dsh-screenshot-plugin

When chatting with an agent in DeepSeek Harness Desktop, you often need to capture a specific area of your screen and hand it over for analysis—UI layout, error dialogs, form state. The conventional flow means switching to a system snipping tool, saving the file, switching back, and typing the path by hand. dsh-screenshot-plugin collapses all of that into a single ✂ button sitting right next to the composer.

Click the button and the whole screen dims; drag to draw a selection rectangle. After you release, the selection stays alive—you can move it by dragging the body and resize it precisely with eight handles (four corners, four edges) before committing. Double-click or press Enter to capture, Esc to walk away. The image lands in your screenshots folder with an auto-numbered name (Screenshot-N_HHmm.png), and a plain-ASCII marker like [Shot 3 14:22] drops straight into the input box. Send that marker, and a vision-enabled agent such as ModLens can locate and read the file without you ever mentioning a path.

Built for Windows users on DSH Desktop who find themselves repeating the screenshot-to-tell-the-agent loop—frontend debugging, UI comparison, error triage, form-state capture. The selection overlay is drawn with PowerShell WinForms in pure-ASCII source, so there are no encoding surprises with file names or cross-process hand-off, and the marker itself is ASCII so it survives chat transport intact. If that screenshot-and-point step shows up a few times a week in your workflow, this plugin will save you the round-trips.