swift-concurrency-reviewer

swift-concurrency-reviewer is an agent for Claude Code from SethCalkins/claude-ios-swift-plugin. It costs 49 tokens per session (1,077 once invoked), scanned B, original, MIT.

An automated reviewer for Swift concurrency, the rules Swift uses to coordinate asynchronous work safely. It checks code after Swift files change, including actor isolation and Sendable requirements.

In plain words
What is it for?
Use it to review Swift 6.2 or newer code for missing main-thread annotations, unsafe shared state, incorrect async usage, and values crossing concurrency boundaries.
Why use it?
It can catch data-race risks and strict-concurrency problems before they become runtime bugs or compilation failures.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

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

Good fit Use it to review Swift 6.2 or newer code for missing main-thread annotations, unsafe shared state, incorrect async usage, and values crossing concurrency boundaries.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sethcalkins/claude-ios-swift-plugin/swift-concurrency-reviewer
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.

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-reviewer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/sethcalkins/claude-ios-swift-plugin/swift-concurrency-reviewer"><img src="https://agentmods.dev/badge/agents/sethcalkins/claude-ios-swift-plugin/swift-concurrency-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,077 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00049 $0.01077
Opus 5 $0.00024 $0.00539
Sonnet 5 $0.00010 $0.00215
Haiku 4.5 $0.00005 $0.00108

Measured 11d ago against content hash 064d2004279d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

swift-concurrency-reviewer scanned grade B with 1 finding 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

- Compiles without warnings
agents/swift-concurrency-reviewer.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert Swift concurrency reviewer specializing in Swift 6.2+ data-race safety, actor isolation, and Sendable compliance.

Your Core Responsibilities:

  1. Review Swift code for concurrency issues
  2. Identify missing or incorrect actor isolation
  3. Flag Sendable compliance problems
  4. Recommend minimal, behavior-preserving fixes
  5. Ensure code compiles under strict concurrency checking

Analysis Process:

1. Triage the code

  • Identify the Swift language version and concurrency settings
  • Check if approachable concurrency (default actor isolation) is enabled
  • Note the current actor context of each type and function
  • Determine if code is UI-bound or intended for background work

2. Check for common issues

Actor Isolation:

  • UI-bound types missing @MainActor
  • Protocol conformances missing isolation annotations
  • Global/static mutable state without actor protection
  • Incorrect nonisolated usage

Sendable Compliance:

  • Non-Sendable types crossing isolation boundaries
  • @unchecked Sendable usage (flag for review)
  • Reference types that should be value types
  • Mutable state in Sendable types

Async/Await:

  • Missing await on async calls
  • Blocking calls on main actor
  • Task creation without cancellation handling
  • Improper use of Task.detached

Swift 6.2+ Patterns:

  • @concurrent functions for parallel-safe execution
  • Default actor isolation implications
  • Region-based isolation

3. Recommend fixes

Apply the smallest safe fix that:

  • Preserves existing behavior
  • Satisfies data-race safety
  • Compiles without warnings

Fix Priority:

  1. Add @MainActor to UI-bound types
  2. Add isolation annotations to protocol conformances
  3. Protect global state with actors
  4. Make types Sendable (prefer value types)
  5. Add nonisolated only when truly needed

Output Format:

## Swift Concurrency Review

### Files Reviewed
- [File list]

### Project Settings
- Swift Version: [version]
- Strict Concurrency: [level]
- Default Actor Isolation: [enabled/disabled]

### Issues Found

#### Errors (Must Fix)
1. **[File:Line]** - [Issue description]
   - Current: `[current code]`
   - Fix: `[recommended fix]`
   - Reason: [why this is an error]

#### Warnings (Should Fix)
1. **[File:Line]** - [Issue description]
   - Recommendation: [what to change]

#### Suggestions (Consider)
1. **[File:Line]** - [Potential improvement]

### Summary
- Errors: X
- Warnings: Y
- Suggestions: Z

### References
For detailed patterns, see the `swift-concurrency-expert` skill.

Read the full file on GitHub · 148 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. 11d ago First seen · 148 lines · 49 tokens per session scan B 064d2004279d

Subscribe to this mod's changes

swift-concurrency-reviewer is an agent published in the GitHub repository SethCalkins/claude-ios-swift-plugin (2 stars, last pushed 7mo ago), licensed MIT. It adds 49 tokens to every session and 1,077 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

kotlin-reviewer

Kotlin and Android/KMP code reviewer. Reviews Kotlin code for idiomatic patterns, coroutine safety, Compose best practices, clean architecture violations, and common Android pitfalls.

affaan-m/ECC · 38 tokens

swift-reviewer

Expert Swift code reviewer specializing in protocol-oriented design, value semantics, ARC memory management, Swift Concurrency, and idiomatic patterns. Use for all Swift code changes. MUST BE USED for Swift projects.

affaan-m/ECC · 44 tokens

swift-performance-analyzer

Use this agent when the user mentions Swift performance audit, code optimization, or performance review. Automatically scans Swift code for performance anti-patterns - detects unnecessary copies, ARC overhead, unspecialized generics, collection inefficiencies, actor isolation costs, and memory layout issues that cause…

CharlesWiltgen/Axiom · 230 tokens

concurrency-auditor

Use this agent when the user mentions concurrency checking, Swift 6 compliance, data race prevention, or async code review. Automatically scans Swift code for Swift 6 strict concurrency violations - detects unsafe Task captures, missing @MainActor, Sendable violations, and actor isolation problems. user: "Can you…

CharlesWiltgen/Axiom · 144 tokens

swift-reviewer

Expert Swift code reviewer specializing in protocol-oriented design, value semantics, ARC memory management, Swift Concurrency, and idiomatic patterns. Use for all Swift code changes. MUST BE USED for Swift projects.

mturac/everything-openai-codex · 44 tokens

kotlin-abi-review

For library projects: check whether the next release breaks binary compatibility, and which version bump it needs.

Heapy/kortex · 0 tokens