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.
npx skills add rouzbeh-abadi/Swift-Agent-Skill --skill swift-expert-skillgit clone --depth 1 https://github.com/rouzbeh-abadi/Swift-Agent-SkillWrote 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/skills/rouzbeh-abadi/swift-agent-skill/swift-expert-skill)<a href="https://agentmods.dev/skills/rouzbeh-abadi/swift-agent-skill/swift-expert-skill"><img src="https://agentmods.dev/badge/skills/rouzbeh-abadi/swift-agent-skill/swift-expert-skill/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/skills/rouzbeh-abadi/swift-agent-skill/swift-expert-skill"><img src="https://agentmods.dev/badge/skills/rouzbeh-abadi/swift-agent-skill/swift-expert-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00061 | $0.01858 |
| Opus 5 | $0.00030 | $0.00929 |
| Sonnet 5 | $0.00012 | $0.00372 |
| Haiku 4.5 | $0.00006 | $0.00186 |
Grade A, and why
swift-expert-skill 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Swift Expert Skill
Overview
Use this skill to write, review, or improve Swift code across language design, concurrency, package management, testing, lightweight SwiftUI ViewModel and view-structure guidance, and style guidance. SwiftLint support is part of the skill, not the whole skill.
Workflow Decision Tree
1) Review existing Swift code
- Start with
references/swift-language-patterns.mdfor optionals, errors, naming, and API shape - Review task and actor usage against
references/swift-concurrency-guide.md - Check package layout and manifest choices with
references/swift-package-manager-guide.md - Review tests using
references/swift-testing-guide.md - For SwiftUI screens, review state ownership and ViewModel usage with
references/swiftui-viewmodel-guide.md - For SwiftUI view composition, review body structure and extraction choices with
references/swiftui-view-structure-guide.md - Use
references/swift-style-and-lint-guide.mdfor formatting, linting, and safe mechanical cleanup - Flag unsafe patterns such as force unwraps, force casts, detached tasks without justification, and weak error handling
- Suggest local improvements first before proposing broad redesigns
2) Improve existing Swift code
- Apply low-risk lint and readability fixes first
- Simplify optional handling and error propagation when behavior stays the same
- Tighten concurrency boundaries:
@MainActor, task ownership, cancellation, and isolation - Improve package manifests and target boundaries when structure is unclear or brittle
- Strengthen tests around touched behavior
- In SwiftUI code, keep presentational views simple and only introduce ViewModels when state or logic justifies them
- Keep SwiftUI
bodyimplementations readable by extracting sections into small helpers or separate subviews when needed - Keep edits local unless the user explicitly wants a broader refactor
3) Implement new Swift code
- Start from clear APIs and obvious ownership
- Prefer safe optionals, explicit error handling, and focused types
- Use structured concurrency rather than ad hoc background work
- Keep package boundaries and dependencies intentional
- Add tests where the new behavior has meaningful logic
- For SwiftUI, choose between local state and a ViewModel based on responsibility, not by default
- Build SwiftUI screens from named sections rather than letting one large
bodyabsorb every view - Use the style guide for final cleanup
What ships with it
8 files beside SKILL.md 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.
- assets/swiftlint.yml 483 B
- references/swift-concurrency-guide.md 1.5 KB
- references/swift-language-patterns.md 4.4 KB
- references/swift-package-manager-guide.md 1.2 KB
- references/swift-style-and-lint-guide.md 5.8 KB
- references/swift-testing-guide.md 2.1 KB
- references/swiftui-view-structure-guide.md 4.7 KB
- references/swiftui-viewmodel-guide.md 2.5 KB
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.
- 10d ago First seen · 174 lines · 61 tokens per session scan A ae7720c87b5f
swift-expert-skill is a skill published in the GitHub repository rouzbeh-abadi/Swift-Agent-Skill (5 stars, last pushed 5mo ago), licensed MIT. It adds 61 tokens to every session and 1,858 once invoked, about $0.0003 per session on Opus 5. 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 2026-08-31.
Other skills, from other repositories
wear-compose-m3
Expert guidance for working with Wear OS Compose Material3. Use this skill when creating, updating, or migrating Wear OS projects. This includes the androidx.wear.compose.material3, androidx.wear.compose.foundation, and androidx.wear.compose.navigation3 libraries. Also working with core components such as AppScaffold…
kotlin-specialist
Provides idiomatic Kotlin implementation patterns including coroutine concurrency, Flow stream handling, multiplatform architecture, Compose UI construction, Ktor server setup, and type-safe DSL design. Use when building Kotlin applications requiring coroutines, multiplatform development, or Android with Compose.…
build-android-binary
Compile a PAM control's Android Kotlin module into the runtime-loadable DEX for a .ppmplugin. Creates a staged Gradle build with the pinned wrapper and react-android compile dependency, verifies manifest/module/package alignment and runtime-loading constraints, builds the release AAR, then runs d8 --min-api 24. Writes…
swiftui-dev
Use this skill for SwiftUI development, architecture, structure, performance, and Apple native app profiling. It combines.
android-navigation-3
Install and migrate to Jetpack Navigation 3. Use when implementing Navigation 3 patterns including NavDisplay, NavKey routes, deep links, multiple backstacks, scenes (dialogs, bottom sheets), or migrating from Navigation 2.
mobiai-kmp
Use when working on a Kotlin Multiplatform project — shared code, expect/actual declarations, platform-specific implementations, building and testing.