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/OkminLee/everything-claude-code-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/okminlee/everything-claude-code-ios/everything-claude-code-ios)<a href="https://agentmods.dev/plugins/okminlee/everything-claude-code-ios/everything-claude-code-ios"><img src="https://agentmods.dev/badge/plugins/okminlee/everything-claude-code-ios/everything-claude-code-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/okminlee/everything-claude-code-ios/everything-claude-code-ios"><img src="https://agentmods.dev/badge/plugins/okminlee/everything-claude-code-ios/everything-claude-code-ios.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
everything-claude-code-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 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": "everything-claude-code-ios",
"version": "1.2.0",
"description": "Comprehensive Claude Code configurations for iOS/Swift development with profile-based installation, Node.js hook infrastructure, session persistence, and continuous learning. Includes Xcode 26 system prompt insights, Liquid Glass, FoundationModels, and Swift 6.2 concurrency patterns.",
"author": {
"name": "okminlee",
"url": "https://github.com/OkminLee"
},
"homepage": "https://github.com/OkminLee/everything-claude-code-ios",
"repository": "https://github.com/OkminLee/everything-claude-code-ios",
"license": "MIT",
"keywords": [
"ios",
"swift",
"swiftui",
"xcode",
"clean-architecture",
"tca",
"tdd",
"xcuitest",
"code-review",
"security",
"liquid-glass",
"foundation-models",
"swift-testing",
"swift-concurrency",
"xcode-26",
"ios-26"
]
}
What it installs
The manifest is a name and a version. 5 skills, 10 commands, 9 agents, 5 hooks, 4 MCP servers travel with it, and installing the plugin installs all of them — 776 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill ios-security-review A 38 tokens
- Skill continuous-learning-v2 A 26 tokens
- Skill verification-loop A 29 tokens
- Skill strategic-compact A 28 tokens
- Skill swift-tdd-workflow B 43 tokens
- Command swift-tdd A 33 tokens
- Command xcuitest A 32 tokens
- Command ios-coverage A 30 tokens
- Command swift-refactor A 31 tokens
- Command swift-review A 27 tokens
- Command xcode-build-fix A 23 tokens
- Command plan A 25 tokens
- Command learn A 0 tokens
- Command update-codemaps A 0 tokens
- Command update-docs C 0 tokens
- Agent xcuitest-runner A 54 tokens
- Agent ios-security-reviewer A 56 tokens
- Agent swift-refactor-cleaner A 49 tokens
- Agent swift-tdd-guide A 34 tokens
- Agent ios-architect A 35 tokens
- Agent swift-code-reviewer A 35 tokens
- Agent ios-planner A 42 tokens
- Agent ios-doc-updater B 53 tokens
- Agent xcode-build-resolver C 53 tokens
- Hook PostToolUse A not measured
- Hook PreToolUse A not measured
- Hook Stop A not measured
- Hook PreCompact A not measured
- Hook SessionStart A not measured
- MCP server github A not measured
- MCP server context7 A not measured
- MCP server memory A not measured
- MCP server sequential-thinking A not measured
What ships with it
1 file beside plugin.json 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.
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 · 31 lines scan A c640ea32a445
everything-claude-code-ios is a plugin published in the GitHub repository OkminLee/everything-claude-code-ios (58 stars, last pushed 6mo 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.