control

A control skill for locally connected Android phones using OpenGUI screenshots and approved actions. It applies to requests involving phones, Android apps, mobile games, or multiple devices.

In plain words
What is it for?
Use it to control Android devices, interact with Android apps or games, and work with more than one connected phone.
Why use it?
It lets an agent handle phone tasks without requiring the user to mention OpenGUI by name.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/core-mate/opengui/control
Any agent
npx skills add Core-Mate/OpenGUI --skill control
Clone the repo
git clone --depth 1 https://github.com/Core-Mate/OpenGUI

Made for: Claude Code, Codex.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 656 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00055 $0.00656
Opus 5 $0.00028 $0.00328
Sonnet 5 $0.00011 $0.00131
Haiku 4.5 $0.00006 $0.00066

Measured 2d ago against content hash 080c819f6aac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

control 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 2d 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.

deepseek-harness-plugin/skills/control/SKILL.md · 32 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Files

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.

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. 2d ago First seen · 32 lines · 55 tokens per session scan A 080c819f6aac

Subscribe to this mod's changes

control is a skill published in the GitHub repository Core-Mate/OpenGUI (1,587 stars, last pushed 2d ago), with no licence file. It adds 55 tokens to every session and 656 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 2026-08-30.

Related

Other skills, from other repositories

autofish-control

Control Android devices with Autofish via the af CLI. Use this skill when you need reliable observe-act-verify loops, ref-based tapping, overlay management, screenshots, and recovery steps.

felinics/Autofish · 42 tokens

kuri-android

Use kuri-android to drive Android devices and emulators from the CLI via a native Zig adb wire-protocol client. Read the screen with state (foreground app plus every actionable element, with tap-ready coordinates), tap by selector (--label/--id/--class/--desc/--index) rather than raw coordinates, swipe (scroll)…

justrach/kuri · 198 tokens

kuri-ios

Use kuri-ios to drive iOS Simulators from the CLI — list sims, boot/shutdown, navigate Safari to URLs (openurl), launch and terminate apps by bundle id, capture PNG screenshots, list installed apps, and (on the Simulator only) tap, doubletap, longpress, swipe/pan, and type via native CGEvent into the Simulator window.…

justrach/kuri · 233 tokens

kuri-mobile

Umbrella skill for mobile device control in the kuri ecosystem. Points to kuri-ios (iOS Simulator + real-device listing) and kuri-android (native Zig adb client). Use this when the user asks about "mobile automation" generally, or hasn't specified a platform. For platform-specific work prefer the kuri-ios or…

justrach/kuri · 79 tokens

platform-web-ui

Use when the UI needs web-specific responsive layout, browser interaction patterns, accessibility behavior, or browser-based verification.

Kainiko943/beautiful-ui · 26 tokens

upgrade-browser

Upgrade browser versions (Chrome or Firefox) in the Flutter Web Engine and/or Framework tests. Use when asked to roll or upgrade Chrome or Firefox to a newer version.

flutter/flutter · 36 tokens