Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tdimino/bg3se-macosnpx agentmods add skills/tdimino/bg3se-macos/bg3-steam-launcherWrote 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.
[](https://agentmods.dev/skills/tdimino/bg3se-macos/bg3-steam-launcher)<a href="https://agentmods.dev/skills/tdimino/bg3se-macos/bg3-steam-launcher"><img src="https://agentmods.dev/badge/skills/tdimino/bg3se-macos/bg3-steam-launcher/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tdimino/bg3se-macos/bg3-steam-launcher"><img src="https://agentmods.dev/badge/skills/tdimino/bg3se-macos/bg3-steam-launcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 22 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 23 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Data Exfiltration · line 149 Code scans file system directories looking for sensitive files. This could be reconnaissance for credential theft.Fix: Remove unnecessary filesystem scanning. If file access is needed, use explicit, scoped paths. Avoid reading ~/.ssh, ~/.aws, or credential directories.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00129 | $0.01345 |
| Opus 5.5 | $0.00052 | $0.00538 |
| Sonnet 5.5 | $0.00026 | $0.00269 |
| Haiku 4.5 | $0.00013 | $0.00135 |
Grade A, and why
bg3-steam-launcher 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BG3 Steam Launcher
Automate launching Baldur's Gate 3 via Steam and loading saved games.
MCP Servers Used:
- macos-automator - AppleScript execution for UI automation
- peekaboo - Fast screenshots and AI-powered visual analysis
Prerequisites
claude mcp add macos-automator -- npx -y @steipete/macos-automator-mcp@latest
claude mcp add peekaboo -- npx -y @steipete/peekaboo-mcp@beta
Grant accessibility permissions to osascript in System Preferences → Security → Accessibility.
MCP Tools Quick Reference
Peekaboo (Vision)
| Tool | Use |
|---|---|
mcp__peekaboo__image |
Capture screenshot of screen/app/window |
mcp__peekaboo__analyze |
Ask AI questions about screenshots |
mcp__peekaboo__list |
List running apps and windows |
macos-automator (Actions)
| Tool | Use |
|---|---|
mcp__macos-automator__execute_script |
Run AppleScript/JXA |
mcp__macos-automator__get_scripting_tips |
Search automation scripts |
Core Workflow
Step 1: Launch BG3 via Steam Protocol
do shell script "open steam://run/1086940"
BG3 Steam App ID: 1086940
Step 2: Wait for Larian Launcher
Use Peekaboo to monitor for the PLAY button, then click it.
Step 3: Wait for Main Menu (15-30s)
Poll with Peekaboo screenshots looking for Continue/Load Game/New Game buttons.
Step 4: Load Save
Navigate menus using keyboard (Enter=36, Esc=53, arrows) or mouse coordinates.
Mouse Clicks (JXA + CGEvent)
Standard AppleScript click at doesn't work for game UIs. Use JXA with CGEvent:
// Execute with language: "javascript"
ObjC.import('Cocoa');
function clickAt(x, y) {
const point = $.CGPointMake(x, y);
const down = $.CGEventCreateMouseEvent($(), $.kCGEventLeftMouseDown, point, $.kCGMouseButtonLeft);
const up = $.CGEventCreateMouseEvent($(), $.kCGEventLeftMouseUp, point, $.kCGMouseButtonLeft);
$.CGEventPost($.kCGHIDEventTap, down);
delay(0.05);
$.CGEventPost($.kCGHIDEventTap, up);
}
// Get window-relative coordinates
function getWindowClickPos(processName, xPercent, yPercent) {
const se = Application('System Events');
const proc = se.processes.byName(processName);
const win = proc.windows[0];
const pos = win.position();
const size = win.size();
return {
x: pos[0] + (size[0] * xPercent),
y: pos[1] + (size[1] * yPercent)
};
}
// Example: click PLAY button (22% across, 87% down)
const coords = getWindowClickPos('bg3', 0.22, 0.87);
clickAt(coords.x, coords.y);
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.
- 2mo ago First seen · 162 lines · 129 tokens per session scan A 1cf334578afd
bg3-steam-launcher is a skill published in the GitHub repository tdimino/bg3se-macos (64 stars, last pushed 1mo ago), licensed MIT. It adds 129 tokens to every session and 1,345 once invoked, about $0.0005 per session on Opus 5.5. 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.
bg3-steam-launcher compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bg3-steam-launchertdimino/bg3se-macos | Skill | 64 | 1mo ago | MIT | A | 129 | Claude Code, Codex |
| analyzing-golang-malware-with-ghidramukul975/Anthropic-Cybersecurity-Skills | Skill | 36k | 2mo ago | Apache-2.0 | A | 95 | Claude Code |
| scenario-walkable-roomscenario-labs/skills | Skill | 3.2k | yesterday | MIT | A | 113 | Claude Code |
| ctf-pwncyberkaida/reverse-engineering-assistant | Skill | 944 | 3d ago | Apache-2.0 | A | 46 | Claude Code |
| deep-analysiscyberkaida/reverse-engineering-assistant | Skill | 944 | 3d ago | Apache-2.0 | A | 98 | Claude Code |
| pyghidra-scriptingcyberkaida/reverse-engineering-assistant | Skill | 944 | 3d ago | Apache-2.0 | A | 209 | Claude Code |
| ctf-revcyberkaida/reverse-engineering-assistant | Skill | 944 | 3d ago | Apache-2.0 | A | 52 | Claude Code |