Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Agent Desktop for Linux Pro

    1

    Everything in Agent Desktop for Linux, plus OCR clicks, set-of-marks vision, smart waits, macros, session reports, parallel desktops and an MCP server.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Agent Desktop for Linux Pro

    Agent Desktop for Linux Pro

    Example session with this skill installed

    Accept the cookie banner on this site, find the "Download report" button and download it. Show me what you clicked and give me a report of the run.

    • Read your context and instructions
    • Compiled the agent desktop
    • Generated the document

    Done. I worked on my own private desktop, so your pointer and windows were never touched.

    What I did

    StepCommandResult
    Start + audit trailadc start --nested · adc journal startPrivate display, every step logged with a screenshot
    Open the siteadc browser https://example.com --name workAgent-owned Chrome profile
    Wait for loadadc wait-stable --ms 700Page settled in 1.4 s
    Cookie banneradc click-text "Accept all"Found by OCR at (1032, 588), clicked
    See the pageadc marks --app chrome23 numbered elements; #14 = button "Download report"
    Downloadadc click-mark 14Clicked
    Checkadc downloads~/Downloads/report-2026.pdf (412 KB)
    Reportadc report --out ~/adc-report.html7 steps, 0 errors

    Safety

    adc guard on was active: a click on "Send" or "Pay" would have stopped and asked you first.

    Next steps

    • Open ~/adc-report.html to review every step with screenshots.
    • Save this flow with adc macro start download-report and replay it any time with adc macro play download-report.

    report-2026.pdf

    PDF · document

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Your AI agent gets its own isolated Linux desktop, a private display with its own pointer, keyboard and clipboard, so it never touches your mouse or steals your focus. Pro adds the tools you need for real, repeatable automation: it can see and click anything on screen, wait correctly, replay workflows and show you exactly what it did.

    Everything in the free edition

    • Isolated desktop: a private Xephyr display on its own workspace, with its own focus, clipboard and D-Bus session.
    • Accessibility engine: snapshot any app, then click, type, select and toggle by element reference (GTK, Qt, Chrome, Electron).
    • Human-like input: a visible agent cursor glides to each element; typing uses the real keyboard, so web apps receive genuine events.
    • Persistent browser profiles: sign in once, stay signed in.
    • User hand-off: the agent asks you to complete logins, captchas and 2FA, then continues.
    • Screen recording to MP4.

    Pro features

    • Set-of-marks vision: adc marks draws numbered boxes on every clickable element of a screenshot; the agent acts with click-mark 7. A picture and exact targets in one step.
    • OCR: find-text, click-text and wait-text find any visible text, even inside buttons and inputs, in canvases, remote desktops or apps without accessibility.
    • Smart waits: wait-stable and wait-change replace fixed sleeps; they ignore a blinking caret.
    • Guard: with adc guard on, actions such as send, pay, delete or publish (English and Spanish) are refused until the user confirms.
    • Macros with variables: record a workflow once and replay it with different data (--var email=...). Elements are matched by role and name, so replays survive layout changes.
    • Journal and HTML report: every step logged with a screenshot, exported as a self-contained HTML timeline you can share.
    • GIF export of any recording.
    • Parallel desktops: ADC_SESSION=name runs several isolated desktops at once, for several agents or tasks.
    • MCP server: adc mcp exposes the desktop as tools to Claude Desktop, Cursor or any MCP client; screenshots come back as images.
    • Clipboard and downloads of the agent desktop.

    How it works

    1. Run adc doctor to check dependencies.
    2. adc start --nested starts the agent's private desktop; adc journal start begins the audit trail.
    3. The agent observes with snapshot, marks or see, and acts with references, marks or text.
    4. It waits with wait-stable / wait-text and verifies the result.
    5. adc stop closes everything gracefully; adc report gives you the timeline.

    Use cases

    • Repetitive back-office work in web apps and desktop software without an API.
    • Filling the same forms with different data through macros.
    • Downloading reports or exporting data from dashboards behind a login.
    • QA runs on desktop and web apps, with an HTML report and a GIF as evidence.
    • Several agents working in parallel, each on its own desktop.

    Known limitations

    Linux with an X11 session only (no Wayland, macOS or Windows). OCR accuracy depends on text size and contrast. Apps without an accessibility tree rely on OCR and coordinates.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Workflow Automation.

    Requires an X11 session; no Wayland, macOS or Windows. OCR accuracy depends on text size and contrast. Apps without an accessibility tree rely on OCR and coordinates. System packages (Xephyr, openbox, tesseract) must be installed; adc doctor lists them.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 8 days ago

    Software
    Python 3 (PyGObject, AT-SPI)XephyropenboxxdotoolImageMagickFFmpegtesseract-ocrNode.jsGit
    Optional
    Google Chrome (for adc browser)tesseract-ocr-spa (Spanish OCR)

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Environment Variables
    Browser

    File Scopes

    ~/.local/share/adc/**
    $XDG_RUNTIME_DIR/adc/**
    ~/Videos/**
    ~/Downloads/**

    Runs a private X display (Xephyr) on its own workspace. Writes screenshots and state to $XDG_RUNTIME_DIR/adc; agent browser profiles, macros and journals to ~/.local/share/adc (mode 0700); optional recordings to ~/Videos. Reads ~/Downloads only to list files the agent downloaded in the session. Network is only used by the browser the agent opens. Credentials are never typed by the agent: sign-ins are handed to the user.

    Listed8 days ago

    What's inside

    Frequently Asked Questions

    Set-of-marks screenshots, OCR click-by-text, smart waits, a confirmation guard for risky actions, macros with variables, journal and HTML reports, GIF export, clipboard and downloads, parallel isolated desktops and an MCP server.

    This skill requires a Linux environment running X11; it currently does not support Wayland or non-Linux operating systems. It is compatible with any AI agent that supports MCP (Model Context Protocol) or can execute CLI commands.

    Not with adc guard on: those actions are refused until you confirm, and the agent repeats them with --confirmed only after your yes.

    Yes. click-text finds visible text with OCR, including text inside buttons and inputs, and see plus coordinates works for canvases, games and remote desktops.

    The tool includes a 'user hand-off' feature that triggers a system notification and pauses the agent, allowing you to manually complete the sensitive step before the agent resumes its automated workflow.

    Yes. claude mcp add adc -- adc mcp (or the equivalent in your client) exposes tools such as adc_see, adc_marks, adc_click_text and adc_act; screenshots come back as images.

    Yes. Each ADC_SESSION=name adc start --nested creates its own isolated desktop, and adc sessions lists them.

    The full free edition plus the Pro module, with a one-user licence for all your machines and updates.

    New in Workflow Automation