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.
npx skills add troyjthomas/ios-agent-skills --skill device-testinggit clone --depth 1 https://github.com/troyjthomas/ios-agent-skillsWrote 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.
[](https://agentmods.dev/skills/troyjthomas/ios-agent-skills/device-testing)<a href="https://agentmods.dev/skills/troyjthomas/ios-agent-skills/device-testing"><img src="https://agentmods.dev/badge/skills/troyjthomas/ios-agent-skills/device-testing/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.
<a href="https://agentmods.dev/skills/troyjthomas/ios-agent-skills/device-testing"><img src="https://agentmods.dev/badge/skills/troyjthomas/ios-agent-skills/device-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00051 | $0.01338 |
| Opus 5.5 | $0.00020 | $0.00535 |
| Sonnet 5.5 | $0.00010 | $0.00268 |
| Haiku 4.5 | $0.00005 | $0.00134 |
Grade A, and why
device-testing 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Device Testing
Simulator is not enough. Real devices reveal real problems.
When to Use
- Polish phase is complete
- You're preparing for TestFlight distribution
- You want to verify the app before showing it to anyone
- You're doing a final check before App Store submission
Prerequisites
- iPhone connected to your Mac via USB or on the same Wi-Fi
- Apple Developer account (free account works for personal device testing)
- Device added in Xcode (Window > Devices and Simulators)
Automated Testing with XcodeBuildMCP
Before manual device testing, run automated checks via Claude Code:
Run all unit tests using XcodeBuildMCP. Report any failures.
Build for the iPhone 16 Pro simulator and verify no warnings.
This catches regressions and compile issues before you invest time in manual testing. Claude Code can also fix failing tests and re-run them in a loop.
What Automated Tests Catch
- Compile errors across all build configurations
- Unit test failures (logic, data model, state management)
- Missing file references or broken imports
What Only Manual Testing Catches
- Visual layout issues on real hardware
- Touch interaction feel (haptics, gesture responsiveness)
- Performance on actual iPhone hardware (not Mac CPU)
- Camera, GPS, and sensor-dependent features
- Real keyboard behavior vs simulator keyboard passthrough
Installing on Device
In Xcode:
- Select your connected iPhone as the run destination
- Press Cmd+R to build and run
- First time: trust the developer certificate on the iPhone (Settings > General > VPN & Device Management)
Tell Claude Code if you need help:
Help me configure Xcode to run the app on my physical iPhone.
Set the development team in Signing & Capabilities.
The Testing Script
Work through these systematically. Take notes on anything that feels wrong.
Core Flow Testing
- First launch experience
- Kill the app. Delete it. Reinstall fresh
- Does the onboarding appear?
- Can you complete setup without confusion?
- After onboarding, is the empty state clear?
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.
- 1mo ago First seen · 174 lines · 51 tokens per session scan A dfc9b8fe6216
device-testing is a skill published in the GitHub repository troyjthomas/ios-agent-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 51 tokens to every session and 1,338 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
swift-testing
Build an Apple-platform test strategy with Swift Testing for unit and integration coverage, XCTest for UI automation, deterministic fixtures, and concise agent-readable results.
iOS Testing
Unit testing, UI testing, TDD patterns, mocking, and test doubles for VIP+W architecture.
swift-testing
Write and migrate tests using the Swift Testing framework with @Test, @Suite, #expect, #require, confirmation, parameterized tests, test tags, traits, withKnownIssue, XCTest UI testing, XCUITest, test plan, mocking, test doubles, testable architecture, snapshot testing, async test patterns, test organization, and…
ios-simulator-skill
21 production-ready scripts for iOS app testing, building, and automation. Provides semantic UI navigation, build automation, accessibility testing, and simulator lifecycle management. Optimized for AI agents with minimal token output.
ios-simulator
Manages iOS Simulator devices and app tests with xcrun simctl: lifecycle, install/launch, push and location simulation, privacy permissions, deep links, status-bar overrides, screenshots/video, log streaming, app containers, and targetEnvironment(simulator). Use when scripting Simulator workflows, debugging…
xcodebuildmcp
Official skill for XcodeBuildMCP. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).