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 Proxy2021/Enso --skill remote_desktopgit clone --depth 1 https://github.com/Proxy2021/EnsoWrote 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/proxy2021/enso/remote_desktop)<a href="https://agentmods.dev/skills/proxy2021/enso/remote_desktop"><img src="https://agentmods.dev/badge/skills/proxy2021/enso/remote_desktop/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/proxy2021/enso/remote_desktop"><img src="https://agentmods.dev/badge/skills/proxy2021/enso/remote_desktop.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 | $0.00017 | $0.00289 |
| Opus 5.5 | $0.00007 | $0.00116 |
| Sonnet 5.5 | $0.00003 | $0.00058 |
| Haiku 4.5 | $0.00002 | $0.00029 |
Grade A, and why
remote_desktop 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.
What it actually says
Remote Desktop
Remote desktop viewer with click, type, scroll, and keyboard control
Available Tools
enso_remote_desktop_capture (primary)
Capture a screenshot of the remote desktop
Parameters:
monitor(number): Monitor index (default 0 = primary)
enso_remote_desktop_click
Click at screen coordinates then capture a new screenshot
Parameters:
x(number): Screen X coordinatey(number): Screen Y coordinatebutton(string): left, right, or double (default: left)
enso_remote_desktop_type
Type text on the remote desktop then capture a new screenshot
Parameters:
text(string): Text to type
enso_remote_desktop_scroll
Scroll at screen coordinates then capture a new screenshot
Parameters:
x(number): Screen X coordinatey(number): Screen Y coordinatedirection(string): up, down, left, or rightamount(number): Scroll amount (default 3)
enso_remote_desktop_key
Send a key combination then capture a new screenshot
Parameters:
combo(string): Key combo like control+c, alt+tab, enter, escape
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 · 51 lines · 17 tokens per session scan A b372d8a18280
remote_desktop is a skill published in the GitHub repository Proxy2021/Enso (6 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 289 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 2026-08-31.
Other skills, from other repositories
argent-device-interact
Interact with an iOS simulator, Android emulator, or Chromium (CDP) app using argent MCP tools. Use when tapping UI elements, performing gestures, scrolling/swiping, typing text, pressing hardware buttons, launching apps, opening URLs, taking screenshots, waiting for an element to appear or disappear, or checking…
douyin-search
An example AI skill that automates searching for videos in Douyin, a Chinese short-video app, using the app's visible controls. It opens Douyin, enters a keyword, searches, and opens the first result.
ui-automation
Control the physical UI of any app on this device (clicks, scrolls, typing).
click
Tap a UI element by text on the screen.
flywheel
Development flywheel - autonomous cycle of run, observe, fix, verify. Use for continuous development with browser automation.
js-reverse
A workflow for examining browser JavaScript to understand how web pages create requests, signatures, encrypted parameters, and risk-control fields.