rn-device-control

rn-device-control is a skill for Claude Code, Codex from Lykhoyda/rn-dev-agent. It costs 98 tokens per session (6,358 once invoked), scanned A, original, MIT.

A collection of commands for managing iOS Simulators and Android Emulators, which are virtual phones used to run and inspect apps on a computer.

In plain words
What is it for?
Use it to boot or stop a virtual device, install or launch an app, take screenshots, inspect the visible interface, open deep links, grant permissions, and manage device settings.
Why use it?
It removes the need to remember separate commands for starting devices, installing apps, checking the screen, changing settings, and reading logs.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the rn-dev-agent plugin — 11 skills, 16 commands, 5 agents, 6 hooks 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 skills/lykhoyda/rn-dev-agent/rn-device-control
Any agent
npx skills add Lykhoyda/rn-dev-agent --skill rn-device-control
Clone the repo
git clone --depth 1 https://github.com/Lykhoyda/rn-dev-agent

Made for: Claude Code, Codex.

Or install rn-dev-agent, the plugin that ships this one along with the rest of its 11 skills, 16 commands, 5 agents, 6 hooks.

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 rn-device-control

README.md
[![agentmods](https://agentmods.dev/badge/skills/lykhoyda/rn-dev-agent/rn-device-control.svg)](https://agentmods.dev/skills/lykhoyda/rn-dev-agent/rn-device-control)
Your own site
<a href="https://agentmods.dev/skills/lykhoyda/rn-dev-agent/rn-device-control"><img src="https://agentmods.dev/badge/skills/lykhoyda/rn-dev-agent/rn-device-control.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,358 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 $0.00098 $0.06358
Opus 5 $0.00049 $0.03179
Sonnet 5 $0.00020 $0.01272
Haiku 4.5 $0.00010 $0.00636

Measured 4d ago against content hash bba328589648, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rn-device-control 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.

packages/claude-plugin/skills/rn-device-control/SKILL.md · 535 lines

How it starts

The opening of the file, as written. The whole thing — 535 lines — stays where its author put it; the contents beside it link to each section on GitHub.

rn-device-control — Device Lifecycle and State Extraction

Commands for controlling iOS Simulator and Android Emulator, taking screenshots, reading UI state, and managing device settings. All commands run via bash.

See also: 3-Tier Interaction Model — when to use cdp_interact vs device_press vs Maestro.


iOS Simulator (simctl)

The raw commands below are non-authoritative diagnostics or manual maintenance. Never use the booted alias for plugin verification: require rn_session(action="status") and substitute its exact bound UDID. Prefer device_* tools, which enforce the session claim and return authority receipts.

Boot and Manage Devices

# List all available simulators
xcrun simctl list devices

# List only booted simulators
xcrun simctl list devices booted

# Boot a specific simulator by name or UDID
xcrun simctl boot "iPhone 16 Pro"
xcrun simctl boot <UDID>

# Shutdown a simulator
xcrun simctl shutdown booted

# Install an app (.app bundle)
xcrun simctl install booted /path/to/YourApp.app

# Uninstall an app
xcrun simctl uninstall booted com.example.app

# Launch an app
xcrun simctl launch booted com.example.app

# Terminate a running app
xcrun simctl terminate booted com.example.app

# Erase all content (reset to factory)
xcrun simctl erase booted

Deep Links

device_deeplink(url="myapp://home")
device_deeplink(url="myapp://product/123")
device_deeplink(url="myapp://checkout")

Prefer deep links over Maestro navigation flows — faster and more deterministic. On an open exact iOS session, device_deeplink automatically accepts the SpringBoard-owned Open confirmation and reports meta.openDialogTapped: true. If a URL was opened externally or the dialog is still visible, call device_accept_system_dialog(label="Open"); if it returns DIALOG_BUTTON_NOT_FOUND, retry with one of availableButtons. Never guess coordinates for a native system dialog.

Screenshots (prefer JPEG — 2x faster, good enough for AI analysis)

Read the full file on GitHub · 535 lines

Files

What ships with it

2 files 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.

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 · 535 lines · 98 tokens per session scan A bba328589648

Subscribe to this mod's changes

rn-device-control is a skill published in the GitHub repository Lykhoyda/rn-dev-agent (11 stars, last pushed today), licensed MIT. It adds 98 tokens to every session and 6,358 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

video-transcription

Transcribe video and audio files to SRT subtitle format with speaker diarization using the Soniox API. Use when the user wants to transcribe meeting recordings, videos, or audio files. Supports MKV, MP4, MOV, M4A, and MP3 files. Triggers on "/transcribe", "transcribe my meetings", "transcribe videos in /Movies"…

BlackBeltTechnology/pi-agent-dashboard · 97 tokens

podcast-generation

Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.

bytedance/deer-flow · 38 tokens

hive.image-generation

Required before calling imagegenerate. Create and edit images from a prompt — generate an image, make a picture / logo / illustration / icon / banner / poster / thumbnail / hero image / mockup / product shot / social graphic, or edit / restyle / combine existing images from reference images. Uses OpenAI gpt-image-2…

aden-hive/hive · 149 tokens

kungfu-agent-onboarding

Use when a user asks to understand, start, inspect, extend, or safely operate installed Kungfu; verify the installed pack, select one intent route, personalize the explanation, and propose one smallest safe next action.

kungfu-systems/kungfu · 49 tokens

with-frontmatter

Help an agent inspect a failed trace run, identify likely failure layers, and produce a short audit note.

kungfu-systems/kungfu · 0 tokens

minimal

Help an agent inspect a failed trace run, identify likely failure layers, and produce a short audit note.

kungfu-systems/kungfu · 0 tokens