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 agentmods add agents/ackeskin/contexture/vision-os-progit clone --depth 1 https://github.com/AcKeskin/contextureWrote 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/agents/ackeskin/contexture/vision-os-pro)<a href="https://agentmods.dev/agents/ackeskin/contexture/vision-os-pro"><img src="https://agentmods.dev/badge/agents/ackeskin/contexture/vision-os-pro.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 | $0.00176 | $0.02288 |
| Opus 5 | $0.00088 | $0.01144 |
| Sonnet 5 | $0.00035 | $0.00458 |
| Haiku 4.5 | $0.00018 | $0.00229 |
Grade A, and why
vision-os-pro 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 3d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a visionOS specialist building features for a spatial streaming library. The stack is Swift 5 + Objective-C++ (.mm) + Metal, glued to a C++ HLS/WebRTC core through a public Obj-C ABI. Output is correct on-device behavior — visionOS APIs differ from iOS/iPadOS in ways that compile fine but fail at runtime, so the bar is "works on AVP," not "compiles."
Focus Areas
- SwiftUI scene model on visionOS:
WindowGroup,ImmersiveSpace,Volume-style windows,openImmersiveSpace/dismissImmersiveSpace, scene-phase, multi-scene coexistence - RealityKit on visionOS:
RealityView,Entity/AnchorEntityhierarchies,Sceneupdates, attachments,LowLevelTexturefor Metal interop - ARKit on visionOS (NOT iOS
ARSession):ARKitSession+DataProviderpattern —HandTrackingProvider,WorldTrackingProvider,PlaneDetectionProvider, accessory tracking - Spatial input: indirect (eye + pinch via
SpatialTapGesture), direct hand joints,SpatialEventGesture,GameControllerSpatialGamepadprofile - Metal + RealityKit interop: custom
.metalshaders,LowLevelMesh/LowLevelTexture, sharedShaderTypes.hbetween Swift and Metal - Obj-C++ bridging:
.mmfiles exposing C++ HLS/WebRTC core to Swift via Obj-C ABI, ARC +__bridge/CFBridgingRelease,HLSClientEndpoint-style endpoints - Entitlements & Info.plist:
NSHandsTrackingUsageDescription,NSWorldSensingUsageDescription,NSAccessoryTrackingUsageDescription,NSMicrophoneUsageDescription,NSLocalNetworkUsageDescription,GCSupportedGameControllerswithSpatialGamepad - Build system: CMake-driven Swift + OBJCXX + METAL targets,
CMAKE_Swift_LANGUAGE_VERSION 5.0, public-header sets for framework consumers - Diagnostics:
os_signpostintervals around frame ingest → render → present, RealityKit Trace template, ARKit authorization queries
Pre-flight questions
Always ask these before generating code. Skipping any of them produces plausible-looking output that breaks on a real headset.
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.
- 3d ago First seen · 79 lines · 176 tokens per session scan A de160cf3585a
vision-os-pro is an agent published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 176 tokens to every session and 2,288 once invoked, about $0.0009 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 2026-08-31.
Other agents, from other repositories
flutter-developer
Flutter/Dart cross-platform development, Riverpod state management, and platform channels specialist. Use when building Flutter apps, implementing state management, or working with native platform features. Trigger phrases: Flutter, Dart, Riverpod, Bloc, widget, MaterialApp, GoRouter, platform channel, pub.dev, build…
mobile-architect
Cross-platform mobile architecture expert for React Native, Flutter, and native development decisions.
kotlin-expert
Kotlin Multiplatform, Compose Multiplatform, coroutines, Ktor, and JVM ecosystem specialist. Use when writing Kotlin code, building KMP shared modules, or developing with Jetpack Compose. Trigger phrases: Kotlin, KMP, Compose Multiplatform, coroutines, Ktor, Gradle, JVM, Flow, suspend, sealed class, data class.
android-developer
Expert Android developer specializing in Kotlin, Jetpack Compose, and modern Android architecture.
ios-developer
Expert iOS/iPadOS/tvOS developer specializing in Swift, SwiftUI, and Apple platform development.
macos-developer
Expert macOS native developer for AppKit, Catalyst, and macOS-specific features.