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 bcastelino/agent-skills-kit --skill vr-argit clone --depth 1 https://github.com/bcastelino/agent-skills-kitWrote 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/bcastelino/agent-skills-kit/vr-ar)<a href="https://agentmods.dev/skills/bcastelino/agent-skills-kit/vr-ar"><img src="https://agentmods.dev/badge/skills/bcastelino/agent-skills-kit/vr-ar/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/bcastelino/agent-skills-kit/vr-ar"><img src="https://agentmods.dev/badge/skills/bcastelino/agent-skills-kit/vr-ar.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 | $0.00016 | $0.00614 |
| Opus 5.5 | $0.00006 | $0.00246 |
| Sonnet 5.5 | $0.00003 | $0.00123 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
vr-ar 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.
This is a copy
88% identical to vr-ar — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VR/AR Development
Immersive experience principles.
1. Platform Selection
VR Platforms
| Platform | Use Case |
|---|---|
| Quest | Standalone, wireless |
| PCVR | High fidelity |
| PSVR | Console market |
| WebXR | Browser-based |
AR Platforms
| Platform | Use Case |
|---|---|
| ARKit | iOS devices |
| ARCore | Android devices |
| WebXR | Browser AR |
| HoloLens | Enterprise |
2. Comfort Principles
Motion Sickness Prevention
| Cause | Solution |
|---|---|
| Locomotion | Teleport, snap turn |
| Low FPS | Maintain 90 FPS |
| Camera shake | Avoid or minimize |
| Rapid acceleration | Gradual movement |
Comfort Settings
- Vignette during movement
- Snap vs smooth turning
- Seated vs standing modes
- Height calibration
3. Performance Requirements
Target Metrics
| Platform | FPS | Resolution |
|---|---|---|
| Quest 2 | 72-90 | 1832x1920 |
| Quest 3 | 90-120 | 2064x2208 |
| PCVR | 90 | 2160x2160+ |
| PSVR2 | 90-120 | 2000x2040 |
Frame Budget
- VR requires consistent frame times
- Single dropped frame = visible judder
- 90 FPS = 11.11ms budget
4. Interaction Principles
Controller Interaction
| Type | Use |
|---|---|
| Point + click | UI, distant objects |
| Grab | Manipulation |
| Gesture | Magic, special actions |
| Physical | Throwing, swinging |
Hand Tracking
- More immersive but less precise
- Good for: social, casual
- Challenging for: action, precision
5. Spatial Design
World Scale
- 1 unit = 1 meter (critical)
- Objects must feel right size
- Test with real measurements
Depth Cues
| Cue | Importance |
|---|---|
| Stereo | Primary depth |
| Motion parallax | Secondary |
| Shadows | Grounding |
| Occlusion | Layering |
6. Anti-Patterns
| ❌ Don't | ✅ Do |
|---|---|
| Move camera without player | Player controls camera |
| Drop below 90 FPS | Maintain frame rate |
| Use tiny UI text | Large, readable text |
| Ignore arm length | Scale to player reach |
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 · 123 lines · 16 tokens per session scan A 057007c86fb7
vr-ar is a skill published in the GitHub repository bcastelino/agent-skills-kit (2 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 614 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to vr-ar, differing in 3 lines, and is treated as a copy.
vr-ar compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vr-arbcastelino/agent-skills-kit | Skill | 2 | 3mo ago | MIT | A | 16 | Claude Code |
| researcherkeli-wen/agy-staff | Skill | 869 | 2d ago | MIT | A | 75 | Claude Code |
| reviewerkeli-wen/agy-staff | Skill | 869 | 2d ago | MIT | B | 94 | Claude Code |
| cloudflare-durable-objectssecondsky/claude-skills | Skill | 248 | 14d ago | MIT | A | 43 | Claude Code |
| dead-code-huntermagic5644/Graph-It-Live | Skill | 63 | yesterday | MIT | A | 165 | Claude Code |
| onboarding-expressmagic5644/Graph-It-Live | Skill | 63 | yesterday | MIT | A | 171 | Claude Code |
| debugging-workflowsCrowdStrike/foundry-skills | Skill | 39 | yesterday | MIT | A | 90 | Claude Code |