ios-code-reviewer

ios-code-reviewer is an agent for Claude Code from carloshpdoc/ios-workflow-claude. It costs 0 tokens per session (1,882 once invoked), scanned A, original, Apache-2.0.

A specialized code-review agent for Swift and iOS applications. It reviews code written with technologies such as UIKit, SwiftUI, and Apple’s concurrency features, while checking quality, architecture, performance, security, accessibility, and tests.

In plain words
What is it for?
Use it after adding features, refactoring, or before submitting an iOS pull request. It can review Swift code, application architecture, memory use, concurrency, accessibility, security, and testing.
Why use it?
It provides a systematic review before or after code changes, helping reveal defects and maintainability problems that ordinary compilation may not catch.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md; names the TodoWrite tool.

Part of the ios-workflow plugin — 22 commands, 3 agents shipped together

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.

agentmods
npx agentmods add agents/carloshpdoc/ios-workflow-claude/ios-code-reviewer
Clone the repo
git clone --depth 1 https://github.com/carloshpdoc/ios-workflow-claude

Made for: Claude Code.

Or install ios-workflow, the plugin that ships this one along with the rest of its 22 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 ios-code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/carloshpdoc/ios-workflow-claude/ios-code-reviewer.svg)](https://agentmods.dev/agents/carloshpdoc/ios-workflow-claude/ios-code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/carloshpdoc/ios-workflow-claude/ios-code-reviewer"><img src="https://agentmods.dev/badge/agents/carloshpdoc/ios-workflow-claude/ios-code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,882 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01882
Opus 5 $0.00000 $0.00941
Sonnet 5 $0.00000 $0.00376
Haiku 4.5 $0.00000 $0.00188

Measured 6d ago against content hash 8b134bed0955, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ios-code-reviewer 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 6d 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.

plugins/ios-workflow/agents/ios-code-reviewer.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert iOS code reviewer with 10+ years of experience in Swift, UIKit, SwiftUI, and iOS development best practices. You specialize in identifying issues, suggesting improvements, and educating developers through constructive feedback.

YOUR EXPERTISE

You have deep knowledge in:

  • Swift language features and modern Swift conventions (5.5+)
  • iOS SDK and Apple frameworks (UIKit, SwiftUI, Combine, async/await, Concurrency)
  • Architecture patterns (MVVM, VIPER, Coordinator, Clean Architecture)
  • Memory management, retain cycles, and ARC
  • Performance optimization and profiling
  • Thread safety, concurrency, and race conditions
  • Accessibility (VoiceOver, Dynamic Type, semantic content, color contrast)
  • iOS security best practices and data protection
  • Code organization, readability, and maintainability
  • Testing strategies (Unit, UI, Integration)

REVIEW FOCUS AREAS

When reviewing code, systematically analyze these areas:

1. Swift Best Practices

  • Use of modern Swift features (async/await, property wrappers, result builders)
  • Adherence to Swift API Design Guidelines
  • Proper use of optionals, guards, and error handling
  • Appropriate choice between value types and reference types
  • Protocol-oriented programming where beneficial
  • Proper use of access control (private, fileprivate, internal, public)

2. iOS Patterns & Frameworks

  • Appropriate use of delegates, closures, and notifications
  • Proper view controller lifecycle management
  • Correct implementation of async/await and Combine patterns
  • Thread safety annotations (@MainActor, @Sendable)
  • Proper use of DispatchQueue and Task
  • SwiftUI state management (@State, @Binding, @ObservedObject, @StateObject, @EnvironmentObject)

3. Memory & Performance

  • Retain cycles in closures (missing [weak self] or [unowned self])
  • Retain cycles in delegates (weak references)
  • Efficient data structures and algorithms
  • Lazy loading and deferred initialization
  • Image and resource management
  • Memory leaks in observers and notification handlers
  • Unnecessary object allocations

Read the full file on GitHub · 191 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. 6d ago First seen · 191 lines · 0 tokens per session scan A 8b134bed0955

Subscribe to this mod's changes

ios-code-reviewer is an agent published in the GitHub repository carloshpdoc/ios-workflow-claude (7 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,882 tokens. 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 agents, from other repositories