Agent skill

Game Automation

by rehan-remade in rehan-remade/universal-modder

Launch, see and drive a real game so an agent can test its own mods.

MITAuto-check passedSecurity

Install Game Automation

skills CLI
$ npx skills add rehan-remade/universal-modder --skill game-automation -a claude-code

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

GitHub CLI
$ gh skill install rehan-remade/universal-modder game-automation --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/rehan-remade/universal-modder.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/game-automation .claude/skills/game-automation && 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
game-automation
GitHub stars
6.5k
Token cost
~1.9k tokens
SKILL.md length
843 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Launch, see and drive a real game so an agent can test its own mods.

  • A mod must be verified in game
  • SKILL.md covers Windows (native or from WSL):…, Make the window predictable, Better than clicking: a… and Crashes and cleanup, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Navigating menus automatically

What it does

Game Automation is an agent skill from rehan-remade/universal-modder. Launch, see and drive a real game so an agent can test its own mods. Covers launching via Steam or the exe, windowed mode at a fixed size, screenshots of the game window (GPU-safe capture), clicking and typing into menus, holding keys, relative mouse, crash-reporter cleanup, killing by PID, reading logs, scripted test scenes, and an in-game JSON bridge that lets an agent observe and act. Windows-first (also from WSL), with notes for Linux and macOS. Use when a mod must be verified in game, when navigating menus…

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Security. It works with Linux and macOS. The repository describes itself as: Point Claude at any game. Skills, tools and the fal MCP that let Claude Code mod almost any PC game you own: recon, reverse engineering, fal-generated art/3D/audio, in-game… The licence is MIT.

When your agent uses it

  • A mod must be verified in game
  • Navigating menus automatically
  • Building a repeatable test

Example prompts

  • “/game-automation”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 50af8bd. 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 (its code samples are bash).

    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

Game Automation loads about 1.9k tokens when it runs. Until then it costs about 149 tokens; SKILL.md has 843 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~149
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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 rehan-remade/universal-modder at commit 50af8bd, republished under its MIT licence (© rehan-remade). 843 words, ~1,859 tokens.

Download SKILL.mdSave it as .claude/skills/game-automation/SKILL.md (or your agent's skills folder).
name
game-automation
description
Launch, see and drive a real game so an agent can test its own mods. Covers launching via Steam or the exe, windowed mode at a fixed size, screenshots of the game window (GPU-safe capture), clicking and typing into menus, holding keys, relative mouse, crash-reporter cleanup, killing by PID, reading logs, scripted test scenes, and an in-game JSON bridge that lets an agent observe and act. Windows-first (also from WSL), with notes for Linux and macOS. Use when a mod must be verified in game, when navigating menus automatically, or when building a repeatable test or demo scene.

Game automation: the agent's hands and eyes

The real game is the oracle. The loop is launch → navigate → set up the scene → act → screenshot and read logs → decide. Build it once per game, then every change you make can be checked in a minute.

Windows (native or from WSL): um win

bash
um win setup                                   # once: PowerShell tools + an ffmpeg with gfxcapture, picks NVENC/AMF/QSV/x264
um win ps                                      # windowed processes: pid, name, title
um win launch --steam 105600                   # or: um win launch "C:\Games\Foo\Foo.exe" -- -windowed
um win shot --exe Terraria.exe shot.png --scale 0.33   # full frame + a 1/3 copy that's cheap to look at
um win drive --proc Terraria "focus" "click 640 360" "key 0x1B" "type hello" "hold 0x44 1500"
um win drive --proc Terraria idle              # seconds since the user last touched mouse/keyboard
um win kill <pid>                              # exact PID only
um win reg get "HKCU\Software\..."             # registry (reg set backs the key up first)

From Python (for longer scripts), from um.win import Drive, shot, Recorder, then d = Drive("AoE2DE_s"), d.focus(), d.click(x, y), d.key("0x0D").

WinDrive commands (um/ps1/WinDrive.ps1; stdin protocol, one reply per line). Coordinates are in the game window's client area.

  • Mouse: move x y, click x y [right], mdown/mup, drag x0 y0 x1 y1, rel dx dy (FPS cameras / raw input), wheel 120.
  • Keyboard: key <vk> [tap|down|up], hold <vk> <ms>, type <text>, scanmode on (DirectInput / raw-input games that ignore virtual-key events).
  • Window: focus, rect, size <w> <h> (sets the client size), title, fg, idle, untop.
  • Virtual-key codes: Esc 0x1B, Enter 0x0D, Space 0x20, W/A/S/D 0x57/0x41/0x53/0x44, F1 0x70, Shift 0x10, Ctrl 0x11, arrows 0x25-0x28.

