swift-code-review

swift-code-review is a skill for Claude Code, Codex from jeremieb/swift-unit-test-instructions. It costs 83 tokens per session (1,439 once invoked), scanned A, original, MIT.

A review guide for Swift, SwiftUI, and UIKit code. It checks architecture, naming, error handling, dependency use, asynchronous code, and common coding mistakes, then groups findings by severity.

In plain words
What is it for?
Use it to review changed files or pull requests, check MVVM boundaries and testability, find unsafe Swift patterns, inspect error and concurrency handling, and report actionable feedback.
Why use it?
It helps identify correctness and maintainability problems before code is merged. It also keeps reviews focused on concrete issues instead of style nitpicks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md.

Good fit Use it to review changed files or pull requests, check MVVM boundaries and testability, find unsafe Swift patterns, inspect error and concurrency handling, and report actionable feedback.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeremieb/swift-unit-test-instructions/swift-code-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 jeremieb/swift-unit-test-instructions --skill swift-code-review
Clone the repo
git clone --depth 1 https://github.com/jeremieb/swift-unit-test-instructions

Made for: Claude Code, Codex.

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-code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/jeremieb/swift-unit-test-instructions/swift-code-review.svg)](https://agentmods.dev/skills/jeremieb/swift-unit-test-instructions/swift-code-review)
Your own site
<a href="https://agentmods.dev/skills/jeremieb/swift-unit-test-instructions/swift-code-review"><img src="https://agentmods.dev/badge/skills/jeremieb/swift-unit-test-instructions/swift-code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,439 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 $0.00083 $0.01439
Opus 5 $0.00042 $0.00720
Sonnet 5 $0.00017 $0.00288
Haiku 4.5 $0.00008 $0.00144

Measured 8d ago against content hash 612b72347351, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

swift-code-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 8d 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-code-review/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Swift Code Review

Instructions

Step 1: Read All Provided Files

Read every file mentioned or pasted before writing any comments. Do not review code you have not fully read.

If reviewing a PR, ask for:

  • The feature or bug being fixed
  • The files changed
  • Any context about constraints or trade-offs

Step 2: Apply the Review Checklist

Architecture (MVVM)

  • Business logic is in ViewModel or Service — not in View/ViewController body
  • External dependencies (network, storage, time) are injected via protocol, not hardcoded
  • No URLSession.shared, UserDefaults.standard, or Date() called directly from Views
  • No global singletons used without injection support
  • Thin View layer: no conditional business logic, no data fetching in onAppear without ViewModel delegation

Swift Quality

  • No force unwraps (!) in production paths
  • Errors propagated via throws or Result — not silently swallowed
  • let preferred over var where value does not change
  • No magic numbers or hardcoded strings — use named constants or localizable strings
  • One primary type per file

Concurrency

  • async/await used for all new async code (not completion handlers)
  • @MainActor applied to ViewModel and any type that updates UI state
  • No DispatchQueue.main.async in ViewModel or Service layers
  • No sleep() anywhere
  • Sendable conformance considered for types crossing actor boundaries
  • Task objects are stored and cancelled if the parent scope is deallocated

Testing

  • New business logic has corresponding tests
  • New dependencies are injectable (protocol-backed)
  • Existing tests still compile and pass
  • No test changes that weaken coverage of critical paths

Naming

  • Types: UpperCamelCase
  • Functions / variables: lowerCamelCase
  • Booleans: assertion form (isLoading, hasError, canSubmit, isPremium)
  • Avoid abbreviations unless universally understood (url, id, api)
  • Test methods: test_when_<Condition>_should_<ExpectedOutcome>()
  • Protocol names: noun or adjective, not Protocol suffix (prefer UserRepository over UserRepositoryProtocol where unambiguous, but Protocol suffix is acceptable for clarity)

Read the full file on GitHub · 157 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. 8d ago First seen · 157 lines · 83 tokens per session scan A 612b72347351

Subscribe to this mod's changes

swift-code-review is a skill published in the GitHub repository jeremieb/swift-unit-test-instructions (5 stars, last pushed 6mo ago), licensed MIT. It adds 83 tokens to every session and 1,439 once invoked, about $0.0004 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

code-reviewer

Code review practices including review checklists, refactoring patterns, PR best practices, and team conventions. Trigger for code review guidance, refactoring advice, or PR process design.

FutureJJ/claude-skills · 39 tokens

offensive-mobile

Mobile (Android + iOS) application penetration testing methodology. Covers static analysis (apktool/jadx for Android, class-dump/Hopper/IDA for iOS), dynamic instrumentation with Frida and Objection, SSL pinning bypass strategies, root/jailbreak detection bypass, deep-link / URL-scheme abuse, exported component…

SnailSploit/Claude-Red · 185 tokens

paywall-pricing-optimizer

Design effective paywalls, structure subscription tiers, and optimize pricing for mobile apps. Covers monetization model selection, paywall screen design, pricing psychology, A/B testing strategy, and RevenueCat/StoreKit/Google Billing integration. Use when the user wants to monetize an app, design a paywall, choose…

robertguss/claude-code-toolkit · 143 tokens

app-store-listing-optimizer

Optimize iOS App Store and Google Play Store listings for maximum discoverability and conversion. Perform competitive keyword research, craft keyword-optimized titles/subtitles/descriptions, design screenshot sequences, and generate A/B test variants. Use when the user has a built app and needs to write or improve…

robertguss/claude-code-toolkit · 137 tokens

app-creator

Orchestrate iOS/macOS app scaffolding and optional skill adoption for existing projects. Use when users want a guided wizard that can scaffold with XcodeGen and optionally install xcode-makefiles and simple-tasks.

robertguss/claude-code-toolkit · 49 tokens

xcode-makefiles

Install strict Xcode Makefile tooling for iOS/macOS projects, including build/run/test scripts with AGENTNAME-based per-agent isolation under build/. Use when a project needs reproducible local CLI builds without full app scaffolding.

robertguss/claude-code-toolkit · 52 tokens