When I paste a screenshot into Claude Code or Cursor, a crop plus an arrow usually fixes the "where." What kept going wrong for me was the "why" once there are three or four things to fix on one screen.
What helped was talking while I draw. I circle a clipped label and say "let this wrap," then draw an arrow to a chart point and say "tooltip on hover and keyboard focus." Lasso puts [1] and [2] in the transcript at the exact words I said while making each mark. So the agent gets numbered marks with my intent attached, instead of a paragraph it has to match back to the image.
I also stopped pasting. A local coding agent on the same Mac can pull the latest annotated capture or voice brief itself through Lasso's local MCP server, and Lasso asks before the first agent call.
I wrote up the full workflow, with an example prompt for a UI fix, here: https://www.trylasso.online/guid...
hey, nika here, i made lasso. it's a tiny mac app for drawing on your screen, and it runs a local mcp server so claude code / cursor can see what you circled instead of you describing it in 3 paragraphs
launching here tue nov 17. before that i'm curious: if your coding agent could see your screen, what would you point at first? ui bugs, design tweaks, something else?
honest takes welcome, including "i'd never use this"
Lasso lets you draw arrows, boxes and notes right on your Mac screen with ⌥⇧A, then press S to screenshot what you marked up. Blur sensitive bits, share an encrypted link that expires in 24 hours, or sketch on an endless whiteboard. It also runs a local MCP server, so Claude Code, Cursor and Claude Desktop can see what you circled and draw back. $9.99 once, no account, no subscription. macOS 14+, Apple silicon and Intel.