xcode-simulator-vision

A collection of 20 tools for controlling Apple simulators and devices, profiling apps, and inspecting or interacting with their interfaces.

In plain words
What is it for?
Booting and managing simulators, installing and launching apps, capturing screenshots or recordings, sending notifications, changing locations or settings, profiling performance, and tapping or filling fields through the accessibility interface.
Why use it?
It helps test how an app behaves across device states and user interactions without manually operating every simulator step.

Skill for Claude CodeCodex

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 skills/yanxreal/xcode-mpc/xcode-simulator-vision
Any agent
npx skills add YanxReal/Xcode-MPC --skill xcode-simulator-vision
Clone the repo
git clone --depth 1 https://github.com/YanxReal/Xcode-MPC

Made for: Claude Code, Codex.

Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 841 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 $0.00087 $0.00841
Opus 5 $0.00044 $0.00420
Sonnet 5 $0.00017 $0.00168
Haiku 4.5 $0.00009 $0.00084

Measured 2d ago against content hash c08854548e5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

xcode-simulator-vision 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 2d 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/xcode-simulator-vision/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Xcode Simulator & Vision/UI

Covers simulators (9 core + 5 extra), devices (2), profiling (1) and Vision/UI (4) — 20 tools for running and interacting with simulators intelligently.

Tools

Core simctl (9): simctl_list (booted), simctl_lifecycle (boot|shutdown|erase), simctl_install_launch, simctl_media_capture (screenshot|record), simctl_push_notification, simctl_location_mock, simctl_privacy_control, simctl_ui_appearance, simctl_open_url

Extra simctl (5): simctl_set_appearance (light|dark), simctl_set_dynamic_type (12 extra-smallaccessibility-extra-extra-extra-large), simctl_manage_storekit (load|clear|buy|refund), simctl_simulate_event (incoming_calltel://, network_offline/onlinestatus_bar), simctl_send_push (object jsonPayload with apssimctl push)

Devices/Profiling: devicectl_list, devicectl_logs (1-120s), xctrace_profile (Time Profiler|Allocations|Leaks)

Vision/UI (4): simctl_get_screen_analysis (screenshot + sips{imagePath,resolution}), simctl_inspect_ui_tree (accessibility tree → [{role,center}]), simctl_tap_by_text (partial/exact → CLICKED:x,y), simctl_fill_field (clearFirst + keystroke)

Vision Workflow (Preferred)

Instead of guessing coordinates:

simctl_get_screen_analysis {udid:"booted"}  // get /tmp/sim_screen_latest.png + resolution for Vision LLM
→ simctl_inspect_ui_tree {}                  // get JSON tree with centers
→ simctl_tap_by_text {text:"Continuar"}      // smart tap computes center
→ simctl_fill_field {labelOrPlaceholder:"Correo", textToType:"[email protected]", clearFirst:true}

For icon-only buttons, use the imagePath from get_screen_analysis with Vision LLM to estimate coordinates, then fallback to tap_by_text.

Classic Simulator Flow

simctl_list {booted:true}
→ simctl_lifecycle {action:"boot", udid:"..."}
→ simctl_install_launch {appPath:"build/.../MyApp.app", bundleId:"com.yanxreal.myapp", launch:true}
→ simctl_location_mock {latitude:40.41, longitude:-3.70}
→ simctl_media_capture {type:"screenshot", outputPath:"/tmp/01.png"}
→ simctl_set_appearance {appearance:"dark"}
→ simctl_set_dynamic_type {sizeCategory:"large"}

Read the full file on GitHub · 54 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. 2d ago First seen · 54 lines · 0 tokens per session scan A c08854548e5f

Subscribe to this mod's changes

xcode-simulator-vision is a skill published in the GitHub repository YanxReal/Xcode-MPC (1 stars, last pushed 2d ago), licensed MIT. It adds 87 tokens to every session and 841 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

shortcuts-playground

Build, validate, sign, archive, and REMIX macOS/iOS Shortcuts by creating plist files. Use when asked to create, modify, or remix shortcuts; automate workflows; build .shortcut files; or generate Shortcuts plists. Covers WF actions, AppIntents, third-party actions, variable references, and control flow using bundled…

viticci/shortcuts-playground-plugin · 81 tokens

heimdall

Work with an Apple App Store Connect account through Heimdall's MCP servers — App Store listings and metadata, TestFlight builds and testers, subscription and in-app-purchase prices, customer reviews, sales and analytics reports, certificates and provisioning profiles. Use this whenever the user asks about their app…

erayendes/app-store-connect-mcp · 180 tokens

apple-design

Complete Apple Human Interface Guidelines (HIG) and Apple Design System standard. Use when designing, building, or auditing UI/UX for iOS, iPadOS, macOS, watchOS, visionOS, or Apple-styled web and mobile applications.

billythekidz/apple-design-skill · 55 tokens

ipaship-audit

Use when auditing iOS/Android app submissions for compliance with Apple App Store Review Guidelines or Google Play Developer Policies. Scan .ipa, .apk, or .zip files against official store policies, generate structured compliance reports, and identify violations with remediation steps.

atharvnaik1/ipaship-audit · 57 tokens

app-review-max

Pass Apple App Review the first time and recover fast when rejected. USE THIS SKILL whenever the user is submitting to the App Store, preparing a submission, asks 'will this get rejected', mentions App Review, a rejection, Resolution Center, an appeal, or any guideline number (2.1, 2.3, 3.1.1, 4.3, 5.1.x, etc.)…

Dev869/swift-tothemax · 218 tokens

apple-legal-max

Legal and privacy compliance for Apple-platform apps (iOS/iPadOS/macOS/watchOS/tvOS/visionOS). Use this skill WHENEVER a task touches - privacy policy, terms of service, ToS, EULA, license agreement, privacy manifest, PrivacyInfo.xcprivacy, required reason APIs, App Tracking Transparency, ATT, IDFA, tracking domains…

Dev869/swift-tothemax · 235 tokens