argent-ios-device-interact

argent-ios-device-interact is a skill for Claude Code, Codex from software-mansion/argent. It costs 59 tokens per session (578 once invoked), scanned A, original, Apache-2.0.

A guide for controlling a real, cable-connected iPhone through Argent's automation tools. It describes supported actions, screen observation, app launching, gestures, buttons, and device-specific limits.

In plain words
What is it for?
Use it to launch or restart apps, inspect screens, take screenshots, tap, swipe, type, press hardware buttons, and compare screenshots on a physical iPhone.
Why use it?
It helps automation stay in sync with what is actually on the phone and explains when an action can change the screen or requires the app to be brought forward.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to launch or restart apps, inspect screens, take screenshots, tap…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/software-mansion/argent/argent-ios-device-interact
About the project

Argent is a toolkit that lets an AI assistant control and inspect iOS, Android, TV, Electron, and Chromium applications through simulators, emulators, physical devices, or desktop connections. It is for developers who want an agent to interact with interfaces, reproduce issues, test features, debug applications, or run profiling tasks. The catalogue add-ons expose Argent's device-control and development workflows to coding agents.

software-mansion/argent · 2,387 stars · on GitHub · argent.swmansion.com

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 software-mansion/argent --skill argent-ios-device-interact
Clone the repo
git clone --depth 1 https://github.com/software-mansion/argent

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.

agentmods badge for argent-ios-device-interact

README.md
[![agentmods](https://agentmods.dev/badge/skills/software-mansion/argent/argent-ios-device-interact.svg)](https://agentmods.dev/skills/software-mansion/argent/argent-ios-device-interact)
Your own site
<a href="https://agentmods.dev/skills/software-mansion/argent/argent-ios-device-interact"><img src="https://agentmods.dev/badge/skills/software-mansion/argent/argent-ios-device-interact.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 578 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.00578
Opus 5 $0.00030 $0.00289
Sonnet 5 $0.00012 $0.00116
Haiku 4.5 $0.00006 $0.00058

Measured 3d ago against content hash 47fd418bf46d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

argent-ios-device-interact 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 3d 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/skills/skills/argent-ios-device-interact/SKILL.md · 21 lines

How it starts

The opening of the file, as written. The whole thing — 21 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Physical iPhone interaction

Read this only for a physical iPhone. argent-device-interact still applies for everything not listed here.

Contract

  • Observation never changes the screen; mutation may. describe and await-ui-element fail on a backgrounded target instead of re-fronting it; await-screen-idle returns settled: false with no reason. The first describe within a second of button home can still return the old tree; describe again. Gestures and keyboard re-front it and return reactivated: true; re-describe before the next step.
  • launch-app, open-url and restart-app set the app under automation; reinstall-app clears it; a tool-server restart forgets it: launch again.
  • Each tool's description states its own hardware limits (named keys, gesture-custom shapes, buttons, edge swipes, tap counts). A gated tool fails with a bare not supported on ios device: the fix is in the list below, not in the error.

Tools on hardware

  • Only these exist: list-devices, launch-app, restart-app, reinstall-app, open-url, describe, screenshot, screenshot-diff, gesture-tap, gesture-swipe, gesture-custom, button (home, volumeUp, volumeDown, actionButton on models that have one), keyboard, await-ui-element, await-screen-idle, run-sequence, the flow tools, stop-simulator-server and stop-all-simulator-servers (session end). Every other device tool fails with not supported on ios device.
  • No two-finger gestures, rotate, shake, paste, settings-permissions, screen recording, debugger-*, react-profiler-*, native-profiler-*, native-*, boot-device: drive the app's own zoom and rotate UI with taps and drags, move the phone by hand, type with keyboard, change permissions in the phone's Settings, and debug, profile or record on a simulator.
  • gesture-swipe: durationMs sets drag speed, not time; momentum:false only rests 300 ms at the end, no damping. open-url https lands in Safari, never in the app that owns the link: pass bundleId.

Read the full file on GitHub · 21 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. 3d ago First seen · 21 lines · 59 tokens per session scan A 47fd418bf46d

Subscribe to this mod's changes

argent-ios-device-interact is a skill published in the GitHub repository software-mansion/argent (2,387 stars, last pushed 2d ago), licensed Apache-2.0. It adds 59 tokens to every session and 578 once invoked, about $0.0003 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 2026-09-03.

Related

Other skills, from other repositories

Detox Mobile Testing

Gray-box end-to-end testing for React Native apps with Detox. Covers .detoxrc.js configuration, build and test commands, matchers, device.launchApp control, automatic synchronization, and macOS CI pipelines.

PramodDutta/qaskills · 48 tokens

maestro-mobile-testing

Maestro mobile E2E testing patterns for React Native/Expo apps: YAML test flows, testID selectors, adaptive auth state, optimistic update verification, GraalJS scripting, cross-platform stability, CI/CD integration, Maestro Cloud, and MCP server integration.

tovimx/maestro-mobile-testing-skill · 56 tokens

truesheet-usage

Consumer-side guide for integrating @lodev09/react-native-true-sheet into a React Native app. Use this skill whenever the user wants to add, configure, control, or debug a bottom sheet using TrueSheet — including ref-based sheets, named global sheets, web support with TrueSheetProvider/useTrueSheet, React Navigation…

lodev09/react-native-true-sheet · 169 tokens

mobile-automation

Control Android and iOS devices, emulators and simulators — launch apps, tap, swipe, type, take screenshots, read the accessibility tree. Use when a task involves a mobile device or app, mobile UI testing, or reproducing a bug on a phone.

mobile-next/mobile-mcp · 58 tokens

uniwind

Uniwind — Tailwind CSS v4 styling for React Native. Use when adding, building, or debugging components in a React Native project that uses Uniwind classNames. Covers setup, Metro config, global.css, theming, className props, accent- color props, platform/data/state/responsive variants, CSS variables, custom utilities…

uni-stack/uniwind · 130 tokens

Appium Mobile Testing

Mobile application testing skill using Appium for iOS and Android, covering device capabilities, selectors, gestures, and cross-platform testing strategies.

PramodDutta/qaskills · 32 tokens