claude

mobile-agent

What fails silently when an agent works on a mobile app: device layer (adb, emulator, UI dumps, mirroring a phone) and bundler layer (Expo, Metro, prebuild). Narrow PreToolUse guards that warn and never block, and the Maestro MCP server for driving UI flows on a device.

0 on GitHubby 4nrryv0.5.0MITupdated yesterdaydevelopment
/

Plugin mobile-agent from marketplace 4nrry in 4nrry/agent-plugins. Commands read from the repo's manifest — today.

This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.

What it installs

Skills (5)

  • android-device

    Covers what fails silently when an agent drives an Android device or emulator — UI dumps that serve stale state, GL surfaces invisible to accessibility, screenshots that exhaust session memory, adb tunnels that drop on their own, and processes that belong to someone else. Use before automating any o

  • android-mirror

    Mirrors and controls a physical Android device's screen on a Linux PC with scrcpy over the wireless debugging already connected, without installing a second adb that drops the tunnels. Covers what does not work (KDE Connect, Phone Link, DeX for Linux), installing without shadowing the SDK's adb, pro

  • expo-metro

    Covers what fails silently in an Expo / React Native project — a prebuild that does not run and says nothing, a Metro serving another checkout's bundle, a missing node_modules that breaks only the bundler while tsc and jest pass, native modules that never reached the device, and EXPO_PUBLIC_ variabl

  • maestro

    Writing and running Maestro UI flows on a phone or emulator, through the Maestro MCP server or the CLI — reading the screen before writing selectors, env defaults inside flows, clearState and what it wipes, loading a dev client, a device listed twice, and finding why a step failed. Use when asked to

  • preflight

    Checks what is already running before starting an emulator, bundler or adb tunnel — devices, reverse tunnels, bundler ports, AVD locks, free memory — and which checkout owns each process. Read-only. Use before starting mobile tooling, especially with several checkouts, worktrees or agent sessions on

MCP servers (1)

  • maestro

    runs: maestro mcp

Hooks (12)

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}"/hooks/guard-adb-kill-server.sh

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}"/hooks/guard-pkill.sh

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}"/hooks/guard-pkill.sh

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}"/hooks/guard-uiautomator.sh

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}"/hooks/guard-expo-run.sh

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}"/hooks/guard-expo-run.sh

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}"/hooks/guard-apt-adb.sh

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}"/hooks/guard-apt-adb.sh

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}"/hooks/guard-apt-adb.sh

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}"/hooks/guard-apt-adb.sh

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}"/hooks/guard-scrcpy.sh

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}"/hooks/guard-scrcpy.sh

View source on GitHub

More from 4nrry/agent-plugins

All 8 plugins →

Media production by an agent on a machine with an 8 GB GPU and commercial licensing, one skill per modality with rules that hold for any model: image and video generation, image retouching, transparent looping cut-outs for web pages, a mechanical check of a web page, voice-over at -16 LUFS, music and sound, stock media with per-item licenses, video composed as code, editing finished video, a 3D product turntable, scripted 3D scenes with characters in Blender, and sourcing rules for factual videos. Two hooks warn: where vipsthumbnail -o really writes, and when Kinocut runs before any skill is loaded.

13 skills · 1 MCP server · hooks

0

homelab

claude

Software you maintain yourself on a Linux box, where the official docs stop: a Palworld dedicated server (the config it erases on shutdown), WireGuard through NetworkManager (the IPv6 leak that passes the IP test), and tarball installs (one versioned layout; self-updating apps stay out of /opt).

3 skills

0

Rules for multi-agent work: model routing per phase, fan-out sizing, closed output schemas and citation checks, with CLI workers for search and extract and hooks that load the rules and check routing at dispatch.

1 skill · hooks

0

crew

claude

Another vendor's agent CLI as an isolated subagent, from any host: ask a read-only question or hold a multi-turn conversation (agy, opencode, Codex, Grok, Hermes, Copilot, Cursor, Muse, Kimi, or Claude Code from another host), get a second opinion on a diff, or delegate one coding slice to agy, opencode, Copilot, Codex, Grok, Cursor or Claude Code under the worker CLI's own hooks and a mechanical gate. Tiers (cheap, mid, top) map to a model and effort per backend. The verdict never reads the CLI's exit 0 as success.

1 skill · hooks

0

Pins the installed game's version before the agent answers from training memory: a UserPromptSubmit hook reads Steam appmanifests and injects appid, buildid, update date and the patch-notes URL, and a skill routes the question and weighs sources against the last patch.

1 skill · hooks

0

agents-md

claude

Writes, trims and audits a repository's AGENTS.md: what belongs in it, what to cut, size limits per tool, and a stdlib checker for missing commands, dead paths, oversize files and a CLAUDE.md that hides AGENTS.md.

1 skill

0

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

slidev

claude

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

slidevjs/slidev 49,452

Maintain mobile-agent?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins8 plugins