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.
npx skills add frontier-ai-next/mgarlbot --skill desktop_automationgit clone --depth 1 https://github.com/frontier-ai-next/mgarlbotWrote 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/frontier-ai-next/mgarlbot/desktop_automation)<a href="https://agentmods.dev/skills/frontier-ai-next/mgarlbot/desktop_automation"><img src="https://agentmods.dev/badge/skills/frontier-ai-next/mgarlbot/desktop_automation/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/frontier-ai-next/mgarlbot/desktop_automation"><img src="https://agentmods.dev/badge/skills/frontier-ai-next/mgarlbot/desktop_automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00015 | $0.00274 |
| Opus 5 | $0.00008 | $0.00137 |
| Sonnet 5 | $0.00003 | $0.00055 |
| Haiku 4.5 | $0.00002 | $0.00027 |
Grade A, and why
desktop_automation 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 11d 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.
What it actually says
Desktop automation (macOS)
Use shell commands for screenshots and simple desktop actions.
Screenshots
Full screen:
screencapture ~/Desktop/screenshot.png
Interactive region:
screencapture -i ~/Desktop/screenshot.png
Interactive window:
screencapture -w ~/Desktop/screenshot.png
Silent (no shutter sound):
screencapture -x ~/Desktop/screenshot.png
Clipboard
Copy capture to clipboard:
screencapture -c
Display info
Resolution hint:
system_profiler SPDisplaysDataType | grep Resolution
Rules
- Default save path
~/Desktop/unless the user specifies another path. - Use
-xto suppress shutter sound when appropriate. - After capture, verify with
ls -la <path>. - If the user asks for a “photo” of the screen, they mean a screenshot.
- Default format:
.png.
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.
- 11d ago First seen · 62 lines · 15 tokens per session scan A cf17cfb2c544
desktop_automation is a skill published in the GitHub repository frontier-ai-next/mgarlbot (17 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 274 once invoked, about $0.0001 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.
Other skills, from other repositories
architecture-diagram
Dark-themed SVG architecture/cloud/infra diagrams as HTML.
orchestrator
Providerneutrales Protokoll zum Zerlegen komplexer Aufgaben, zum Beauftragen unabhängiger Worker und zur evidenzbasierten Abnahme ihrer Ergebnisse.
choose-your-orchestrator
Wählt vor komplexer Multi-Agent-Arbeit gemeinsam mit dem Nutzer eine passende, begrenzte Orchestrierung und erzeugt einen kompakten Session-Vertrag. Nutze den Skill bei /choose-your-orchestrator, bei unsicherer Kombination aus Orchestrator, Schwarm, Modellrouting oder Nutzerpräferenzmodell sowie vor Agentenprogrammen…
agent-config-sync
Provider-neutral planner for synchronizing MCP configuration, skills and rule files across agent providers and app classes. It discovers evidenced local options and lets the user choose truth, targets, direction and conflicts.
Docker Compose Generator
Generates production-ready docker-compose.yml files for any application stack.
agent-comm-hub
A local communication hub that lets separate AI agents exchange messages, share context, coordinate tasks, and review suggestions.