New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Agent Device

by gronxb in gronxb/codex-relay

Automates interactions for Apple-platform apps (iOS, tvOS, macOS) and Android devices.

Apache-2.0Auto-check passedMobile

Install Agent Device

skills CLI
$ npx skills add gronxb/codex-relay --skill agent-device -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install gronxb/codex-relay agent-device --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/gronxb/codex-relay.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/agent-device .claude/skills/agent-device && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agent-device
GitHub stars
679
Token cost
~1.8k tokens
SKILL.md length
973 words
Files
8 (incl. references)
Skills in repo
5
Repo updated
First seen
Licence
Apache-2.0

At a glance

Automates interactions for Apple-platform apps (iOS, tvOS, macOS) and Android devices.

  • Works in 7 steps: Load references/bootstrap-install.md and… → Use bootstrap first to confirm or… → Once the app session is open and stable,… → …
  • Navigating apps
  • SKILL.md covers Default operating rules, Default flow, QA modes and Required references, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Agent Device is an agent skill from gronxb/codex-relay. Automates interactions for Apple-platform apps (iOS, tvOS, macOS) and Android devices. Use when navigating apps, taking snapshots/screenshots, tapping, typing, scrolling, extracting UI info, or collecting logs, network inspection, and perf snapshots across mobile, TV, and desktop targets.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including reference files (for example `references/bootstrap-install.md`, `references/coordinate-system.md` and `references/debugging.md`).

It sits in Mobile, covering iOS development. It works with Android, iOS and macOS. The repository describes itself as: Use Codex from your phone while the real work stays on your computer. The licence is Apache-2.0.

When your agent uses it

  • Navigating apps
  • Taking snapshots/screenshots
  • Extracting UI info
  • Collecting logs

Example prompts

  • “Use the agent-device skill to automate interactions for Apple-platform apps (iOS, tvOS, macOS) and Android devices”
  • “/agent-device”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Load references/bootstrap-install.md and references/exploration.md before acting on a normal device task.
  2. Use bootstrap first to confirm or establish the correct target, app install, and open app session.
  3. Once the app session is open and stable, use exploration for inspection, interaction, and verification.
  4. Start with plain snapshot if the goal is to read or verify what is visible.
  5. Escalate to snapshot -i only if you need refs for interactive exploration or a requested action.
  6. Use get, is, or find before mutating the UI when a read-only command can answer the question.
  7. End by capturing proof if needed, then close.

What it can do on your machine

Read from SKILL.md and the folder at commit 2a0cca2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Device loads about 1.8k tokens when it runs, and up to ~16k if it reads all its reference files. Until then it costs about 76 tokens; SKILL.md has 973 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~76
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~16k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from gronxb/codex-relay at commit 2a0cca2, republished under its Apache-2.0 licence (© gronxb). 973 words, ~1,831 tokens.

Download SKILL.mdSave it as .claude/skills/agent-device/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
agent-device
description
Automates interactions for Apple-platform apps (iOS, tvOS, macOS) and Android devices. Use when navigating apps, taking snapshots/screenshots, tapping, typing, scrolling, extracting UI info, or collecting logs, network inspection, and perf snapshots across mobile, TV, and desktop targets.

agent-device

Use this skill as a router with mandatory defaults. Read this file first. For normal device tasks, always load references/bootstrap-install.md and references/exploration.md before acting. Use bootstrap to confirm or establish deterministic setup. Use exploration for UI inspection, interaction, and verification once the app session is open.

Default operating rules

  • Start conservative. Prefer read-only inspection before mutating the UI.
  • Start deterministic. If the app name, package, device, or session is uncertain, load bootstrap and discover them before interacting.
  • Use plain snapshot when the task is to verify what text or structure is currently visible on screen.
  • Use snapshot -i only when you need interactive refs such as @e3 for a requested action or targeted query. On iOS and Android, default snapshot output uses the same visible-first model: off-screen interactive content is exposed as discovery hints, not tappable refs.
  • Prefer diff snapshot after a nearby mutation when you only need to know what changed.
  • Avoid speculative mutations. You may take the smallest reversible UI action needed to unblock inspection or complete the requested task, such as dismissing a popup, closing an alert, or clearing an unintended surface.
  • In React Native dev or debug builds, check early for visible warning or error overlays, tooltips, and toasts that can steal focus or intercept taps. If they are not part of the requested behavior, dismiss them and continue. If you saw them, report them in the final summary.
  • In Metro-backed React Native dev loops, use agent-device metro reload for a JS app reload before falling back to open <app> --relaunch. It mirrors pressing r in the Metro terminal and preserves the native app process.
  • Do not browse the web or use external sources unless the user explicitly asks.
  • Re-snapshot after meaningful UI changes instead of reusing stale refs.
  • Treat refs in default snapshot output as actionable-now, not durable identities. If a target appears only in an off-screen summary, use scroll <direction> and re-snapshot until the target is visible.
  • Prefer @ref or selector targeting over raw coordinates.
  • Ensure the correct target is pinned and an app session is open before interacting.
  • Keep the loop short: open -> inspect/act -> verify if needed -> close.

