xcuitest

xcuitest is a command for coding agents from OkminLee/everything-claude-code-ios. It costs 32 tokens per session (2,705 once invoked), scanned A, original, MIT.

A command for creating and running end-to-end user-interface tests for iOS apps with XCUITest. These tests exercise complete user journeys on simulators or devices, such as logging in or completing onboarding.

In plain words
What is it for?
Use it to generate and run tests for login, payments, notifications, accessibility, and other multi-step app flows, with screenshots, videos, and test reports.
Why use it?
It checks that screens, navigation, and interactions work together and records evidence when a journey fails.

Command

Part of the everything-claude-code-ios plugin — 5 skills, 10 commands, 12 agents, 5 hooks, 4 MCP servers 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 commands/okminlee/everything-claude-code-ios/xcuitest
Clone the repo
git clone --depth 1 https://github.com/OkminLee/everything-claude-code-ios

Or install everything-claude-code-ios, the plugin that ships this one along with the rest of its 5 skills, 10 commands, 12 agents, 5 hooks, 4 MCP servers.

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 xcuitest

README.md
[![agentmods](https://agentmods.dev/badge/commands/okminlee/everything-claude-code-ios/xcuitest.svg)](https://agentmods.dev/commands/okminlee/everything-claude-code-ios/xcuitest)
Your own site
<a href="https://agentmods.dev/commands/okminlee/everything-claude-code-ios/xcuitest"><img src="https://agentmods.dev/badge/commands/okminlee/everything-claude-code-ios/xcuitest.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,705 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 $0.00032 $0.02705
Opus 5 $0.00016 $0.01352
Sonnet 5 $0.00006 $0.00541
Haiku 4.5 $0.00003 $0.00270

Measured 4d ago against content hash 710d10ca948e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

xcuitest 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 4d 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.

commands/xcuitest.md · 439 lines

How it starts

The opening of the file, as written. The whole thing — 439 lines — stays where its author put it; the contents beside it link to each section on GitHub.

XCUITest Command

This command invokes the xcuitest-runner agent to generate, maintain, and execute end-to-end UI tests for iOS apps.

What This Command Does

  1. Generate Test Journeys - Create XCUITest tests for user flows
  2. Run UI Tests - Execute tests on simulators/devices
  3. Capture Artifacts - Screenshots, videos on failures
  4. Manage Flaky Tests - Quarantine unstable tests
  5. Generate Reports - xcresult bundles for analysis

When to Use

Use /xcuitest when:

  • Testing critical user journeys (login, onboarding, payments)
  • Verifying multi-step flows work end-to-end
  • Testing UI interactions and navigation
  • Validating accessibility
  • Preparing for App Store submission
  • Testing push notification handling

How It Works

The xcuitest-runner agent will:

  1. Analyze user flow and identify test scenarios
  2. Generate XCUITest using Page Object Model (Screen Objects)
  3. Set up accessibility identifiers if missing
  4. Run tests on specified simulators
  5. Capture failures with screenshots and videos
  6. Generate report with results and artifacts

Example Usage

User: /xcuitest Test the login and home flow

Agent (xcuitest-runner):
# E2E Test Generation: Login to Home Flow

## Test Scenario Identified

**User Journey:** Launch → Login → Home Screen

**Test Coverage:**
1. App launches successfully
2. Login screen appears
3. Enter credentials
4. Tap login button
5. Home screen loads
6. User name displayed

## Generated Screen Objects

```swift
// UITests/Screens/LoginScreen.swift
import XCTest

final class LoginScreen {
    private let app: XCUIApplication

    init(app: XCUIApplication) {
        self.app = app
    }

    // MARK: - Elements
    var emailField: XCUIElement { app.textFields["email-field"] }
    var passwordField: XCUIElement { app.secureTextFields["password-field"] }
    var loginButton: XCUIElement { app.buttons["login-button"] }
    var errorLabel: XCUIElement { app.staticTexts["error-label"] }

Read the full file on GitHub · 439 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. 4d ago First seen · 439 lines · 32 tokens per session scan A 710d10ca948e

Subscribe to this mod's changes

xcuitest is a command published in the GitHub repository OkminLee/everything-claude-code-ios (58 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 2,705 once invoked, about $0.0002 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 2026-08-30.