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 agentmods add skills/notque/vexjoy-agent/swiftnpx skills add notque/vexjoy-agent --skill swiftgit clone --depth 1 https://github.com/notque/vexjoy-agentWrote 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/notque/vexjoy-agent/swift)<a href="https://agentmods.dev/skills/notque/vexjoy-agent/swift"><img src="https://agentmods.dev/badge/skills/notque/vexjoy-agent/swift.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.00921 |
| Opus 5 | $0.00011 | $0.00461 |
| Sonnet 5 | $0.00004 | $0.00184 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
swift 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 2d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Swift Skill
Swift concurrency and testing: async/await, Actors, TaskGroups, Sendable, structured concurrency, XCTest, Swift Testing framework, and async test patterns.
Reference Loading Table
| Signal | Reference | Size |
|---|---|---|
| async/await, Task, Sendable | references/fundamentals.md |
~20 lines |
| Actor, @MainActor, nonisolated | references/actor-isolation.md |
~20 lines |
| TaskGroup, AsyncSequence, AsyncStream, cancellation | references/task-patterns.md |
~20 lines |
| Failure modes, common mistakes | references/preferred-patterns.md |
~20 lines |
| concurrency overview, structured concurrency patterns | references/swift-concurrency.md |
~30 lines |
| XCTest, Swift Testing, test doubles, async tests, UI tests | references/swift-testing.md |
~250 lines |
Loading rule. Read the references whose signals match the task before responding.
Core Rules (Always Apply)
Concurrency
- Prefer structured concurrency -- use
TaskGroupover looseTask { }whenever possible; structured tasks propagate cancellation and errors automatically. - Mark types Sendable -- enable strict concurrency checking (
-strict-concurrency=complete) and resolve all warnings before they become errors in Swift 6. - Use actors for shared mutable state -- avoid manual locks; actors provide compiler-verified safety.
- Cancel what you create -- every
Taskstored in a property should have a corresponding cancellation path. - Minimize @MainActor surface -- isolate only the UI layer; keep business logic and networking off the main actor.
Testing
- One assertion per concept -- a single test can have multiple assertions if they verify the same logical behavior, but avoid testing unrelated things together.
- Arrange-Act-Assert -- structure every test into setup, execution, and verification phases.
- Name tests descriptively --
testFetchUser_withExpiredToken_throwsAuthErroris better thantestFetch2. - Prefer Swift Testing for new code -- use
@Testand#expectwhen targeting Swift 5.9+; fall back to XCTest for older targets or UI tests. - Ensure test independence -- each test must be runnable in isolation; always produce self-contained test state.
What ships with it
6 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.
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.
- 2d ago First seen · 108 lines · 22 tokens per session scan A b5e023461f07
swift is a skill published in the GitHub repository notque/vexjoy-agent (420 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 921 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
swift-testing
The Swift Testing framework (import Testing) — @Test functions.
swift-testing-pro
Writes, reviews, and improves Swift Testing code using modern APIs and best practices. Use when reading, writing, or reviewing projects that use Swift Testing.
kotlin-patterns
Kotlin: coroutines, Flow, sealed/data classes, null safety, Ktor, Compose, KMP. Triggers: Kotlin, coroutine, Flow, suspend, Ktor, Jetpack Compose, KMP, kotlinx.
swift-patterns
Swift/iOS: SwiftUI, Combine, async/await, actors, SPM, Core Data, UIKit interop. Triggers: Swift, SwiftUI, Combine, iOS, Xcode, actor, Core Data, @MainActor, @State.
agent-flutter-expert
Expert Flutter specialist mastering Flutter 3+ with modern architecture patterns. Specializes in cross-platform development, custom animations, native integrations, and performance optimization with focus on creating beautiful, native-performance applications.
add-ktnip-ksp-tests
Adds tests for the ktnip KSP processor. Use when adding tests for a new collector, testing processor behavior with new annotations, or verifying KSP code generation for the telegram-bot library.