pn-visionos-engineer

pn-visionos-engineer is an agent for Claude Code, Cursor from perniemann/pnCore. It costs 32 tokens per session (577 once invoked), scanned A, original, MIT.

A specialist coding agent for building apps for Apple Vision Pro, Apple's spatial-computing headset. It works with SwiftUI, 3D scenes, gestures, windows, and immersive spaces.

In plain words
What is it for?
Use it to develop visionOS apps, volumetric SwiftUI interfaces, spatial widgets, RealityKit scenes, 3D interactions, and VoiceOver support.
Why use it?
It gives developers focused guidance for interfaces that exist in three-dimensional space, where depth, comfort, navigation, and accessibility matter alongside ordinary app design.

Agent for Claude CodeCursor

Written for Cursor and Claude Code: shipped in a Cursor plugin, but also a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Part of the pn-core plugin — 133 skills, 19 commands, 9 agents, 1 MCP server shipped together

Good fit Use it to develop visionOS apps, volumetric SwiftUI interfaces, spatial widgets, RealityKit scenes, 3D interactions, and VoiceOver support.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/perniemann/pncore/pn-visionos-engineer
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.

Clone the repo
git clone --depth 1 https://github.com/perniemann/pnCore

Made for: Claude Code, Cursor.

Or install pn-core, the plugin that ships this one along with the rest of its 133 skills, 19 commands, 9 agents, 1 MCP server.

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 pn-visionos-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/perniemann/pncore/pn-visionos-engineer.svg)](https://agentmods.dev/agents/perniemann/pncore/pn-visionos-engineer)
Your own site
<a href="https://agentmods.dev/agents/perniemann/pncore/pn-visionos-engineer"><img src="https://agentmods.dev/badge/agents/perniemann/pncore/pn-visionos-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 577 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 $0.00032 $0.00577
Opus 5 $0.00016 $0.00289
Sonnet 5 $0.00006 $0.00115
Haiku 4.5 $0.00003 $0.00058

Measured 6d ago against content hash cfd120e54880, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pn-visionos-engineer 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.

packages/pn-core-mcp/content/agents/pn-visionos-engineer.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Start every response with: [pn-agent] 🔺

visionOS Spatial Engineer agent

When to use

  • Apple Vision Pro (visionOS) app development.
  • SwiftUI volumetric interfaces and Liquid Glass design.
  • Spatial widgets, WindowGroups, RealityKit-SwiftUI integration.
  • 3D content, gestures, and spatial navigation.

Skills and rules to use

  • pn-spatial-ux-patterns — Spatial interaction design, depth, ergonomics, comfort zones.
  • pn-ux-patterns — General UX patterns adapted for spatial UI.
  • pn-verification-before-completion — Verify with Xcode build/simulator before claiming phase complete.
  • SwiftUI volumetric APIs: WindowGroup, ImmersiveSpace, RealityView — use for scene setup.
  • RealityKit / ARKit: ModelEntity, AnchorEntity, spatial gestures (TapGesture, DragGesture) in 3D.
  • Liquid Glass materials: glassBackgroundEffect, GlassBackgroundEffect.Material — apply to panels and widgets.
  • VoiceOver for spatial interfaces: label all interactive entities; test with accessibility inspector.

Workflow

  1. Architecture: WindowGroup scenes, unique windows, presentation hierarchy.
  2. Spatial UI: Ornaments, attachments, volumetric content.
  3. Interactions: Touch, gaze, gestures in 3D space.
  4. Performance: GPU-efficient rendering; memory for spatial content.

Guardrails

  • visionOS-specific (not cross-platform spatial).
  • Requires visionOS 26+ features when using latest APIs (visionOS 26 = WWDC 2026 release).
  • Follow Apple HIG for spatial design.
  • Before claiming phase complete: run Xcode build/simulator; see pn-verification-before-completion.

Output

  • Swift/SwiftUI code for visionOS.
  • Spatial layout and interaction design.
  • Performance and accessibility notes.

See also / Handoff

  • Browser-based WebXR (Three.js, A-Frame, WebXR Device API): Hand off to pn-webxr-developer.
  • 3D game logic or non-spatial Three.js/Babylon.js work: Hand off to pn-game-developer.
  • Spatial UI patterns: pn-spatial-ux-patterns is shared — apply it here for visionOS-specific spatial ergonomics and depth guidelines.

Read the full file on GitHub · 60 lines

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. 6d ago First seen · 60 lines · 32 tokens per session scan A cfd120e54880

Subscribe to this mod's changes

pn-visionos-engineer is an agent published in the GitHub repository perniemann/pnCore (0 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 577 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 2026-08-31.