swift-concurrency-guard

swift-concurrency-guard is a skill for Claude Code from SethCalkins/claude-ios-swift-plugin. It costs 55 tokens per session (2,745 once invoked), scanned A, original, MIT.

A Swift static analyzer that checks code edits for unsafe concurrency patterns. Swift concurrency is the language system for running asynchronous work safely across tasks and actors.

In plain words
What is it for?
It runs as a Claude Code pre-edit hook, rejects forbidden patterns such as unstructured detached tasks, and reports the rule that must be fixed.
Why use it?
It blocks edits that can cause cancellation problems, launch hangs, priority issues, or too many simultaneous tasks before those problems enter the codebase.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: mentions Claude Code.

Part of the swift-skills plugin — 10 skills, 4 commands, 3 agents shipped together

Good fit It runs as a Claude Code pre-edit hook, rejects forbidden patterns such as unstructured detached tasks, and reports the rule that must be fixed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sethcalkins/claude-ios-swift-plugin/swift-concurrency-guard
Install

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.

Any agent
npx skills add SethCalkins/claude-ios-swift-plugin --skill swift-concurrency-guard
Clone the repo
git clone --depth 1 https://github.com/SethCalkins/claude-ios-swift-plugin

Made for: Claude Code.

Or install swift-skills, the plugin that ships this one along with the rest of its 10 skills, 4 commands, 3 agents.

Wrote 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.

agentmods badge for swift-concurrency-guard

README.md
[![agentmods](https://agentmods.dev/badge/skills/sethcalkins/claude-ios-swift-plugin/swift-concurrency-guard/github.svg)](https://agentmods.dev/skills/sethcalkins/claude-ios-swift-plugin/swift-concurrency-guard)
Your own site
<a href="https://agentmods.dev/skills/sethcalkins/claude-ios-swift-plugin/swift-concurrency-guard"><img src="https://agentmods.dev/badge/skills/sethcalkins/claude-ios-swift-plugin/swift-concurrency-guard/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.

agentmods 80×15 button for swift-concurrency-guard

Your own site · 80×15
<a href="https://agentmods.dev/skills/sethcalkins/claude-ios-swift-plugin/swift-concurrency-guard"><img src="https://agentmods.dev/badge/skills/sethcalkins/claude-ios-swift-plugin/swift-concurrency-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,745 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.02745
Opus 5 $0.00028 $0.01373
Sonnet 5 $0.00011 $0.00549
Haiku 4.5 $0.00006 $0.00275

Measured 11d ago against content hash 6ad6b499ee79, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

swift-concurrency-guard 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 11d 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.

skills/swift-concurrency-guard/SKILL.md · 457 lines

How it starts

The opening of the file, as written. The whole thing — 457 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Swift Concurrency Guard

Overview

The Concurrency Guard is a SwiftSyntax-based static analyzer that blocks edits introducing concurrency anti-patterns. It runs as a Claude Code PreToolUse hook, preventing regressions before they happen.

Blocker Rules (Exit Code 2)

These rules block edits when violated. Claude receives the error and must fix the code.

CC-CONC-001 — No Task.detached

Why: Unstructured tasks cause priority inversions and are hard to cancel. SSE reconnection loops using Task.detached became unbounded/unowned.

Detect: Task.detached anywhere outside allowlisted paths.

Fix: Replace with structured Task {} owned by a lifecycle object; store handle + cancel.

// BAD
Task.detached { await fetchData() }

// GOOD
private var fetchTask: Task<Void, Never>?

func startFetch() {
    fetchTask = Task { await fetchData() }
}

deinit { fetchTask?.cancel() }

CC-CONC-002 — No Task in init for App-Critical Types

Why: Actor hops during sync init cause launch hangs ("actor hop during sync init").

Scope: App, Scene, AppShellState, ViewModels, Coordinators, Services created at launch.

Detect: In init() { ... } block, forbid Task {, Task(, await, withTaskGroup.

Fix: Move to .task {} in the view, or an explicit async start() called from .task.

// BAD
init() {
    Task { await loadData() }  // Actor hop in sync init!
}

// GOOD
init() {
    // Synchronous setup only
}

var body: some View {
    ContentView()
        .task { await viewModel.start() }
}

CC-CONC-003 — No Async Work in Render/Layout Paths

Why: Tasks launched during layoutSubviewsCA::Transaction::commit hangs.

Detect: Forbid Task creation inside:

  • var body: some View { ... } (and nested builders)
  • layoutSubviews, updateUIView, updateNSView, draw(_:), viewDidLayoutSubviews, updateConstraints

Fix: Use .task(id:), onAppear (guarded), or a coordinator started after first frame.

Read the full file on GitHub · 457 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 11d ago First seen · 457 lines · 55 tokens per session scan A 6ad6b499ee79

Subscribe to this mod's changes

swift-concurrency-guard is a skill published in the GitHub repository SethCalkins/claude-ios-swift-plugin (2 stars, last pushed 7mo ago), licensed MIT. It adds 55 tokens to every session and 2,745 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.

Related

Other skills, from other repositories

swift-concurrency-expert

Swift concurrency review/fix: compiler errors, Sendable, isolation, remediation.

steipete/agent-scripts · 22 tokens

axiom-analyze-swift-performance

Use when the user mentions Swift performance audit, code optimization, or performance review.

CharlesWiltgen/Axiom · 24 tokens

kotlin-tooling-native-build-performance

Diagnoses and fixes slow Kotlin/Native compilation and linking in Kotlin Multiplatform projects that target iOS. Use when the user reports slow iOS or shared-framework builds, long linkDebug/linkRelease or XCFramework tasks, cold CI builds that re-download the Kotlin/Native toolchain, KSP or other generated code on…

Kotlin/kotlin-agent-skills · 96 tokens

xcode-compilation-analyzer

Analyze Swift and mixed-language compile hotspots using build timing summaries and Swift frontend diagnostics, then produce a recommend-first source-level optimization plan. Use when a developer reports slow compilation, type-checking warnings, expensive clean-build compile phases, long CompileSwiftSources tasks…

AvdLee/Xcode-Build-Optimization-Agent-Skill · 74 tokens

kotlin-coroutines-skill

Load, when a developer writes, reviews, or debugs Kotlin coroutine code and needs help spotting concurrency bugs — GlobalScope leaks, runBlocking in suspend, missing Flow catch, hardcoded or wrong dispatchers, unhandled timeouts, cancellation and structured-concurrency mistakes — or asks how to make async Kotlin…

santimattius/structured-coroutines · 71 tokens

agent-swift-build-resolver

Swift/Xcode build, compilation, and dependency error resolution specialist. Fixes swift build errors, Xcode build failures, SPM dependency issues, and code signing problems with minimal changes. Use when Swift builds fail.

KunanonJ/ai-skills-hub · 50 tokens