Visual context for coding agents
Show your agent exactly what you mean.
Capture a window or region with the controls behind it, then paste the result into Claude Code, Cursor, or Codex. Less explaining. Less guessing. Faster UI fixes.
Capture what the pixels cannot say
A screenshot shows the screen. ContextClip shows your agent which controls you mean.
The agent receives what the interface looks like and what its elements are, so you spend less time describing which button, field, or state needs attention.
Point or select
Capture the window under the pointer, or draw a region around the part that matters.
Capture both layers
ContextClip records a screenshot and the relevant accessibility tree in one local capture.
Paste into your agent
The clipboard is prepared for the way Claude Code, Cursor, or Codex reads context.
Two shortcuts, three capture modes
Capture the whole window or only the region that matters.
Choose Full capture, Screenshot only, or Text tree in Settings. Then use the shortcut that matches the scope of your task.
Window capture
Captures the window under the pointer and prepares the active mode for pasting.
Region capture
Draw a frame around a specific area. The screenshot and accessibility context are limited to that selection.
Choose the payload
Full capture combines screenshot and text tree. Screenshot only and Text tree send just the layer you need.
Tested delivery profiles
One capture. The right paste for each agent.
Agent apps interpret the macOS clipboard differently. ContextClip prepares the combination that works for the selected target.
On demand and local
You choose when to capture and where to paste.
ContextClip does not sign in to your agent accounts. It prepares the capture locally, places the selected delivery format on the clipboard, and keeps the source files available on your Mac.
No continuous screen monitoring
A capture starts when you use ContextClip.
Local capture files
The screenshot, accessibility JSON, and capture summary are written to a local bundle.
macOS permissions are explicit
Screen Recording and Accessibility access are required and explained during setup. Granted permissions take effect immediately — no restart.
Automatic local cleanup
Only the 25 most recent captures are kept on disk; older ones are removed automatically.
Where it fits
Built for the visual part of software work.
Debug the right control
Point to a clipped label, incorrect state, or misplaced button without describing its location in prose.
Polish generated UI
Point to the visual fix while preserving the roles, names, identifiers, and frames behind it.
Share a reproducible state
Attach the screenshot and structural context from the same moment in one capture.
Documentation for the beta
From first launch to the right agent profile.
The companion documentation covers setup, permissions, capture modes, shortcuts, agent-specific delivery, local files, and troubleshooting.
ContextClip beta for macOS 15.6+
Less explaining. Less guessing. Faster UI fixes.
The beta runs on macOS 15.6 or later, on Apple silicon and Intel. Grant Screen Recording and Accessibility in the setup assistant — no restart — and your first capture is one shortcut away.
Version 1.0 · 5.4 MB · signed and notarised