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 perniemann/pnCore --skill pn-spatial-ux-patternsgit clone --depth 1 https://github.com/perniemann/pnCoreWrote 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/perniemann/pncore/pn-spatial-ux-patterns)<a href="https://agentmods.dev/skills/perniemann/pncore/pn-spatial-ux-patterns"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-spatial-ux-patterns/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/perniemann/pncore/pn-spatial-ux-patterns"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-spatial-ux-patterns.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 | $0.00040 | $0.01028 |
| Opus 5 | $0.00020 | $0.00514 |
| Sonnet 5 | $0.00008 | $0.00206 |
| Haiku 4.5 | $0.00004 | $0.00103 |
Grade A, and why
pn-spatial-ux-patterns 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 6d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spatial UX patterns
When to use
- AR/VR/XR interface design.
- Spatial interaction patterns.
- 3D UI placement, depth, layout.
- Immersive UX for headsets and spatial displays.
Workflow
- Context: Platform (Quest 3, Vision Pro, HoloLens, browser WebXR), use case, user posture (seated, standing, walking).
- Architecture: UI placement, depth layers, interaction zones.
- Patterns: Apply the patterns documented below for menus, controls, and feedback in 3D space.
- Document: Specs for implementation.
Depth layers
Organize UI and world content into three depth zones:
| Zone | Distance | Use |
|---|---|---|
| Near | < 0.5 m | Direct manipulation, hand tracking menus, pinch targets |
| Mid | 0.5 – 2 m | Primary content panels, action buttons, gaze-and-commit controls |
| Far | > 2 m | Ambient information, world labels, navigation waypoints |
- Never place interactive elements closer than ~0.4 m — creates eye strain and missed tracking.
- Never use a far-zone element for a critical action; bring it to mid-zone when interaction is needed.
- Use depth cues (subtle shadow, scale-at-distance, opacity falloff) to reinforce layer hierarchy.
Ergonomic gaze angles
Keep interactive content within the comfortable gaze cone:
- Horizontal: ±35° from forward axis (Quest 3 / Vision Pro recommendation)
- Vertical: −20° (below horizon) to +10° (above horizon) — users rest gaze slightly below horizontal
- Avoid placing primary actions at extreme angles; use anchor points that follow the user's head rotation lazily (lag = 0.2–0.3 s) to keep content in zone without snapping.
Interaction zones and input models
| Zone | Distance | Primary input |
|---|---|---|
| Direct touch | < 0.5 m | Hand-tracking: pinch, poke, palm |
| Ray cast / point | 0.5 – 2 m | Gaze + commit, controller ray, vision OS eye + hand |
| Voice / ambient | > 2 m | Voice commands, passive awareness |
- For Quest 3 / Vision Pro: implement at minimum ray-cast + pinch. Hand tracking is the primary modality; controller as fallback.
- For WebXR (browser): use
XRSessionselectevent for primary action;selectstart/selectendfor hold. Support both controller (XRInputSource.targetRayMode = 'tracked-pointer') and gaze ('gaze'). - Provide visual feedback on hover/proximity (highlight, scale pulse) within 0.1 s of gaze entry — response latency above 150 ms feels broken in XR.
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.
- 6d ago First seen · 93 lines · 40 tokens per session scan A 9811d6f2ecdd
pn-spatial-ux-patterns is a skill published in the GitHub repository perniemann/pnCore (0 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 1,028 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
typescript
TypeScript coding conventions, best practices, and patterns for writing clean, maintainable code.
taiyi-diagram-arch
A workflow for turning written system or product architecture into readable, version-controlled diagrams using Mermaid or exported SVG and PNG files. Architecture diagrams show components, boundaries, data flows, and deployment relationships.
taiyi-restyle
A planning guide for breaking a large user-interface redesign into smaller, independently reviewable tasks. A user interface is the part of an application that people see and use.
taiyi-diagram-pipeline
A pipeline that creates and updates architecture diagrams in three stages: a C4 model from the code, an engineering architecture diagram, and an exported PNG image. C4 is a way to describe software architecture at several levels of detail.
taiyi-diagram-render
A tool for rendering existing C4 or architecture Mermaid diagrams as SVG or PNG images. C4 is a way to show software systems at different levels, while Mermaid is a text format for diagrams.
apply-mantel-styles
Provides guidelines for applying Mantel's brand styles to diagrams and frontend components. Use when asked to create visuals that need to align with Mantel's branding.