote devices on Developer Device Platform (DDP). Use when reserving remote Android devices, establishing connection tunnels, checking session status, or extending/cancelling leases. Don't use for iOS or local device/hardware inquiries.
camerax
Provide technical guidance for Android camera development with CameraX. Use when implementing camera features, handling asynchronous recording lifecycles, wiring low-level hardware interop using CameraX, or integrating ML Kit or Media3 effects.
mobile-platform-native-capabilities-integrate
Build a Salesforce LWC that uses native mobile device capabilities — barcode scanner, biometrics, location, NFC, calendar, contacts, document scanner, geofencing, AR space capture, app review, and payments. Use this skill when the user asks for an LWC that scans a barcode, captures a photo of a document, reads…
audio-skill
Control Android audio - get/set volume, mute/unmute for media, ringtone, notification, and call volumes.
bluetooth-skill
Control Android Bluetooth - enable, disable, get status, and list paired devices.
motion-skill
Get Android motion sensor data - accelerometer, gyroscope, detect motion, shake gestures, and device orientation.