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.
git clone --depth 1 https://github.com/facebook/meta-wearables-dat-iosWrote 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/plugins/facebook/meta-wearables-dat-ios/mwdat-ios)<a href="https://agentmods.dev/plugins/facebook/meta-wearables-dat-ios/mwdat-ios"><img src="https://agentmods.dev/badge/plugins/facebook/meta-wearables-dat-ios/mwdat-ios/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/plugins/facebook/meta-wearables-dat-ios/mwdat-ios"><img src="https://agentmods.dev/badge/plugins/facebook/meta-wearables-dat-ios/mwdat-ios.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mwdat-ios 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 16d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What it installs
The manifest is a name and a version. 17 skills travel with it, and installing the plugin installs all of them — 359 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill display-access A 25 tokens
- Skill sample-app-guide A 15 tokens
- Skill camera-streaming A 16 tokens
- Skill getting-started A 23 tokens
- Skill mockdevice-testing A 13 tokens
- Skill dat-conventions A 22 tokens
- Skill debugging A 15 tokens
- Skill permissions-registration A 12 tokens
- Skill session-lifecycle A 14 tokens
- Skill dat-docs-mcp A 38 tokens
- Skill live-debugging-mcp A 54 tokens
- Skill camera-capture A 15 tokens
- Skill inputs A 19 tokens
- Skill motion A 22 tokens
- Skill voice-invocations A 22 tokens
- Skill audio-streaming A 16 tokens
- Skill speech A 18 tokens
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.
- 16d ago Changed 4f87c4d1c241
- 1mo ago Changed · +1 lines def66966117d
- 1mo ago First seen · 20 lines scan A 390ad83e0bd3
mwdat-ios is a plugin published in the GitHub repository facebook/meta-wearables-dat-ios (577 stars, last pushed today), with no licence file. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
android-skills
Android and KMP development skills for Claude Code — architecture, Compose, coroutines, flows, networking (Retrofit, Ktor), persistent storage (Room, DataStore), pagination, dependency injection (Hilt, Koin), testing, debugging, Gradle, and Material Design 3.
ios-developer
iOS and Swift development with SwiftUI views and models.
swift-engineer
Elite iOS and macOS development expertise with automatic skill activation for Swift, UIKit, AppKit, SwiftUI, Xcode, and Apple frameworks plus code formatting tools.
app-intents
Reviews and writes Swift App Intents code, exposing app actions and data to Siri, Shortcuts, Spotlight, and Apple Intelligence.
swift-performance-pro
Performance: Instruments, SwiftUI render cost, memory and retain cycles, launch time, lists.
widgets
Reviews and writes Swift WidgetKit code: timeline providers, configurations, families, accented/tinted rendering, interactive widgets, Controls, Live Activities, Smart Stack relevance, push-updated widgets, data loading, deep links, animations, and SiriKit/ClockKit migration.