Item logo image for SnipToss – Screenshot & Annotate for AI

SnipToss – Screenshot & Annotate for AI

ExtensionTools6 users
Item media 5 (screenshot) for SnipToss – Screenshot & Annotate for AI
Item media 1 (screenshot) for SnipToss – Screenshot & Annotate for AI
Item media 2 (screenshot) for SnipToss – Screenshot & Annotate for AI
Item media 3 (screenshot) for SnipToss – Screenshot & Annotate for AI
Item media 4 (screenshot) for SnipToss – Screenshot & Annotate for AI
Item media 5 (screenshot) for SnipToss – Screenshot & Annotate for AI
Item media 1 (screenshot) for SnipToss – Screenshot & Annotate for AI
Item media 1 (screenshot) for SnipToss – Screenshot & Annotate for AI
Item media 2 (screenshot) for SnipToss – Screenshot & Annotate for AI
Item media 3 (screenshot) for SnipToss – Screenshot & Annotate for AI
Item media 4 (screenshot) for SnipToss – Screenshot & Annotate for AI
Item media 5 (screenshot) for SnipToss – Screenshot & Annotate for AI

Overview

Capture part of a web page or your whole screen, mark what to change, add notes, and paste one image into ChatGPT, Claude or Codex.

Mark up a screenshot instead of typing it all out. When something on a web page needs changing, explaining it to an AI in words takes a whole paragraph, and the AI still has to guess which button you mean. SnipToss lets you point instead. Take a screenshot of the page (or of your whole screen), draw on the parts you mean, write a short note for each one, and paste the result into ChatGPT, Claude or any other AI chat as a single image. HOW TO USE IT 1. Start: press Alt+Shift+S (⌥⇧S on Mac), click the SnipToss icon and choose "Capture & annotate", or right-click the page. 2. Select: click an element to take the whole thing, such as a card, a button or a paragraph. Scroll to pick a bigger or smaller one, or drag any area. 3. Mark: draw a box, ellipse, arrow or pen stroke, or drop a pin, and write what should change. Keep marking while the note box is open to point at several places with one note. 4. Finish: press Enter. One image goes to your clipboard: the screenshot with numbered marks, and your notes listed under it. The cursor goes back to the box you were typing in, so you can paste right away. MARKING TOOLS • Rectangle, ellipse, arrow, pen and numbered pin, each with its own note • One note can mark several places, and each place can have its own color • Eight colors plus a color picker; your recent custom colors stay in the color row • Text on the image, and mosaic to hide sensitive information • An overall comment for notes that aren't about one spot • Click a mark and its colors pop up right next to it, with Delete at the end. Delete (⌫ on Mac) removes just that place, and undo brings it back • Drawings: draw a rectangle, ellipse, arrow or pen stroke and leave its note empty, and it stays on the image without a number. Click it to recolor or delete it, or double-click it to add a note • Drag the note box aside when it covers something you still want to mark • A magnifier with the pixel position and color under the cursor, and a one-key shortcut for every tool WHAT THE AI GETS • Every note is numbered to match its mark, and tagged Change, Remove, Add or Question • Each note says where its mark is, in pixel coordinates of the screenshot, and names the color when places differ, so you can write "the blue one" • The notes also tell the AI that lines and boxes without a number were drawn by you and aren't part of the screenshot, and that a note tagged Question only needs an answer • Notes are drawn under the picture, so nothing is lost in apps that only take the image when you paste, such as Claude Code and Codex • Prefer text? Turn off "Include notes in the image" and the notes go to the clipboard as separate text • Add the same line to every capture, for example "Keep the existing style and only change what's marked." • Ctrl+S (⌘S on Mac) saves the image as a PNG file instead CAPTURING THE WHOLE SCREEN (OPTIONAL) • Switch "Capture area" to "Whole screen" in the toolbar popup and you can annotate anything on your screen, such as another app, a PDF, a design file or an error message • Make the shortcut "Global" to start from any app. The screen pauses and opens full screen with the same tools • Chrome asks which screen to share for each capture. Turn on "Quick mode" to choose once; Chrome then shows that your screen is being shared until you turn it off • SnipToss takes one still frame per capture. Nothing is recorded or uploaded • A short setup walks you through it the first time, with a test capture On Windows • No system permission needed: Chrome's own screen sharing is all it takes • When you finish, you're back in the app you were using, so you can paste right away On Mac • Chrome needs the Screen Recording permission in System Settings. The setup shows how, and its test capture tells you whether windows show up (without the permission macOS only gives the wallpaper) • macOS 15 and later asks you to confirm this permission again about once a month • Annotation opens in its own full-screen space and lines up with the real screen, notch included • When you finish, Chrome stays in front: switch back to your app to paste PRIVACY • Everything happens in your browser. Screenshots and notes are never uploaded, and SnipToss makes no network requests • No account, no sign-up, no analytics, no ads • SnipToss only sees a page when you start a capture on it • Minimal permissions: activeTab, scripting, storage, contextMenus and system.display (to open the annotation window on the screen you captured). Screen capture is optional and only requested when you turn on "Whole screen". No access to your browsing history or to other tabs GOOD TO KNOW • SnipToss captures the visible part of the page; it doesn't stitch long scrolling pages • Chrome doesn't let extensions capture its own pages, such as chrome:// pages and the Chrome Web Store • To capture files opened from your computer, turn on "Allow access to file URLs" for SnipToss on its details page • If a page blocks the clipboard, SnipToss copies the image from its own popup instead • You can change the shortcut at chrome://extensions/shortcuts • Interface languages: English, Spanish, German, French, Portuguese (Brazil), Japanese, Korean, Simplified Chinese and Traditional Chinese THE DESKTOP VERSION SnipToss for Windows and SnipToss for Mac are free, open-source (MIT) desktop apps for the images and videos your coding agent makes. Your notes are saved as plain files in your project, so Claude Code, Codex and other agents that read local files can act on them. Windows 11, or macOS 14 and later. https://github.com/Moy339339/SnipToss SUPPORT SnipToss for Chrome is free. Made by MoyGoldenAge. Problems or ideas: https://github.com/Moy339339/SnipToss/issues/new/choose (no GitHub account? Email jujuw3939@outlook.com) If it saves you time, you can buy me a coffee: https://ko-fi.com/moygoldenage Google Chrome is a trademark of Google LLC.

Details

  • Version
    1.2.1
  • Updated
    November 15, 2026
  • Offered by
    Moy
  • Size
    695KiB
  • Languages
    9 languages
  • Developer
    Email
    jujuw3939@outlook.com
  • Non-trader
    This developer has not identified itself as a trader. For consumers in the European Union, please note that consumer rights do not apply to contracts between you and this developer.

Privacy

Manage extensions and learn how they're being used in your organization
The developer has disclosed that it will not collect or use your data. To learn more, see the developer’s privacy policy.

This developer declares that your data is

  • Not being sold to third parties, outside of the approved use cases
  • Not being used or transferred for purposes that are unrelated to the item's core functionality
  • Not being used or transferred to determine creditworthiness or for lending purposes

Support

For help with questions, suggestions, or problems, please open this page on your desktop browser

Search
Clear search
Close search
Google apps
Main menu