argent-tv-interact

argent-tv-interact is a skill for Claude Code, Codex from software-mansion/argent. It costs 107 tokens per session (1,992 once invoked), scanned A, original, Apache-2.0.

A toolset for controlling and inspecting Apple TV, Android TV, and Amazon Fire TV applications with a remote-style interface.

In plain words
What is it for?
Use it to start a TV app, navigate with the D-pad, type, take screenshots, inspect focus, and debug JavaScript on Fire TV.
Why use it?
TV apps are controlled by focus and directional navigation rather than touch, so testing them requires checking what is selected and moving through the interface carefully.

Skill for Claude CodeCodex

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

Good fit Use it to start a TV app, navigate with the D-pad, type, take screenshots, inspect focus, and debug JavaScript on Fire TV.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/software-mansion/argent/argent-tv-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 · 2,388 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-tv-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-tv-interact

README.md
[![agentmods](https://agentmods.dev/badge/skills/software-mansion/argent/argent-tv-interact.svg)](https://agentmods.dev/skills/software-mansion/argent/argent-tv-interact)
Your own site
<a href="https://agentmods.dev/skills/software-mansion/argent/argent-tv-interact"><img src="https://agentmods.dev/badge/skills/software-mansion/argent/argent-tv-interact.svg" alt="Measured on agentmods" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,992 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. Third-party audits
  • Socket pass 18 Aug 2026
  • Snyk pass 18 Aug 2026
How audits are shown
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 $0.00107 $0.01992
Opus 5 $0.00053 $0.00996
Sonnet 5 $0.00021 $0.00398
Haiku 4.5 $0.00011 $0.00199

Measured 7d ago against content hash c510bd082a7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

argent-tv-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 7d 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-tv-interact/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Argent TV (Apple TV + Android TV + Fire TV)

Critical

  • A TV is focus-driven, not touch-driven. Drive every interaction with describe + tv-remote + keyboard; never use gesture-* / coordinate taps — they don't apply on any TV platform.
  • Always describe before navigating to find the live cursor and your target — never guess focus from a screenshot. The cursor is the focused element; on Vega the toolkit often leaves focused false and marks the highlighted item [selected], so treat [selected] as the cursor when nothing reports [focused].
  • Pass the udid from list-devices — an Apple TV simulator UDID or an Android TV / Vega serial. Dispatch is automatic from the id; the same tools drive all three.

The navigation loop

  1. describe — find the cursor and your target (returns the focused element + all focusable ones, not a tap tree).
  2. tv-remote — move focus toward the target. Prefer one call with a path ending in select, e.g. {button:["down","right","select"]}; count rows/columns from the frames to build the path.
  3. describe again to confirm. On a miss, repeat.

Tools

  • describe {udid} — focus view: the focused / [selected] element + focusable elements with labels and normalized frames. The discovery tool — call before and after navigating. Empty tree → see the per-platform notes.
  • tv-remote {udid, button} — D-pad / remote. button is one key or a whole path (run in one call). Keys: up/down/left/right, select, back, menu, home, playPause, plus media keys rewind/fastForward/next/previous/volumeUp/volumeDown/mute. Single: {button:"down"}; repeat: {button:"down", repeat:3}; path: {button:["up","right","select"]}.
  • keyboard {udid, text} — type into the focused field (focus it with tv-remote first). One call carries text or key, never both — to type and then press a key, send two keyboard steps in one run-sequence. Named key presses (e.g. {key:"enter"}) work on Vega; on Apple TV / Android TV move focus with tv-remote instead.
  • launch-app / restart-app / reinstall-app {udid, bundleId}bundleId from the app manifest. Vega reinstall-app takes appPath = a .vpkg.
  • screenshot {udid, scale?} — Apple TV via xcrun simctl io (downscaled); Android TV / Vega host-side via adb / screencap.

Read the full file on GitHub · 71 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. 7d ago First seen · 71 lines · 107 tokens per session scan A c510bd082a7d

Subscribe to this mod's changes

argent-tv-interact is a skill published in the GitHub repository software-mansion/argent (2,388 stars, last pushed today), licensed Apache-2.0. It adds 107 tokens to every session and 1,992 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

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

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

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

react-native

Use when writing the JS/TS inside a React Native or Expo app — screens, Expo Router navigation, lists, Reanimated gestures, platform forks, offline state, native modules — or killing jank and render storms. NOT eas build/submit/OTA/config-plugin (that is expo), NOT a Dart app (that is flutter), NOT web React/DOM (that…

ericrisco/rsc-harness · 90 tokens

react-native-expert

Expert in React Native, cross-platform mobile development, native modules, and performance optimization. Use when the user mentions mobile, JavaScript, TypeScript, cross platform, iOS, or Android, or when the task involves React Native Architecture, Component Types, Hooks Essentials, or Navigation.

personamanagmentlayer/pcl · 62 tokens

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…

uni-stack/uniwind · 82 tokens