Default flow

  1. Load references/bootstrap-install.md and references/exploration.md before acting on a normal device task.
  2. Use bootstrap first to confirm or establish the correct target, app install, and open app session.
  3. Once the app session is open and stable, use exploration for inspection, interaction, and verification.
  4. Start with plain snapshot if the goal is to read or verify what is visible.
  5. Escalate to snapshot -i only if you need refs for interactive exploration or a requested action.
  6. Use get, is, or find before mutating the UI when a read-only command can answer the question.
  7. End by capturing proof if needed, then close.

QA modes

Required references

  • For every normal device task, after reading this file, load references/bootstrap-install.md first, then references/exploration.md, before acting.
  • Use bootstrap to confirm or establish deterministic setup, especially in sandbox or cloud environments.
  • Use exploration once the app session is open and stable.
  • Load additional references only when their scope is needed.
Show full SKILL.md (431 more words)Show less

Decision rules

  • Use plain snapshot when you need to verify whether text is visible.
  • Use snapshot -i mainly for interactive exploration and choosing refs.
  • Use diff snapshot for compact post-action verification; use snapshot --diff when that alias is easier to discover from snapshot help.
  • Use get, is, or find when they can answer the question without changing UI state.
  • Use fill to replace text.
  • Use type to append text.
  • Do not write type @eN "text". Use fill @eN "text" to target a field directly, or press @eN then type "text" when the field already has focus and you want append semantics.
  • If the on-screen keyboard blocks the next step, prefer keyboard dismiss over navigation. On iOS, keep an app session open first; keyboard status|get remains Android-only.
  • When a task asks to "go back", use plain back for predictable app-owned navigation and reserve back --system for platform back gestures or button semantics.
  • Use type --delay-ms or fill --delay-ms for debounced search fields that drop characters when typed too quickly.
  • If there is no simulator, no app install, or no open app session yet, switch to bootstrap-install.md instead of improvising setup steps.
  • Use the smallest unblock action first when transient UI blocks inspection, but do not navigate, search, or enter new text just to make the UI reveal data unless the user asked for that interaction.
  • In React Native dev or debug apps, treat visible warning or error overlays as transient blockers unless the user is explicitly asking you to diagnose them. Dismiss them when safe, then continue the requested flow.
  • For React Native code changes where the app is already connected to Metro, prefer agent-device metro reload, then wait and re-snapshot. Use open <app> --relaunch only when Metro reload does not reconnect or native startup state must reset.
  • Do not use external lookups to compensate for missing on-screen data unless the user asked for them.
  • If the needed information is not exposed on screen, say that plainly instead of compensating with extra navigation, text entry, or web search.
  • Prefer @ref or selector targeting over raw coordinates.

Additional references

  • Need logs, network, alerts, permissions, or failure triage: references/debugging.md
  • Need screenshots, diff, recording, replay maintenance, or perf data: references/verification.md
  • Need desktop surfaces, menu bar behavior, or macOS-specific interaction rules: references/macos-desktop.md
  • Need remote HTTP transport, connect --remote-config, or tenant leases on a remote macOS host: references/remote-tenancy.md This includes remote React Native runs where agent-device now prepares Metro locally and manages the local Metro companion tunnel automatically.
  • Need the React Native component tree, props, state, hooks, or render profiling: use agent-device react-devtools ... and the react-devtools skill.

© gronxb, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (references) in .agents/skills/agent-device of gronxb/codex-relay.

  • SKILL.md
  • references/bootstrap-install.md
  • references/coordinate-system.md
  • references/debugging.md
  • references/exploration.md
  • references/macos-desktop.md
  • references/remote-tenancy.md
  • references/verification.md

Open the folder on GitHubat commit 2a0cca2

Compare with similar skills

Agent Device next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent Device compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Device this skillgronxb/codex-relay679—~1.8kAutomated safety check: PassApache-2.0
Phoneagentrounak/PhoneAgent798—~2.2kAutomated safety check: PassMIT
Ksafeioannisa/KSafe332—~17kAutomated safety check: PassApache-2.0
Agent DeviceCherryHQ/cherry-studio-app4k—~342Automated safety check: PassAGPL-3.0
Agent Devicecallstackincubator/agent-skills1.7k—~1.2kAutomated safety check: PassMIT
Eas Simulatorexpo/skills2.7k—~6.6kAutomated safety check: NotesMIT

Similar skills

  • Phoneagent

    rounak/PhoneAgent

    Control a connected iPhone, iOS simulator, Android emulator, or Android device from macOS through PhoneAgent's JSON-RPC bridge.

