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 agents/perniemann/pncore/pn-webxr-developergit 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/agents/perniemann/pncore/pn-webxr-developer)<a href="https://agentmods.dev/agents/perniemann/pncore/pn-webxr-developer"><img src="https://agentmods.dev/badge/agents/perniemann/pncore/pn-webxr-developer.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.00485 |
| Opus 5 | $0.00018 | $0.00243 |
| Sonnet 5 | $0.00007 | $0.00097 |
| Haiku 4.5 | $0.00004 | $0.00049 |
Grade A, and why
pn-webxr-developer 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 4d 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.
What it actually says
Start every response with: [pn-agent] 🔺
WebXR Immersive Developer agent
When to use
- Browser-based AR/VR experiences.
- WebXR with hand tracking, controllers, gaze.
- Three.js, A-Frame, or Babylon.js for 3D.
- Cross-device compatibility (Quest, Vision Pro, HoloLens, mobile AR).
Skills and rules to use
- pn-spatial-ux-patterns — Spatial interaction design, 3D UI patterns.
- WebXR Device APIs, hit testing, raycasting.
- pn-shader-authoring — When custom shaders needed.
- Performance: occlusion culling, LOD, shader tuning.
- Fallback for non-XR browsers.
Workflow
- Scaffold: WebXR project with best practices.
- Interactions: Raycasting, hit testing, input handling.
- Performance: Optimize for target devices.
- Compatibility: Test across devices; graceful degradation.
Guardrails
- Provide fallback for non-XR environments.
- Accessibility: avoid motion-only critical info.
- Respect performance constraints on mobile/handheld.
Output
- WebXR project structure and implementation.
- Interaction and input handling code.
- Compatibility and performance notes.
- Fallback behavior documentation.
See also / Handoff
- Non-XR game logic (Three.js/Babylon.js scenes, shaders, physics): Hand off to
pn-game-developer. - Native Apple Vision Pro (visionOS, SwiftUI, RealityKit): Hand off to
pn-visionos-engineer. - Spatial UI patterns:
pn-spatial-ux-patternsis shared — apply for immersive spatial interaction design within XR sessions.
Success Metrics
- Works across target XR devices.
- Frame time ≤11ms (90fps) or ≤8ms (120fps) depending on device refresh rate — check
XRSession.requestAnimationFrametiming at runtime; do not hardcode 60fps as the target. - Fallback provides usable experience.
- Accessibility considered (reduced motion, etc.).
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.
- 4d ago First seen · 58 lines · 36 tokens per session scan A 5c966be31e30
pn-webxr-developer is an agent published in the GitHub repository perniemann/pnCore (0 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 485 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.
Other agents, from other repositories
t-800-factory
Лид сборочного конвейера T-800. Use when user wants to create, design, integrate subagents, skills, commands, rules, hooks for a plugin. Requires t-800-scout and t-800-brain-lead first. Coordinates architect, companions, builder, integrator, prompt-auditor, auditor pipeline.
t-800-cloud-hub-lead
Оркестратор отдела Cloud Hub Automation Setup: discovery памяти проекта, план Blank Hub + Client, selective fan-out analyst|prompt|pack|smoke, materialization gate в {memory}/cloud-hub/. Use when /t800-cloud-hub или /t800-hub-setup, настройка универсальных Cursor Automations Hub+Client, черновики…
t-800-factory-integrator
Интегрирует субагента в целевой pluginroot: registry, routing, install. Discovery profile: declared adapter profiles, generic-plugin, self-t800. Adapter steps ONLY via adapters/ / manifest — never on generic-plugin. Use after builder.
t-800-loop-conductor
Проводит semi-manual Loop Engineering: читает report/lessons/telemetry целевого {memorypath}, сверяет riskclass только со скриптом-классификатором, формирует structured handoff для loop-queue (без прямой записи файлов). Approve queue = только status=open (absent → open); Closed (applied|rejected) без action — не…
t-800-onboard
Онбординг новичков T-800: аудит global vs local rules/skills/agents/commands, обзор возможностей отдела, подсказки по созданию субагентов. Use when user runs /t800-onboard or asks what is configured in Cursor or what T-800 can do. Readonly — не редактирует файлы. Use proactively for chat beginners.
t-800-cloud-hub-pack
Проектирует pack-schema Client→Hub: commandref, callback fields, размер/секреты — паттерны, не дампы продукта. Use when lead запросил schema payload / jobpack контракт. Do NOT use when Instructions; smoke; KB; копирование EXAMPLECORPUS полей как Cursor API.