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 hoangatg/ai-agent-toolkit --skill vr-argit clone --depth 1 https://github.com/hoangatg/ai-agent-toolkitWrote 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/hoangatg/ai-agent-toolkit/vr-ar)<a href="https://agentmods.dev/skills/hoangatg/ai-agent-toolkit/vr-ar"><img src="https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/vr-ar.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 5.1 | $0.00016 | $0.00627 |
| Opus 5 | $0.00008 | $0.00313 |
| Sonnet 5 | $0.00003 | $0.00125 |
| Haiku 4.5 | $0.00002 | $0.00063 |
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 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.
This is a copy
100% identical to vr-ar — 0 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 — 124 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.
- 4d ago First seen · 124 lines · 16 tokens per session scan A 59ddbdecc4fa
vr-ar is a skill published in the GitHub repository hoangatg/ai-agent-toolkit (1 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 627 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to vr-ar, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
opencode
Delegate coding tasks to the OpenCode CLI for feature work, refactoring, PR review, and autonomous-style runs. Requires opencode installed where the agent can execute shell commands.
codex
Delegate coding tasks to the OpenAI Codex CLI for features, refactoring, PR reviews, and batch fixes. Requires the codex CLI and typically a git repository.
deepnote
DeepNote knowledge base: persistent interlinked markdown wiki with ingest, query, lint, link graph and history.
golang-patterns
Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications.
clickhouse-io
ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.
springboot-patterns
Spring Boot architecture patterns, REST API design, layered services, data access, caching, async processing, and logging. Use for Java Spring Boot backend work.