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 skills/sceneview/sceneview/sceneview-iosnpx skills add sceneview/sceneview --skill sceneview-iosgit clone --depth 1 https://github.com/sceneview/sceneviewWhat 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 | $0.00148 | $0.03479 |
| Opus 5 | $0.00074 | $0.01740 |
| Sonnet 5 | $0.00030 | $0.00696 |
| Haiku 4.5 | $0.00015 | $0.00348 |
Grade A, and why
sceneview-ios 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What SceneViewSwift is
SceneViewSwift is the Apple-platform half of the SceneView SDK — a declarative
SwiftUI API over RealityKit. Same mental model as the Android library
(SceneView { } / ARSceneView { }) but expressed with SwiftUI result-builders
and view modifiers, not Jetpack Compose.
- 3D —
SceneView { … }SwiftUI view (iOS / macOS / visionOS). - AR —
ARSceneView(…)SwiftUI view (iOS only — ARKit). - Renderer — RealityKit. There is no Filament on Apple platforms.
- Distribution — Swift Package Manager. The package lives in the
github.com/sceneview/sceneviewmonorepo; consumers add it by URL and pin a version tag (currently4.33.0).
SceneViewSwift is consumable directly from Swift, and also underneath the
Flutter and React Native bridges.
Authoritative API reference
Three sources, in priority order:
docs/docs/cheatsheet-ios.mdin the repo — the complete Apple-platform API reference (every node factory, view modifier, environment preset, the Android↔Apple mapping table, and the iOS parity-status tables). https://github.com/sceneview/sceneview/blob/main/docs/docs/cheatsheet-ios.mdSceneViewSwift/Sources/SceneViewSwift/— the actual Swift source. When in doubt about a signature, read it. Node factories live underNodes/, the views inSceneView.swift/ARSceneView.swift.samples/ios-demo/SceneViewDemo/Views/Demos/— a working SwiftUI demo for every feature. Read the demo, do NOT improvise an API.
llms.txt at the repo root carries the cross-platform surface but is
Android-centric — prefer cheatsheet-ios.md for Swift.
When to use this skill
Trigger on any of:
- "Build me a 3D viewer / AR app in SwiftUI."
- "Load a
.usdz/.glb/.gltf/.realitymodel on iOS." - "Place a model on a detected AR plane in ARKit + SwiftUI."
- "Add 3D content to a visionOS / macOS app with SceneView."
- "Convert this SceneKit / RealityView code to SceneViewSwift."
- "Make
SceneViewerfrom our Compose Multiplatform app actually render on iOS."
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.
- 3d ago First seen · 291 lines · 148 tokens per session scan A 94da41af5a08
sceneview-ios is a skill published in the GitHub repository sceneview/sceneview (1,299 stars, last pushed 4d ago), licensed Apache-2.0. It adds 148 tokens to every session and 3,479 once invoked, about $0.0007 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
compose-ui-testing-patterns
Use when writing or reviewing Jetpack Compose UI tests, screenshot tests, previews, semantics assertions, fake image loading, keyboard input, focus assertions, interaction state (hover/pressed/focused), or tests for plain state-driven UI composables.
compose-animations
Use when writing or reviewing Jetpack Compose motion: visibility enter/exit, animating one property toward a target, color or size transitions, multiple properties from one state, switching composable content, or choosing between AnimatedVisibility, animateAsState, rememberTransition, AnimatedContent, and Crossfade.
compose-focus-navigation
Use when writing or reviewing Jetpack Compose UI for TV, keyboard, desktop, accessibility focus, D-pad navigation, FocusRequester, focusProperties, key events, or initial focus behavior.
compose-state-and-effects
Use when writing or reviewing Jetpack Compose state ownership, remember state, state hoisting, screen state holders, LaunchedEffect, DisposableEffect, SideEffect, Flow collection, navigation, snackbar, analytics, or focus requests.
using-chrisbanes-skills
Use when debugging, benchmarking, or profiling leads into Kotlin or Jetpack Compose source before the cause is known, or when one task spans multiple Kotlin or Compose concerns, especially plain Kotlin Flow or navigation delivery plus sealed branching.
compose-component-design
Use when designing or reviewing reusable Jetpack Compose component APIs with modifier parameters, root layout placement, caller-provided variable content, primitive content parameters, optional content, or boolean shape flags.