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/mintuz/skillsWrote 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/mintuz/skills/app)<a href="https://agentmods.dev/plugins/mintuz/skills/app"><img src="https://agentmods.dev/badge/plugins/mintuz/skills/app/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/mintuz/skills/app"><img src="https://agentmods.dev/badge/plugins/mintuz/skills/app.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
app 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.
What it actually says
{
"name": "app",
"version": "1.8.1",
"description": "Agents and skills for Swift app development on iOS.",
"author": {
"name": "Adam Bulmer",
"email": "[email protected]",
"url": "https://github.com/mintuz"
},
"repository": "https://github.com/mintuz/claude-plugins",
"license": "MIT",
"keywords": ["swift", "ios", "architecture", "microapps", "spm"]
}
What it installs
The manifest is a name and a version. 10 skills, 2 MCP servers travel with it, and installing the plugin installs all of them — 660 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill app-intent-driven-development A 59 tokens
- Skill app-store-scraper A 47 tokens
- Skill local-ai-models A 97 tokens
- Skill xcode-dev-loop A 58 tokens
- Skill swift-testing A 66 tokens
- Skill ios-localize-copy A 82 tokens
- Skill app-store-keyword-ops A 53 tokens
- Skill asc-screenshots A 64 tokens
- Skill debug A 80 tokens
- Skill swiftui-architecture A 54 tokens
- MCP server XcodeBuildMCP A not measured
- MCP server ios-simulator 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.
- 1mo ago Changed 2a44506f3782
- 1mo ago First seen · 14 lines scan A 61b90d2e27a1
app is a plugin published in the GitHub repository mintuz/skills (29 stars, last pushed 2d ago), 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 2026-08-30.
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.
app-intents
Reviews and writes Swift App Intents code, exposing app actions and data to Siri, Shortcuts, Spotlight, and Apple Intelligence.
mwdat-ios
Git-native DAT SDK guidance for ios development, covering setup, camera streaming, display access, MockDeviceKit, session lifecycle, permissions, debugging, and sample app patterns.
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.