What is iphone-mirroring?

A tool for controlling a nearby iPhone from a Mac window using macOS iPhone Mirroring, including viewing, tapping, scrolling, and opening Settings or Shortcuts.

Use it to inspect an iPhone screen, change iOS settings, or edit an existing Shortcut on the device. It does not create .shortcut files.

It removes the need to handle the phone directly for supported tasks. It also sets strict limits around private apps and sensitive actions such as messaging, payments, sharing, and deletion.

iphone-mirroring — Skill for Claude Code and Codex by truth0530

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 truth0530/mcp-server-ios-shortcuts --skill iphone-mirroring

Clone the repo

git clone --depth 1 https://github.com/truth0530/mcp-server-ios-shortcuts

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/truth0530/mcp-server-ios-shortcuts/iphone-mirroring/github.svg)](https://agentmods.dev/skills/truth0530/mcp-server-ios-shortcuts/iphone-mirroring)

Your own site

<a href="https://agentmods.dev/skills/truth0530/mcp-server-ios-shortcuts/iphone-mirroring"><img src="https://agentmods.dev/badge/skills/truth0530/mcp-server-ios-shortcuts/iphone-mirroring/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/truth0530/mcp-server-ios-shortcuts/iphone-mirroring"><img src="https://agentmods.dev/badge/skills/truth0530/mcp-server-ios-shortcuts/iphone-mirroring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,309 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.

Model	Per session	Once invoked
Fable 5.1	$0.00115	$0.01309
Opus 5	$0.00057	$0.00655
Sonnet 5	$0.00023	$0.00262
Haiku 4.5	$0.00012	$0.00131

Measured 11d ago against content hash 8b936e529760, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

iphone-mirroring 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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/iphone_mirror.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/iphone-mirroring/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

iPhone Mirroring

macOS iPhone 미러링 앱이 아이폰 화면을 맥 창으로 보여 준다. 에이전트는 그 창을 캡처·클릭·휠 스크롤한다. 단축어 .shortcut 생성은 이 스킬이 아니라 ios-shortcuts MCP다.

This is an unlocked iPhone. Every PNG you Read is sent to the agent context and the model provider. Treat capture as exfiltration, not “just looking.”

Hard stops (do not bypass)

Denied apps — do not capture, do not Read, do not click inside.
Messages / 메시지, Photos / 사진, Wallet / 지갑, Health / 건강, Mail / 메일, Phone / 전화, Contacts / 연락처, FaceTime, Passwords / 암호, banking / 은행 / 카드 / 증권, Kakao / 카카오, WhatsApp, Telegram, any chat or 2FA screen.
If the window is already there: menu home (no capture), tell the user, stop.
Do not paste, quote, or commit a capture PNG in chat, tickets, or git. Describe only what the user asked (e.g. “Shortcuts editor, card named X”).
Do not activate unless the user asked to bring the phone forward. Raising the window exposes the iPhone on the Mac display (and on screen-share).
Do not send / share / delete / confirm / transfer / pay. Physical click can do all of those. “Don’t unless asked” is not enough — those controls are off-limits even if visible.
Scrub after use. iphone_mirror.py scrub. Never leave PNGs in /tmp or the repo.

Do not exfiltrate the user’s shortcut library or personal data. ios-shortcuts MCP must run with IOS_SHORTCUTS_MCP_SAFE_MODE=1 (the server default). Do not set it to 0. Do not call export_library_shortcut or extract_system_library.

Helper

Skill dir = this file’s folder. Prefer the helper over ad-hoc mouse drags.

PY=python3   # must import Quartz (PyObjC)
$PY "<SKILL_DIR>/scripts/iphone_mirror.py" info
# activate only if the user asked to bring the window forward
$PY "<SKILL_DIR>/scripts/iphone_mirror.py" activate
$PY "<SKILL_DIR>/scripts/iphone_mirror.py" capture          # private $IPHONE_MIRROR_DIR/latest.png
$PY "<SKILL_DIR>/scripts/iphone_mirror.py" click X Y        # window-relative points
$PY "<SKILL_DIR>/scripts/iphone_mirror.py" scroll -4 --ticks 12
$PY "<SKILL_DIR>/scripts/iphone_mirror.py" menu home|spotlight|switcher
$PY "<SKILL_DIR>/scripts/iphone_mirror.py" scrub            # delete private captures

Read the full file on GitHub · 79 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

scripts/iphone_mirror.py 10 KB runs code

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.

11d ago First seen · 79 lines · 115 tokens per session scan A 8b936e529760

Subscribe to this mod's changes

iphone-mirroring is a skill published in the GitHub repository truth0530/mcp-server-ios-shortcuts (12 stars, last pushed 24d ago), licensed MIT. It adds 115 tokens to every session and 1,309 once invoked, about $0.0006 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.

Browser automation Mobile

android-unit-test

Guide for writing and converting Chromium Android unit tests across host Robolectric (chromejunittests) and on-device (chromepublicunittestapk) suites.

chromium/chromium · 36 tokens

android-test-batching

Guide for auditing and applying batching annotations (@Batch) and AutoReset rules (AutoResetCtaTransitTestRule) to Android javatests in Chromium. Use this skill when optimizing Java instrumentation test runtimes, resolving test state leaks, or migrating tests to batched execution.

chromium/chromium · 60 tokens

iphone-mirroring