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/The-Artificer-of-Ciphers-LLC/skills-from-the-artificerWrote 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/the-artificer-of-ciphers-llc/skills-from-the-artificer/swift-agents)<a href="https://agentmods.dev/plugins/the-artificer-of-ciphers-llc/skills-from-the-artificer/swift-agents"><img src="https://agentmods.dev/badge/plugins/the-artificer-of-ciphers-llc/skills-from-the-artificer/swift-agents/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/the-artificer-of-ciphers-llc/skills-from-the-artificer/swift-agents"><img src="https://agentmods.dev/badge/plugins/the-artificer-of-ciphers-llc/skills-from-the-artificer/swift-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
swift-agents 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 today.
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.
What it actually says
{
"name": "swift-agents",
"description": "16 specialized Swift agents for Claude Code and VS Code Copilot. Covers concurrency, SwiftUI, Core ML, Foundation Models, MLX Swift, on-device AI, accessibility, security, testing, App Store review, Meta glasses SDK, SwiftData, visionOS, StoreKit 2, and performance.",
"version": "2.0.0",
"author": {
"name": "Taylor Arndt",
"url": "https://github.com/taylorarndt"
},
"repository": "https://github.com/The-Artificer-of-Ciphers-LLC/swift-agents",
"homepage": "https://github.com/The-Artificer-of-Ciphers-LLC/swift-agents",
"keywords": [
"swift",
"ios",
"macos",
"visionos",
"swiftui",
"swiftdata",
"storekit",
"concurrency",
"coreml",
"mlx",
"realitykit",
"performance",
"accessibility",
"security",
"testing",
"app-store"
],
"components": {
"agents": "agents/",
"hooks": "hooks/",
"settings": "settings.json"
}
}
What it installs
The manifest is a name and a version. 16 agents, 3 hooks travel with it, and installing the plugin installs all of them — 823 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Agent app-review-guardian A 42 tokens
- Agent coreml-specialist A 60 tokens
- Agent foundation-models-specialist A 55 tokens
- Agent mlx-specialist A 84 tokens
- Agent testing-specialist A 44 tokens
- Agent visionos-specialist A 55 tokens
- Agent meta-glasses-sdk-specialist A 68 tokens
- Agent mobile-a11y-specialist A 50 tokens
- Agent on-device-ai-architect A 62 tokens
- Agent performance-specialist A 45 tokens
- Agent storekit-specialist A 47 tokens
- Agent swiftdata-specialist A 56 tokens
- Agent swift-lead A 25 tokens
- Agent swift-security-specialist A 45 tokens
- Agent concurrency-specialist A 38 tokens
- Agent swiftui-specialist A 47 tokens
- Hook UserPromptSubmit A not measured
- Hook PostToolUse A not measured
- Hook SubagentStop A not measured
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.
- today First seen · 35 lines scan A 26e4c92856f4
swift-agents is a plugin published in the GitHub repository The-Artificer-of-Ciphers-LLC/skills-from-the-artificer (6 stars, last pushed yesterday), licensed MIT. 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 2026-10-15.
Other plugins, from other repositories
android-skills
Android skills are Google's official dedicated repository of AI-optimized, modular instructions and resources, to help LLMs better understand and execute specific patterns that follow the best practices and guidance on Android development. Android skills follow the open-standard agent skills - markdown files…
android-developer
Android and Kotlin development with Jetpack Compose.
ios-developer
iOS and Swift development with SwiftUI views and models.
agent-skills-android
Production-grade Android engineering skills for AI coding agents. Covers the full development lifecycle from spec to Play Store: Kotlin, Jetpack Compose, Gradle, Android SDK, and the Android ecosystem.
android-dev-skills
Android, Kotlin, Java, Gradle, testing, and release workflows.
swift-tothemax
Swift and Apple development to the max — skills covering the Swift language (6.x), SwiftUI, UX/HIG, App Store review, Apple legal/privacy compliance, and release operations.