swift-concurrency-review

swift-concurrency-review is a skill for Claude Code from charlesjones-dev/claude-code-plugins-dev. It costs 94 tokens per session (1,947 once invoked), scanned A, original, MIT.

A focused review guide for Swift 6 and SwiftUI code, covering compiler and runtime problems related to concurrency, data sharing, and platform-specific code. SwiftUI is Apple's framework for building user interfaces in Swift.

In plain words
What is it for?
Use it to review changed Swift files for actor-boundary errors, protocol isolation problems, unsafe optionals, predicate limits, and missing operating-system guards.
Why use it?
It helps catch issues that may be rejected by the compiler, crash during compilation, or pass basic checks but fail at runtime.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the ai-swift plugin — 5 skills, 1 agent shipped together

Good fit Use it to review changed Swift files for actor-boundary errors, protocol isolation problems, unsafe optionals, predicate limits, and missing operating-system guards.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/charlesjones-dev/claude-code-plugins-dev/swift-concurrency-review
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 charlesjones-dev/claude-code-plugins-dev --skill swift-concurrency-review
Clone the repo
git clone --depth 1 https://github.com/charlesjones-dev/claude-code-plugins-dev

Made for: Claude Code.

Or install ai-swift, the plugin that ships this one along with the rest of its 5 skills, 1 agent.

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-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/charlesjones-dev/claude-code-plugins-dev/swift-concurrency-review.svg)](https://agentmods.dev/skills/charlesjones-dev/claude-code-plugins-dev/swift-concurrency-review)
Your own site
<a href="https://agentmods.dev/skills/charlesjones-dev/claude-code-plugins-dev/swift-concurrency-review"><img src="https://agentmods.dev/badge/skills/charlesjones-dev/claude-code-plugins-dev/swift-concurrency-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,947 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00094 $0.01947
Opus 5 $0.00047 $0.00974
Sonnet 5 $0.00019 $0.00389
Haiku 4.5 $0.00009 $0.00195

Measured yesterday against content hash 6d9d89363d16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

swift-concurrency-review 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 yesterday.

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.

plugins/ai-swift/skills/swift-concurrency-review/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Swift 6 + SwiftUI Concurrency Review

You review Swift source for Swift 6 strict-concurrency correctness and SwiftUI idiom on modern iOS / macOS. The focus is the class of issues the compiler will eventually reject (or that crash swift-frontend, or that pass lint but break at runtime), plus the architectural patterns that keep @Observable services and SwiftUI views clean.

Scope discipline: this is not a general bug hunt or a style cleanup. Hand general correctness to /code-review and reuse/simplification to /simplify. Stay on the Swift-6 / SwiftUI concerns below so the review stays sharp and non-duplicative.

What to review

Default to the changed Swift files (git diff --name-only + staged + untracked *.swift). If $ARGUMENTS names a path or files, review those. If a KB exists at docs/kb/conventions/swift-6-patterns.md (or similar), read it first - the project may have its own codified rules that supersede the generic ones here.

Review dimensions

For each, report file:line, the issue, the concrete fix, and a one-line why. Cite the compiler diagnostic text where it helps the user recognize it.

1. Sendability across isolation boundaries

  • A type sent across an actor boundary (an endpoint body, a value captured into a detached Task, anything an actor method returns) must be Sendable. Endpoint bodies that cross the boundary need (any Encodable & Sendable)?, not bare any Encodable.
  • Domain models that drop Sendable (e.g. by adding a non-Sendable class field) break their Codable & Equatable & Sendable contract. Flag a new stored property that is a non-Sendable reference type.
  • CFString and most CoreFoundation types are not Sendable. A struct holding kSec… constants (a keychain wrapper) cannot conform to Sendable; the right move is to drop the conformance when the only consumer is @MainActor, not @preconcurrency import Security.

2. Actor isolation mismatches

  • @MainActor witness vs nonisolated protocol requirement. A @MainActor type (including any static func/static let on a SwiftUI.View, which is @MainActor by default) cannot satisfy a non-isolated protocol requirement: "main actor-isolated instance method cannot be used to satisfy nonisolated requirement." Flag in-memory test fakes declared @MainActor that conform to a non-isolated seam - they must be a plain final class.
  • Static helper on a View type read from a nonisolated context (e.g. a plain XCTestCase) warns under Swift 6. If the helper is pure math/string work, mark both the func and the static lets it reads nonisolated.
  • nonisolated init() for default-param evaluation. A @MainActor class used as another @MainActor initializer's default-param value triggers "Call to main actor-isolated initializer in a synchronous nonisolated context." Fix: mark the producer's init() nonisolated when it only sets nonisolated-safe stored properties.
  • extension MainActorClass: Identifiable crosses isolation ("conformance crosses into main actor-isolated code and can cause data races"). Use a plain Sendable struct as the sheet(item:) payload instead.

Read the full file on GitHub · 91 lines

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. yesterday First seen · 91 lines · 94 tokens per session scan A 6d9d89363d16

Subscribe to this mod's changes

swift-concurrency-review is a skill published in the GitHub repository charlesjones-dev/claude-code-plugins-dev (34 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 1,947 once invoked, about $0.0005 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 2026-09-06.

Related

Other skills, from other repositories

axiom-audit-codable

Use when the user mentions Codable review, JSON encoding/decoding issues, data serialization audit, or modernizing legacy code.

CharlesWiltgen/Axiom · 32 tokens

axiom-swift-simplifier

Use when the user wants to simplify Swift code, reduce boilerplate, or make Swift more readable and idiomatic without changing behavior.

CharlesWiltgen/Axiom · 34 tokens

solid-principles

SOLID principles checklist with Java examples. Use when a class has too many responsibilities, an abstraction leaks, or a dependency points the wrong way, and when the user asks about Single Responsibility, Open/Closed, Liskov, Interface Segregation or Dependency Inversion. For naming, duplication and method length…

decebals/claude-code-java · 73 tokens

concurrency-review

Review Java concurrency code for thread safety, race conditions, deadlocks, and modern patterns (Virtual Threads, CompletableFuture, @Async). Use when user asks "check thread safety", "concurrency review", "async code review", or when reviewing multi-threaded code.

decebals/claude-code-java · 58 tokens

java-code-review

Systematic code review for Java with null safety, exception handling, concurrency, and performance checks. Use when user says "review code", "check this PR", "code review", or before merging changes.

decebals/claude-code-java · 45 tokens

code-quality

Agents should invoke this skill for code reviews, linting/formatting setup, maintainability checks, complexity concerns, warning cleanup, coding standards, or quality gates in Rust, TypeScript, Python, shell, and mixed repos.

waybarrios/opencode-power-pack · 49 tokens