TheMizeGuy

Ios Code Review

Name: Ios Code Review
Author: TheMizeGuy

Code Quality community

SOURCE https://github.com/TheMizeGuy/ios-code-review

Description

Claude Code plugin: senior iOS code review agent simulating both Apple App Review and a senior Apple platform engineer — 12 dimensions in 4 tiers, evidence-tagged findings, dual submission/engineering verdicts, optional multi-agent team mode with runtime simulator verification.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

ios-code-review

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![Plugin Version](https://img.shields.io/badge/version-0.3.1-blue.svg)](https://github.com/TheMizeGuy/ios-code-review/releases) [![Claude Code](https://img.shields.io/badge/Claude%20Code-plugin-8A2BE2.svg)](https://claude.com/claude-code) [![Model](https://img.shields.io/badge/model-session--model-orange.svg)](https://www.anthropic.com/claude) [![Platform](https://img.shields.io/badge/platform-iOS%20%7C%20iPadOS%20%7C%20watchOS%20%7C%20tvOS%20%7C%20visionOS-lightgrey.svg)](https://developer.apple.com)

A [Claude Code](https://claude.com/claude-code) plugin that dispatches a senior iOS developer agent — running on the session model, always the strongest available Claude, with no model pin — to review your Swift / SwiftUI / UIKit code. The agent simulates **both** the Apple App Review team **and** a senior Apple platform engineer, producing two independent verdicts — and verifies runtime behavior on a real simulator via [XcodeBuildMCP](https://xcodebuildmcp.com) when available.

Two dispatch modes:

Standard (default) — single senior-ios-reviewer agent. 5-15 min. Best for diffs, features, or codebases under ~80 Swift files.
Team (requires the exact phrase "ios team review" or --team) — the orchestrator acts as team lead per the ios-team-lead manual: maps the codebase, partitions it into 4-10 non-overlapping scopes, dispatches senior-ios-reviewer sub-agents in one parallel wave, adds a dedicated runtime-verification agent and a mandatory seam review at the partition boundaries, and consolidates findings into one unified report with single submission + engineering verdicts. ~15-30 min. Best for whole-project audits, multi-target apps, and pre-submission reviews (30+ Swift files; 100+ is the sweet spot).

The reviewer is a fresh-context subagent with strict **read-only** tool access. Findings come back evidence-tagged with sp