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/johnrogers/claude-swift-engineeringWrote 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/johnrogers/claude-swift-engineering/swift-engineering)<a href="https://agentmods.dev/plugins/johnrogers/claude-swift-engineering/swift-engineering"><img src="https://agentmods.dev/badge/plugins/johnrogers/claude-swift-engineering/swift-engineering/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/johnrogers/claude-swift-engineering/swift-engineering"><img src="https://agentmods.dev/badge/plugins/johnrogers/claude-swift-engineering/swift-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
swift-engineering 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": "swift-engineering",
"version": "0.1.31",
"description": "Modern Swift/SwiftUI development toolkit with TCA support. Provides agents for planning, implementing, testing, documenting, and building Swift features.",
"keywords": [
"swift",
"swiftui",
"ios",
"macos",
"tca",
"composable-architecture",
"mobile",
"apple"
]
}
What it installs
The manifest is a name and a version. 17 skills, 3 commands, 11 agents travel with it, and installing the plugin installs all of them — 1,182 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill swift-testing A 13 tokens
- Skill storekit A 46 tokens
- Skill localization A 44 tokens
- Skill modern-swift A 41 tokens
- Skill swiftui-patterns A 61 tokens
- Skill composable-architecture A 55 tokens
- Skill foundation-models A 42 tokens
- Skill haptics A 47 tokens
- Skill ios-26-platform A 49 tokens
- Skill sqlite-data A 39 tokens
- Skill swiftui-advanced A 60 tokens
- Skill grdb A 53 tokens
- Skill ios-hig A 49 tokens
- Skill swift-diagnostics A 58 tokens
- Skill swift-networking A 56 tokens
- Skill generating-swift-package-docs A 46 tokens
- Skill swift-style B 32 tokens
- Command reflect A 0 tokens
- Command snapshot A 0 tokens
- Command restore-snapshot A 0 tokens
- Agent swift-search A 82 tokens
- Agent swiftui-specialist A 24 tokens
- Agent tca-engineer A 37 tokens
- Agent swift-documenter A 31 tokens
- Agent swift-engineer A 31 tokens
- Agent swift-test-creator A 21 tokens
- Agent swift-architect A 34 tokens
- Agent tca-architect A 39 tokens
- Agent swift-code-reviewer A 29 tokens
- Agent swift-ui-design A 33 tokens
- Agent swift-modernizer A 30 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.
- 1mo ago First seen · 16 lines scan A ff6033994946
swift-engineering is a plugin published in the GitHub repository johnrogers/claude-swift-engineering (231 stars, last pushed 9mo 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-engineer
Elite iOS and macOS development expertise with automatic skill activation for Swift, UIKit, AppKit, SwiftUI, Xcode, and Apple frameworks plus code formatting tools.
swift-performance-pro
Performance: Instruments, SwiftUI render cost, memory and retain cycles, launch time, lists.