Annotate screenshots before pasting them into any AI chat.
Snapmark sits in your clipboard. Copy a screenshot, hit ⌘⇧A, draw on it, and paste into Claude, Copilot, Cursor — anything.
Works with
…and anything else that accepts pasted images.
Three things the marketplace doesn’t ship.
Snapmark is built for one workflow: annotating screenshots for AI agents. That’s it.
Blur sensitive regions
Hide API keys, tokens, and PII before the image leaves your machine. No key survives the paste.
Numbered step callouts
Drop 1 · 2 · 3 markers to walk the model through a UI flow in order. No more "what am I looking at" back-and-forth.
Auto-compress on copy
Retina screenshots get resized to 1920px on the long edge so vision models don't burn tokens on pixels they can't use.
How it works
Snapmark never touches any agent’s window. It lives in your clipboard.
- 1
Copy a screenshot
Use your OS screenshot tool — ⌃⇧⌘4 on macOS, Win+Shift+S on Windows, or any Linux snipper.
- 2
Annotate in VS Code
Snapmark notices the clipboard image and arms its status-bar button. Hit ⌘⇧A (Ctrl+Shift+A) to open the annotator.
- 3
Paste into any AI chat
Click Copy and paste the annotated image into Claude Code, Copilot Chat, Cursor — anything that accepts pasted images.
