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 spatial-app-architecturegit 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/spatial-app-architecture)<a href="https://agentmods.dev/skills/tomkrikorian/visionosagents/spatial-app-architecture"><img src="https://agentmods.dev/badge/skills/tomkrikorian/visionosagents/spatial-app-architecture/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/spatial-app-architecture"><img src="https://agentmods.dev/badge/skills/tomkrikorian/visionosagents/spatial-app-architecture.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 | $0.00772 |
| Opus 5.5 | $0.00026 | $0.00309 |
| Sonnet 5.5 | $0.00013 | $0.00154 |
| Haiku 4.5 | $0.00006 | $0.00077 |
Grade A, and why
spatial-app-architecture 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spatial App Architecture
Quick Start
Use this skill for architecture questions, not API questions.
Use it when:
- you need to choose the right surface: window, volume, immersive space, or a mixed flow
- you are deciding which state is app-wide, scene-scoped, immersive-scoped, or view-local
- a root file owns too many concerns and needs a refactor plan
- you need a file or module plan before writing or splitting SwiftUI code
Load References When
| Reference | When to Use |
|---|---|
references/surface-selection.md |
When choosing window vs volume vs immersive space and their lifecycle boundaries. |
references/state-ownership.md |
When deciding what belongs to the app, scene, feature coordinator, RealityKit owner, or view. |
references/file-layouts.md |
When proposing a layered or feature-sliced file and module shape. |
references/refactor-playbook.md |
When the app already exists and the main task is refactoring without breaking behavior. |
references/anti-patterns.md |
When you need to call out structural smells or explain why an approach is wrong. |
Workflow
- Classify the feature by user job and current or intended surface.
- Choose the owning surface model: window, volume, immersive space, or a combination.
- Assign state ownership boundaries: app, scene, immersive, feature, view.
- Choose a file/module shape that matches the ownership model.
- Define the implementation handoff: SwiftUI, RealityKit, ARKit, SharePlay, or build/debug.
- If this is a refactor, sequence the extraction so behavior stays stable.
- Verify the structure with
build-run-debugafter the first usable slice.
When To Switch Skills
- Switch to
spatial-swiftui-developerwhen the surface and ownership model are already chosen and the next step is implementing SwiftUI APIs. - Switch to
realitykit-visionos-developerwhen the work is mainly about entities, components, systems, or RealityKit runtime behavior. - Switch to
arkit-visionos-developerwhen the architecture choice depends on provider constraints, anchors, or tracked-world behavior. - Switch to
shareplay-developerwhen the app structure is driven by group activity or shared immersive presence. - Switch to
build-run-debugafter the first usable architectural slice exists and needs validation.
What ships with it
6 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 · 73 lines · 65 tokens per session scan A b9dde29d5f2d
spatial-app-architecture 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 772 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.
spatial-app-architecture compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| spatial-app-architecturetomkrikorian/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 |