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 skills/tomkrikorian/visionosagents/visionos-widgetkit-developernpx skills add tomkrikorian/visionOSAgents --skill visionos-widgetkit-developergit clone --depth 1 https://github.com/tomkrikorian/visionOSAgentsWrote 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/tomkrikorian/visionosagents/visionos-widgetkit-developer)<a href="https://agentmods.dev/skills/tomkrikorian/visionosagents/visionos-widgetkit-developer"><img src="https://agentmods.dev/badge/skills/tomkrikorian/visionosagents/visionos-widgetkit-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 5.1 | $0.00080 | $0.00769 |
| Opus 5 | $0.00040 | $0.00385 |
| Sonnet 5 | $0.00016 | $0.00154 |
| Haiku 4.5 | $0.00008 | $0.00077 |
Grade A, and why
visionos-widgetkit-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 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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
visionOS WidgetKit Developer
Quick Start
Treat visionOS widgets as spatial objects first, not as small 2D surfaces.
- Decide the platform and family scope first.
- Define both close and far layouts before polishing visuals.
- Treat timeline entries, shared storage, and App Intents as the integration boundary; do not depend on live host-app state.
- Load only the reference files that match the current problem.
Load References When
| Reference | When to Use |
|---|---|
widget-overview.md |
Overview, decision points, and a quick checklist for Vision Pro widgets. |
families-and-platforms.md |
When choosing native visionOS families, compatible iOS families, or extra-large widget support. |
mounting-styles.md |
When deciding elevated vs recessed support and avoiding layout breakage. |
visionos-rendering-styles.md |
When checking official visionOS widget rendering modes, backgrounds, families, textures, and routing to shared button-shape policy. |
textures-and-rendering.md |
When choosing glass vs paper, and ensuring legibility in different render modes. |
proximity-levelofdetail.md |
When implementing near/far layouts using LevelOfDetail. |
interactive-widgets.md |
When adding Button, Toggle, or AppIntent-driven interactions to a widget. |
debugging-and-updates.md |
When widgets don’t refresh, don’t appear, or appear stale or broken. |
widget-animation.md |
When animating widget content using timeline entries and Canvas crossfade, tuning frame rate, or hitting bundle or computation budget limits. |
Workflow
- Confirm the widget platform and family set.
- Choose mounting style, texture, and near/far layout strategy.
- Decide the data path: timeline-only, App Group/shared storage, background URL session, or WidgetKit push notification.
- Add interaction only if the widget still stays glanceable.
- Verify timelines, reloads, rendering modes, and extension logs after the structure is set.
What ships with it
12 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.
- agents/openai.yaml 395 B
- assets/studio-meije-logo-small.png 4.2 KB
- assets/studio-meije-logo.png 42 KB
- references/debugging-and-updates.md 2.1 KB
- references/families-and-platforms.md 1.2 KB
- references/interactive-widgets.md 2.0 KB
- references/mounting-styles.md 1.0 KB
- references/proximity-levelofdetail.md 1.3 KB
- references/textures-and-rendering.md 2.4 KB
- references/visionos-rendering-styles.md 1.7 KB
- references/widget-animation.md 11 KB
- references/widget-overview.md 2.5 KB
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.
- 6d ago First seen · 62 lines · 80 tokens per session scan A 491d1c686271
visionos-widgetkit-developer is a skill published in the GitHub repository tomkrikorian/visionOSAgents (60 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 769 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
developer-device-platform-basics
Provides guidance and instructions on managing remote devices on Developer Device Platform (DDP). Use when reserving remote Android devices, establishing connection tunnels, checking session status, or extending/cancelling leases. Don't use for iOS or local device/hardware inquiries.
camerax
Provide technical guidance for Android camera development with CameraX. Use when implementing camera features, handling asynchronous recording lifecycles, wiring low-level hardware interop using CameraX, or integrating ML Kit or Media3 effects.
serve-sim-placeholder-assets
Audit and update serve-sim's Device Hub-style simulator placeholder assets from local Xcode/CoreTypes resources. Use after installing a new Xcode or macOS seed, or when iPhone, iPad, Watch, or Vision placeholder previews look wrong.
mobile-platform-native-capabilities-integrate
Build a Salesforce LWC that uses native mobile device capabilities — barcode scanner, biometrics, location, NFC, calendar, contacts, document scanner, geofencing, AR space capture, app review, and payments. Use this skill when the user asks for an LWC that scans a barcode, captures a photo of a document, reads…
audio-skill
Control Android audio - get/set volume, mute/unmute for media, ringtone, notification, and call volumes.
wifi-skill
Control Android WiFi - enable, disable, get status, scan for networks, and get current connection info.