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 sandraschi/windows-computer-use-mcp --skill desktop-automation-protocolgit clone --depth 1 https://github.com/sandraschi/windows-computer-use-mcpWrote 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/sandraschi/windows-computer-use-mcp/desktop-automation-protocol)<a href="https://agentmods.dev/skills/sandraschi/windows-computer-use-mcp/desktop-automation-protocol"><img src="https://agentmods.dev/badge/skills/sandraschi/windows-computer-use-mcp/desktop-automation-protocol/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/sandraschi/windows-computer-use-mcp/desktop-automation-protocol"><img src="https://agentmods.dev/badge/skills/sandraschi/windows-computer-use-mcp/desktop-automation-protocol.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00029 | $0.00444 |
| Opus 5.5 | $0.00012 | $0.00178 |
| Sonnet 5.5 | $0.00006 | $0.00089 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
desktop-automation-protocol 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 1mo 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- desktop-automation-protocol — 100% identical, 0 lines differ
- desktop-automation-protocol — 100% identical, 0 lines differ
What it actually says
Desktop automation protocol (windows-computer-use-mcp)
Tool selection guide
| Goal | Tool | Example |
|---|---|---|
| Click a known button | automation_elements(click, title="Save") |
fast, needs exact title |
| Click by intent | automation_smart(click="the Save button") |
slower, finds across all windows |
| Complex multi-step | automation_mission(run="save file as PDF") |
autonomous loop with retry |
| Record + replay | automation_macro(record) → stop → replay |
repeatable sequences |
| Wait for event | automation_watch(start, "window_appears", "Update") |
event-driven triggers |
| Explore desktop | automation_smart(discover) |
get all running apps |
| Extract + chain | automation_mission(workflow, actions, store_as, dollar-ref) |
cross-app data pipeline |
Focus rules
- After automation starts, do not Alt+Tab or touch the mouse
- The target window must stay in foreground during click/type sequences
- If HITL approval appears, approve it and let the target window regain focus
- Prefer reading logs between paused steps or on a second monitor
Safety
- Read docs/SAFETY.md before production use
- Pair with virtualization-mcp for sandbox/VM isolation when running untrusted automation
- Opt-in features (face, keylogger) are off by default — enable only when needed
Mission design (automation_mission)
For run operation: provide a clear, concrete goal. The server decomposes via LLM sampling.
For workflow operation: provide explicit steps with tool, params, label, and optional store_as/dollar-ref for data chaining.
For self-healing: set app_path on steps so the mission can re-launch crashed apps.
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.
- 1mo ago First seen · 37 lines · 29 tokens per session scan A 857216599875
desktop-automation-protocol is a skill published in the GitHub repository sandraschi/windows-computer-use-mcp (48 stars, last pushed 3d ago), licensed MIT. It adds 29 tokens to every session and 444 once invoked, about $0.0001 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.
Other skills, from other repositories
hermes-cron-automations
Use when building a recurring automation on the Hermes box.
storage-analyzer
A read-only disk-space scanner for macOS and Windows that groups files into categories such as caches, personal data, and files to keep. It produces an HTML report with commands you can review before cleanup.
robotgo
Use when automating desktop GUI in Go — robotgo.Move/Click/KeyTap, CaptureImg vs CaptureScreen, bitmap.Find template matching, gohook global hotkeys, gcv OpenCV matching, clipboard and window control. RobotGo v1.3.7: cross-platform Go desktop automation for macOS/Windows/Linux. Also for black screenshots or silently…
excalidraw
Hand-drawn diagrams in Excalidraw JSON (architecture, flowcharts).
google-workspace
Gmail, Calendar, Drive, Sheets, Docs via Google API (SA / OAuth).
linear
Manage Linear issues, projects, and cycles via the Linear GraphQL API.