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-rendering-context-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-rendering-context-providers)<a href="https://agentmods.dev/skills/tomkrikorian/visionosagents/arkit-rendering-context-providers"><img src="https://agentmods.dev/badge/skills/tomkrikorian/visionosagents/arkit-rendering-context-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-rendering-context-providers"><img src="https://agentmods.dev/badge/skills/tomkrikorian/visionosagents/arkit-rendering-context-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 | $0.00065 | $0.00565 |
| Opus 5.5 | $0.00026 | $0.00226 |
| Sonnet 5.5 | $0.00013 | $0.00113 |
| Haiku 4.5 | $0.00006 | $0.00056 |
Grade A, and why
arkit-rendering-context-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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ARKit Rendering Context Providers
Quick Start
- Identify whether the rendering problem needs lighting, stereo viewpoint properties, or visual fidelity/device-fit data.
- Load the shared ARKit session guidance, then only the matching provider reference.
- Keep these providers as rendering inputs; do not mix them with anchor ownership unless the task also uses a spatial provider.
- Route RealityKit component or material implementation details to
$realitykit-visionos-developeror$shadergraph-editor.
Load References When
| Reference | When to Use |
|---|---|
session-basics.md |
When setting up ARKitSession, authorization, events, or teardown. |
environment-light-estimation-provider.md |
When using EnvironmentLightEstimationProvider and environment probes. |
stereo-properties-provider.md |
When using StereoPropertiesProvider for custom stereo rendering inputs. |
visual-fidelity-provider.md |
When using VisualFidelityProvider for device-fit status or foveated field of view. |
realitykit-bridge.md |
When provider output needs to drive RealityKit entities or rendering state. |
Workflow
- Check provider support and required authorizations.
- Decide how the rendering pipeline consumes provider output.
- Run only the provider needed for the rendering signal.
- Observe update sequences and store the latest rendering context in a model object that rendering code can consume.
Guardrails
- Do not present visual-fidelity coaching unless that is the intended user experience.
- Keep custom stereo-rendering decisions isolated from SwiftUI layout code.
- Treat environment lighting as an input to rendering, not as a replacement for authored material or Shader Graph work.
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 · 52 lines · 65 tokens per session scan A 1ca6f8da7be8
arkit-rendering-context-providers is a skill published in the GitHub repository tomkrikorian/visionOSAgents (66 stars, last pushed 4mo ago), licensed MIT. It adds 65 tokens to every session and 565 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-rendering-context-providers compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| arkit-rendering-context-providerstomkrikorian/visionOSAgents | Skill | 66 | 4mo ago | MIT | A | 65 | 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 |