spatial-design

spatial-design is a skill for Claude Code from rshankras/claude-code-apple-skills. It costs 90 tokens per session (2,277 once invoked), scanned A, original, MIT.

A design guide for visionOS apps and immersive experiences, where windows and content are placed around the user in three-dimensional space. It covers layout, eye-and-hand input, motion comfort, immersion, sound, and video formats.

In plain words
What is it for?
Use it to design or review visionOS windows, volumes, immersive spaces, gestures, hover effects, environments, spatial audio, and spatial or 180-degree video experiences.
Why use it?
It addresses problems that do not arise in ordinary screens, such as uncomfortable motion, hard-to-reach controls, poor field-of-view placement, and conflicting depth cues.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the apple-skills plugin — 182 skills shipped together , and of apple-skills

Good fit Use it to design or review visionOS windows, volumes, immersive spaces, gestures, hover effects, environments, spatial audio, and spatial or 180-degree video experiences.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rshankras/claude-code-apple-skills/spatial-design
Install

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.

Any agent
npx skills add rshankras/claude-code-apple-skills --skill spatial-design
Clone the repo
git clone --depth 1 https://github.com/rshankras/claude-code-apple-skills

Made for: Claude Code.

Or install apple-skills, the plugin that ships this one along with the rest of its 182 skills.

Wrote 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.

agentmods badge for spatial-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/rshankras/claude-code-apple-skills/spatial-design/github.svg)](https://agentmods.dev/skills/rshankras/claude-code-apple-skills/spatial-design)
Your own site
<a href="https://agentmods.dev/skills/rshankras/claude-code-apple-skills/spatial-design"><img src="https://agentmods.dev/badge/skills/rshankras/claude-code-apple-skills/spatial-design/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.

agentmods 80×15 button for spatial-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/rshankras/claude-code-apple-skills/spatial-design"><img src="https://agentmods.dev/badge/skills/rshankras/claude-code-apple-skills/spatial-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,277 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00090 $0.02277
Opus 5.5 $0.00036 $0.00911
Sonnet 5.5 $0.00018 $0.00455
Haiku 4.5 $0.00009 $0.00228

Measured yesterday against content hash 17631b1cbb68, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spatial-design 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 yesterday.

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.

skills/visionos/spatial-design/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spatial Design (visionOS)

The design rules that make a visionOS app comfortable instead of exhausting — distilled from Apple's spatial-design sessions (WWDC23–26). Widget-specific rules live in visionos/widgets; custom immersive-environment production and budgets live in immersive-environments.md.

When This Skill Activates

  • Designing or reviewing a visionOS app, window, volume, or immersive space
  • "Users say it's tiring / uncomfortable / hard to hit controls"
  • Porting an iPad app and deciding what should become spatial
  • Adding hover effects, custom gestures, environments, or spatial audio
  • Choosing a video experience format (spatial, 180°, 360°, wide-FOV, Apple Immersive)

The prime directive: find the key moment

Don't window a 2D app. Identify the one thing only possible on visionOS — the "key moment" — and build around it. Immersion has three approaches, and full immersion is not mandatory: full environments · integration with real surroundings (scene sensing) · meaningful audio.

Layout & ergonomics

  • Wide beats tall — layouts match the human field of view; turning the head left/right is easier than up/down. Center = primary content; edges = secondary, infrequent actions.
  • Default placement sits along the natural line of sight, a bit further than arm's reach; extended reading goes farther out, centered and slightly below eye line.
  • Design in points, not meters — dynamic scale keeps windows legible at any distance (they scale up as they move away). Never fixed scale for UI; keep custom UI facing the viewer.
  • Depth is hierarchy, used sparingly — "prefer subtle depth" (a modal pushes its parent back). Keep text flat; 3D text is hard to read at an angle.
  • Glass, never solid window backgrounds — solid colors block the world, don't adapt to lighting, and "can feel constricting." Elements on glass use vibrancy + white text/symbols; system colors over custom (they're calibrated for legibility). Brand color goes in backgrounds or whole buttons, not glyphs.
  • Typography runs heavier than iOS: body = medium (vs regular), titles = bold (vs semibold), slightly increased tracking. Avoid small/lightweight custom fonts.
  • Component specs: vertical tab bar fixed left, ≤6 items, expands on gaze · ornaments overlap the window's bottom edge by 20pt, borderless buttons inside · sheets appear centered at the parent's Z while the parent dims and pushes back · nested corners concentric (outer radius = inner + padding).
  • SwiftUI spatial layout: stacks default to .back depth alignment — switch to .front when content should read toward the viewer; rotation3DLayout (not rotation3DEffect) when rotation must affect layout; SpatialContainer/spatialOverlay for shared 3D space; scaledToFit3D() for models.

Read the full file on GitHub · 161 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. yesterday First seen · 161 lines · 90 tokens per session scan A 17631b1cbb68

Subscribe to this mod's changes

spatial-design is a skill published in the GitHub repository rshankras/claude-code-apple-skills (864 stars, last pushed 2d ago), licensed MIT. It adds 90 tokens to every session and 2,277 once invoked, about $0.0004 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 2026-11-05.

Related

spatial-design compared with skills from other repositories

spatial-design next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
spatial-designrshankras/claude-code-apple-skillsSkill8642d agoMITA90Claude Code
apple-hig-uxDev869/swift-tothemaxSkill74mo agoMITA164Claude Code
app-icon-optimizationEronred/aso-skillsSkill2.2k1mo agoMITA103Claude Code
apple-higjustinwetch/HIGAgentSkillsSkill80420d agoMITA158Claude Code, Codex
flame-harness-admobtjdrhs90/flutter-flame-harnessSkill6110d agoMITA41Claude Code
flame-harness-submittjdrhs90/flutter-flame-harnessSkill6110d agoMITA38Claude Code
flame-harness-designtjdrhs90/flutter-flame-harnessSkill6110d agoMITA38Claude Code