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.
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 agentmods add skills/software-mansion/argent/argent-device-interactnpx skills add software-mansion/argent --skill argent-device-interactgit clone --depth 1 https://github.com/software-mansion/argentWrote 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/software-mansion/argent/argent-device-interact)<a href="https://agentmods.dev/skills/software-mansion/argent/argent-device-interact"><img src="https://agentmods.dev/badge/skills/software-mansion/argent/argent-device-interact.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.07045 |
| Opus 5 | $0.00036 | $0.03522 |
| Sonnet 5 | $0.00015 | $0.01409 |
| Haiku 4.5 | $0.00007 | $0.00705 |
Grade A, and why
argent-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 today.
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 — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unified tool surface
All interaction tools below accept a udid parameter and auto-dispatch iOS vs Android based on its shape (UUID → iOS simulator, chromium-cdp-<port> → Chromium (CDP) app, anything else → Android adb serial). You use the same tool names on every platform.
Chromium (CDP) app = any Chromium runtime exposing a Chrome DevTools Protocol endpoint: an Electron app (boot it with boot-device + electronAppPath), or any Chromium-family browser (Chrome/Brave/Edge) launched with --remote-debugging-port. The latter is auto-discovered by list-devices on port 9222 plus anything in ARGENT_CHROMIUM_PORTS. The same describe/tap/swipe/keyboard/screenshot surface drives all of them.
Multi-tab / windows (Chromium only): a Chromium device may have several tabs / BrowserWindows. Use chromium-tabs to list them (stable ids t1, t2, …, optional labels), open a new one, select which is active, or close one. Every other tool (describe, gesture-tap, screenshot, debugger-evaluate, open-url, …) acts on the active tab, so chromium-tabs action=select before driving a different tab. Note: a cross-process navigation (some redirects) can swap a tab's underlying CDP target — re-run chromium-tabs action=list to pick it up under a fresh id.
Cookies & storage (Chromium only): chromium-cookies reads/writes cookies via the Network domain (so HttpOnly cookies are visible): action=get (optionally scoped by url), set (name, value, + url/domain, optional secure/httpOnly/sameSite/expires), delete (name), clear (all). chromium-storage reads/writes Web Storage for the active page: store=local|session, action=get (one key or all entries), set, remove, clear. Both are per-origin / active-tab. Handy for seeding auth before a flow or asserting app state after one.
TV targets (Apple TV / Android TV) are not covered by this skill. A TV target is focus-driven, not touch-driven — the
gesture-*tools are the wrong tools for it. This applies to both Apple TV simulators (UUID-shaped, identical to iOS) and Android TV / leanback devices (serial-shaped, identical to a phone emulator). Iflist-devicestags your targetruntimeKind: "tv", stop and use theargent-tv-interactskill:describeto read focus,tv-remotefor remote / D-pad presses, andkeyboardto type.
Physical iPhones (an iOS entry with kind
"device") follow a different contract: automation is app-scoped and only a subset of these tools exists there. Use theargent-ios-device-interactskill instead.
For platform-specific caveats (Metro adb reverse, locked-screen describe errors, etc.), see § 9 Platform-specific notes at the bottom.
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.
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.
- today Changed · +2 lines 08145c501374
- 4d ago First seen · 398 lines · 73 tokens per session scan A 351e8aaba5f8
argent-device-interact is a skill published in the GitHub repository software-mansion/argent (2,372 stars, last pushed today), licensed Apache-2.0. It adds 73 tokens to every session and 7,045 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 2026-08-30.
Other skills, from other repositories
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…
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…
migrate-nativewind-to-uniwind
Migrate a React Native project from NativeWind to Uniwind. Use when the user wants to replace NativeWind with Uniwind, upgrade from NativeWind, switch to Uniwind, or mentions NativeWind-to-Uniwind migration. Handles package removal, config migration, Tailwind 4 upgrade, cssInterop removal, theme conversion, and all…
react-native-docs
Comprehensive React Native reference covering core components, APIs, styling, flexbox, navigation, networking, animations, platform-specific code, debugging, performance, TypeScript integration, Fast Refresh, environment setup, React fundamentals, running on devices, and the New Architecture (Fabric, JSI…
mobile
Mobile development with React Native, Flutter, and native patterns.
mobile-developer
Expert in React Native, Expo, and cross-platform mobile development.