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-reference-tracking-providersgit 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-reference-tracking-providers)<a href="https://agentmods.dev/skills/tomkrikorian/visionosagents/arkit-reference-tracking-providers"><img src="https://agentmods.dev/badge/skills/tomkrikorian/visionosagents/arkit-reference-tracking-providers/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/tomkrikorian/visionosagents/arkit-reference-tracking-providers"><img src="https://agentmods.dev/badge/skills/tomkrikorian/visionosagents/arkit-reference-tracking-providers.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00064 | $0.00627 |
| Opus 5.5 | $0.00026 | $0.00251 |
| Sonnet 5.5 | $0.00013 | $0.00125 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
arkit-reference-tracking-providers 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 2mo 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ARKit Reference Tracking Providers
Quick Start
- Identify the physical reference: known image, reference object, barcode, or supported accessory.
- Load the shared ARKit session guidance, then the matching provider file.
- Confirm required authorizations, privacy text, entitlement, and profile requirements before debugging runtime data flow.
- Keep tracked-reference state separate from RealityKit presentation state.
Load References When
| Reference | When to Use |
|---|---|
session-basics.md |
When setting up ARKitSession, authorization, events, or teardown. |
anchor-processing.md |
When reconciling reference anchor updates into app state. |
realitykit-bridge.md |
When tracked references need visible RealityKit content. |
image-tracking-provider.md |
When using ImageTrackingProvider with known 2D images. |
object-tracking-provider.md |
When using ObjectTrackingProvider with 3D reference objects. |
barcode-detection-provider.md |
When using BarcodeDetectionProvider; check barcode entitlement first. |
accessory-tracking-provider.md |
When using AccessoryTrackingProvider with supported accessories. |
Workflow
- Verify the reference asset or target set is correct before touching session code.
- Check provider support and entitlements before interpreting missing updates.
- Request only the required authorizations for the chosen provider set.
- Store tracked anchors by stable IDs and remove stale model state on removed updates.
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.
- 2mo ago First seen · 54 lines · 64 tokens per session scan A 041b0a5367ab
arkit-reference-tracking-providers is a skill published in the GitHub repository tomkrikorian/visionOSAgents (66 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 627 once invoked, about $0.0003 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.
arkit-reference-tracking-providers compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| arkit-reference-tracking-providerstomkrikorian/visionOSAgents | Skill | 66 | 4mo ago | MIT | A | 64 | Codex |
| orca-emulator-androidstablyai/orca | Skill | 120k | today | MIT | A | 102 | Claude Code, Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | today | Apache-2.0 | A | 56 | Claude Code |
| android-tombstone-symbolicationdotnet/skills | Skill | 5.9k | today | MIT | A | 176 | Claude Code |
| dogfoodcallstack/agent-device | Skill | 5.3k | today | MIT | A | 55 | Claude Code |
| winapp-mauimicrosoft/winappCli | Skill | 1.4k | today | MIT | A | 68 | Claude Code |
| app_remixrome-os/rome | Skill | 894 | yesterday | MIT | A | 50 | Claude Code, Codex |