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 meta-quest/agentic-tools --skill hz-iwsdk-webxrgit clone --depth 1 https://github.com/meta-quest/agentic-toolsWrote 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/meta-quest/agentic-tools/hz-iwsdk-webxr)<a href="https://agentmods.dev/skills/meta-quest/agentic-tools/hz-iwsdk-webxr"><img src="https://agentmods.dev/badge/skills/meta-quest/agentic-tools/hz-iwsdk-webxr/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/meta-quest/agentic-tools/hz-iwsdk-webxr"><img src="https://agentmods.dev/badge/skills/meta-quest/agentic-tools/hz-iwsdk-webxr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.02833 |
| Opus 5.5 | $0.00021 | $0.01133 |
| Sonnet 5.5 | $0.00011 | $0.00567 |
| Haiku 4.5 | $0.00005 | $0.00283 |
Grade A, and why
hz-iwsdk-webxr 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 1mo 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IWSDK WebXR Skill
Build immersive WebXR experiences for Meta VR using Meta's Immersive Web SDK (IWSDK). This skill covers the current package layout, ECS architecture, Three.js integration, spatial UI development, XR input handling, and the recommended Vite-based development loop.
When to Use This Skill
Use this skill when you need to:
- Build a WebXR experience targeting Meta VR using IWSDK
- Create 3D scenes using the ECS architecture on top of Three.js
- Design spatial UI panels with UIKitML and
PanelUI - Handle XR input from controllers, hands, and world-space pointers
- Run a closed-loop edit, reload, observe, and fix workflow for IWSDK apps
- Optimize WebXR performance for Meta VR hardware
- Debug and test WebXR applications with IWSDK's Vite dev tooling and Quest Browser
This skill applies to Meta VR Glasses with gaze-pinch input, and to all Meta Quest headsets with Quest Browser.
What Is IWSDK
The Immersive Web SDK (IWSDK) is Meta's framework for building WebXR experiences. It provides:
- Entity Component System (ECS): a data-oriented architecture built on typed component storage and query-driven systems
- Three.js integration: IWSDK manages the renderer, scene, camera, and XR session lifecycle so app code can focus on content
- Spatial UI toolkit: UIKitML plus
PanelUI,PanelDocument, andUIKitDocumentfor in-world and screen-space UI - XR input management: unified handling of controllers, hand tracking, pointers, and grabbing
- Locomotion and interaction systems: opt-in grabbing, teleport, slide, and turning features
- Asset management: manifest-based preloading and keyed access through
AssetManager
IWSDK runs in the browser via the WebXR Device API. Applications are standard web pages that are usually served by Vite during development and opened in Quest Browser for on-device validation.
Current Packaging And Tooling
These details are important because older pre-release guidance is now wrong:
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +4 lines f7caa6ed0751
- 2mo ago First seen · 269 lines · 53 tokens per session scan A 884ad561acc8
hz-iwsdk-webxr is a skill published in the GitHub repository meta-quest/agentic-tools (242 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 53 tokens to every session and 2,833 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
defuddle
Extract clean Markdown from HTML pages with Defuddle CLI.
yao-geo-baidu-keywords
A browser-based Baidu keyword research workflow that collects search suggestions and “related searches,” captures screenshots as evidence, scores commercial value, and exports an Excel workbook.
yao-geo-xiaohongshu
A browser-based collector for related search suggestions from Xiaohongshu, a Chinese social content platform. It expands supplied seed terms through two levels, records screenshots and source paths, scores commercial intent, and exports an Excel workbook.
yao-geo-douyin
A browser-based collector for related search suggestions from Douyin, a Chinese short-video platform. It expands seed terms through two levels, records screenshots and search paths, scores commercial intent, and exports an Excel workbook.
yao-chatgpt-crawler
Use when a user provides ChatGPT web AI-search keywords, repeat count, target entity, entity type, OpenCLI profile, and crawl interval preference, then needs repeated crawls aggregated into JSON plus a Kami HTML GEO report. Not for generic crawling, ChatGPT API chat, SEO writing, or one-off answers.
yao-doubao-crawler
Use when a user needs repeated Doubao AI-search collection from web or Android Appium into compatible JSON plus Markdown/Excel/HTML GEO reports. Requires keywords/questions and repeat count; target entity/type are required only for target-vs-competitor diagnosis. Not for generic scraping, Doubao API chat, hidden API…