Rules of the road

  • Never focus a game with an online mode while the human is typing. It happened with GTA V: the agent focused GTA to click Story Mode, the human's keystrokes hit GTA's landing page, and GTA warned about "accessing GTA Online servers with an altered version". ScriptHookV blocked it; don't rely on that. Check idle, ask the human to click, and launch with the anti-cheat off so online can't start. See knowledge/techniques/driving-real-games-safely.md.
  • Input only goes to the game. WinDrive refuses to send while another app is in the foreground. The one exception is when nothing is and the cursor is over the game, which windowed games cause by dropping the foreground on clicks.
  • The user may be at the PC. If idle is under a minute, ask before driving, and keep sessions short. Unattended runs are fine once the user says so.
  • Screenshots cost tokens. Look at --scale 0.33 copies. Multiply coordinates back ×3 for clicks, and keep a table of menu click points in MODLOG.md, measured once.
  • Why gfxcapture: GPU-rendered games come out black with GDI capture. gfxcapture (Windows.Graphics.Capture) grabs one window's real frames, even when covered. It can't capture minimized windows.
  • HDR displays: with Windows Auto HDR on for an SDR game, captures come out washed out (2-3x brighter, cyan-shifted), so colours can't be judged. um win shot/record warn when it's on; turn it off for the game while capturing (Settings > System > Display > Graphics > the game > Auto HDR), and back on after if the user wants.

Make the window predictable

  • Windowed mode at a fixed client size. Every game hides this setting somewhere:
    • an ini ([/Script/Engine.GameUserSettings] in UE GameUserSettings.ini, Unity's Screenmanager Fullscreen mode / Resolution registry values under HKCU\Software\<company>\<product>);
    • a launch flag (-windowed -w 1920 -h 1080, Unity -screen-fullscreen 0 -screen-width 1920 -screen-height 1080, Source -sw -w 1920 -h 1080);
    • or the game's own registry (AoE2: Mode Display 0 + Windowed Width/Height).
    • um win drive --proc X "size 1920 1080" also resizes most windowed games.
  • Skip intros: launch flags (-skipintro, -nosplash, Unity -popupwindow), or delete/rename intro videos in a copy of the game.
  • Jump straight in: loader flags (tModLoader -skipselect Player:World), a save made for testing, scenario auto-load, a dev console command.
  • Background throttling: many games throttle or pause unfocused. Find the setting (Terraria: Main.instance.InactiveSleepTime = TimeSpan.Zero; Unity: Application.runInBackground = true; UE: t.IdleWhenNotForeground 0).
Show full SKILL.md (299 more words)Show less

Better than clicking: a scripted scene or a bridge

  • Chat or console commands in your mod give items, spawn enemies and teleport. They make tests one line (/arsenal, /mothership).
  • Test scenes: a mod-side timeline (spawn waves at frame N, fire at N+30), a scenario with triggers (AoE2 via AoE2ScenarioParser), a dedicated test world with a pristine backup.
  • Agent bridge: a JSON-lines socket inside the mod on 127.0.0.1 (see examples/terraria-tmodloader/reference/AgentBridge.cs).
    • Commands like observe (menu options or world state as text), click <id>, controls, step.
    • Handle every request on the game's main thread after an update, so replies are consistent.
    • Read menus generically from the UI tree, so the agent sees what a player would. Leave destructive buttons (delete) out.
    • An agent can then play without pixels at all.
  • Out-of-process backend: keep the in-game part thin and put the brains outside (HTTP/file-drop). That pattern scales to AI NPCs and cross-game mashups.

Crashes and cleanup

  • Crash reporters (BugSplat BsSndRpt64.exe, CrashReportClient.exe, UnityCrashHandler64.exe) can linger and make Steam say "already running". um win ps to spot them, um win kill <pid> to clear them.
  • Never pkill -f or wildcard taskkill /IM. The pattern can match your own shell or other apps.
  • After a crash, read the loader or game log first (the mod-any-game skill lists them), then the Windows Event Viewer (Application log) for native crashes.

Linux and macOS

  • Linux (X11): xdotool search --name "Game" windowactivate --sync key Escape, xdotool mousemove --window $W 640 360 click 1. Screenshots: import -window $(xdotool search --name Game) shot.png, or ffmpeg x11grab.
  • Linux (Wayland): ydotool + grim. Proton games are Windows games under Wine: launch options (WINEDLLOVERRIDES, PROTON_LOG=1) go in Steam.
  • macOS: screencapture -l <windowid> shot.png (window id via GetWindowID or AppleScript), osascript / cliclick for input. Input and screen recording need Accessibility and Screen Recording permission for the terminal.

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

Files

Just SKILL.md in skills/game-automation of rehan-remade/universal-modder.

Open the folder on GitHubat commit 50af8bd

Compare with similar skills

Game Automation 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.

Game Automation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Game Automation this skillrehan-remade/universal-modder6.5k—~1.9kAutomated safety check: PassMIT
Ctf Cryptoljagiello/ctf-skills3.4k—~11kAutomated safety check: NotesMIT
Os Hardware Inventorycdxgen/cdxgen1.1k—~1.5kAutomated safety check: PassApache-2.0
Forensics OsqueryAgentSecOps/SecOpsAgentKit2201 repos~4.9kAutomated safety check: NotesCustom licence
Bumblebeesickn33/agentic-awesome-skills47k1 repos~2.5kAutomated safety check: NotesMIT
Performing Memory Forensics With Volatility3 Pluginsmukul975/Anthropic-Cybersecurity-Skills34k—~2.1kAutomated safety check: PassApache-2.0

Similar skills

  • Ctf Crypto

    ljagiello/ctf-skills

    Provides cryptography attack techniques for CTF challenges. An agent skill from ljagiello/ctf-skills.