    798 GitHub stars~2.2k tokensUpdated 1 mo ago
    MobileAuto-check passed

  • Ksafe

    ioannisa/KSafe

    Required before any reply that touches KSafe (by ksafe(...), ksafe.get/put, :ksafe-compose, :ksafe-biometrics), even a 'can KSafe do X?' question or a one-line change that looks like plain Kotlin.

    332 GitHub stars~17k tokensUpdated 5 days ago
    MobileAuto-check passed

  • Agent Device

    CherryHQ/cherry-studio-app

    Automates Apple-platform apps (iOS, tvOS, macOS) and Android devices.

    4k GitHub stars~342 tokensUpdated today
    MobileAuto-check passed

  • Agent Device

    callstackincubator/agent-skills

    Official

    Automates interactions for Apple-platform apps (iOS, tvOS, macOS) and Android devices.

    1.7k GitHub stars~1.2k tokensUpdated 2 days ago
    MobileAuto-check passed

  • Eas Simulator

    expo/skills

    Official

    Run and control a user's app on a remote iOS/Android simulator hosted on EAS cloud.

    2.7k GitHub stars~6.6k tokensUpdated yesterday
    MobileAuto-check: notes

  • Tauri Packaging

    bkywksj/knowledge-base

    Tauri 打包与分发技能,指导桌面端（Windows/macOS/Linux）与移动端（Android/iOS）的构建、签名和分发。

    330 GitHub stars~3.3k tokensUpdated 6 days ago
    MobileAuto-check passed

More from gronxb/codex-relay

  • Agent Cdp

    gronxb/codex-relay

    Chrome DevTools Protocol CLI workflow for runtime, console, network, trace, memory, and JavaScript CPU profiling analysis.

    679 GitHub stars~956 tokensUpdated yesterday
    Auto-check passed

  • Hot Updater

    gronxb/codex-relay

    Set up, upgrade, operate, and diagnose Hot Updater projects.

    679 GitHub stars~2.7k tokensUpdated yesterday
    Auto-check passed

  • Hot Updater QA Ship

    gronxb/codex-relay

    Deploy the current Modex iOS app version with Hot Updater for QA-only delivery.

    679 GitHub stars~818 tokensUpdated yesterday
    Auto-check passed

  • Deploy iOS

    gronxb/codex-relay

    Deploy the Modex/Codex Relay mobile app iOS OTA update with Hot Updater.

    679 GitHub stars~382 tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Agent Device

What does Agent Device do?

Automates interactions for Apple-platform apps (iOS, tvOS, macOS) and Android devices. Agent Device is an agent skill from gronxb/codex-relay. Automates interactions for Apple-platform apps (iOS, tvOS, macOS) and Android devices.

When should I use Agent Device?

Agent Device fits situations like: navigating apps; taking snapshots/screenshots; extracting UI info; collecting logs.

How do I install Agent Device in Claude Code?

Run `npx skills add gronxb/codex-relay --skill agent-device -a claude-code`. Or copy the skill folder (.agents/skills/agent-device in gronxb/codex-relay) into .claude/skills/agent-device in your project. Claude Code loads it when a task matches its description.

How do I install Agent Device in Codex?

Run `npx skills add gronxb/codex-relay --skill agent-device -a codex`. Or copy the skill folder (.agents/skills/agent-device in gronxb/codex-relay) into .agents/skills/agent-device in your project. Codex loads it when a task matches its description.

Can I use Agent Device in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add gronxb/codex-relay --skill agent-device -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-device, .gemini/skills/agent-device, .github/skills/agent-device and .opencode/skills/agent-device in your project.

What does Agent Device need to run?

SKILL.md names no scripts, command-line tools or credentials: Agent Device is instructions for the agent only.

Does Agent Device access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Agent Device safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Agent Device use?

Agent Device is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent Device use?

About 1.8k tokens (SKILL.md is roughly 7.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 15k tokens, read only when the agent opens those files.

What are the alternatives to Agent Device?

Skills that share tags, products or a category with Agent Device: Phoneagent (rounak/PhoneAgent, 798 stars), Ksafe (ioannisa/KSafe, 332 stars), Agent Device (CherryHQ/cherry-studio-app, 4k stars) and Agent Device (callstackincubator/agent-skills, 1.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Device?

gronxb (a GitHub user) maintains it in gronxb/codex-relay, which has 679 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 7, 2026.

Source: gronxb/codex-relay on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.