    3.4k GitHub stars~11k tokensUpdated 27 days ago
    SecurityAuto-check: notes
  • Collects live operating-system inventory (OBOM) and host hardware inventory (HBOM) as CycloneDX documents using the cdxgen obom and hbom commands, including osquery-backed runtime artifacts, Linux…

    1.1k GitHub stars~1.5k tokensUpdated today
    SecurityAuto-check passed
  • Forensics Osquery

    AgentSecOps/SecOpsAgentKit

    SQL-powered forensic investigation and system interrogation using osquery to query operating systems as relational databases.

    220 GitHub starsUsed in 1 repo~4.9k tokens
    SecurityAuto-check: notes
  • Bumblebee

    sickn33/agentic-awesome-skills

    Run Bumblebee supply-chain inventory and exposure scans on macOS/Linux to detect compromised packages, extensions, and MCP host configs.

    47k GitHub starsUsed in 1 repo~2.5k tokens
    SecurityAuto-check: notes
  • Performing Memory Forensics With Volatility3 Plugins

    mukul975/Anthropic-Cybersecurity-Skills

    Analyze memory dumps using Volatility3 plugins to detect injected code, rootkits, credential theft, and malware artifacts in Windows, Linux, and macOS memory images.

    34k GitHub stars~2.1k tokensUpdated 1 mo ago
    SecurityAuto-check passed
  • Analyzing Memory Dumps With Volatility

    mukul975/Anthropic-Cybersecurity-Skills

    Analyzes RAM memory dumps from compromised systems using the Volatility framework to identify malicious processes, injected code, network connections, loaded modules, and extracted credentials.

    34k GitHub stars~2.9k tokensUpdated 1 mo ago
    SecurityAuto-check passed

More from rehan-remade/universal-modder

All 10 skills in this repo
  • Mashup Mods

    rehan-remade/universal-modder

    Build cross-game mashups and total conversions, the "Minecraft inside Elden Ring" or "skateboarding in MW2" kind.

    6.5k GitHub stars~3.3k tokensUpdated today
    Auto-check passed
  • Asset Pipeline

    rehan-remade/universal-modder

    Turn generated or hand-made art into exactly what a game engine loads.

    6.5k GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Game Recon

    rehan-remade/universal-modder

    Figure out how a specific installed game can be modded, before writing any mod code.

    6.5k GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Game Research Websearch

    rehan-remade/universal-modder

    Research a game, engine or modding technique on the open web with archive-aware, rate-limit-safe searches — Wayback Machine/archive.today for dead forums (XeNTaX, Zenhax, old threads), GitHub…

    6.5k GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • Publish Mod

    rehan-remade/universal-modder

    Package and release a finished game mod. An agent skill from rehan-remade/universal-modder.

    6.5k GitHub stars~812 tokensUpdated today
    Auto-check: notes
  • Showcase Video

    rehan-remade/universal-modder

    Record and cut a short showcase video of a game mod, or a compilation of clips, ready to post on X/YouTube.

    6.5k GitHub stars~1.3k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Game Automation

What does Game Automation do?

Launch, see and drive a real game so an agent can test its own mods. Game Automation is an agent skill from rehan-remade/universal-modder. Launch, see and drive a real game so an agent can test its own mods.

When should I use Game Automation?

Game Automation fits situations like: A mod must be verified in game; navigating menus automatically; building a repeatable test.

How do I install Game Automation in Claude Code?

Run `npx skills add rehan-remade/universal-modder --skill game-automation -a claude-code`. Or copy the skill folder (skills/game-automation in rehan-remade/universal-modder) into .claude/skills/game-automation in your project. Claude Code loads it when a task matches its description.

How do I install Game Automation in Codex?

Run `npx skills add rehan-remade/universal-modder --skill game-automation -a codex`. Or copy the skill folder (skills/game-automation in rehan-remade/universal-modder) into .agents/skills/game-automation in your project. Codex loads it when a task matches its description.

Can I use Game Automation 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 rehan-remade/universal-modder --skill game-automation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/game-automation, .gemini/skills/game-automation, .github/skills/game-automation and .opencode/skills/game-automation in your project.

What does Game Automation need to run?

SKILL.md names no scripts, command-line tools or credentials: Game Automation is instructions for the agent only. Our summary lists: Python 3.

Does Game Automation 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 Game Automation 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 Game Automation use?

Game Automation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Game Automation use?

About 1.9k tokens (SKILL.md is roughly 7.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Game Automation?

Skills that share tags, products or a category with Game Automation: Ctf Crypto (ljagiello/ctf-skills, 3.4k stars), Os Hardware Inventory (cdxgen/cdxgen, 1.1k stars), Forensics Osquery (AgentSecOps/SecOpsAgentKit, 220 stars) and Bumblebee (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Game Automation?

rehan-remade (a GitHub user) maintains it in rehan-remade/universal-modder, which has 6,452 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 11, 2026.

Source: rehan-remade/universal-modder on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.