LLMent Picker

LLMent Picker (say: el-el-ment): point at any element in your own browser, on live sites and logged-in portals, in Firefox or Chrome, and paste it into Claude Code, Codex, Cursor or any chat. No server, no MCP, no setup. It sees nothing until you click, sends nothing anywhere and runs only on the page you point it at. Why not the browser built into your coding tool? That one runs a clean profile without your logins and is made for the local dev server. LLMent Picker works where you already are: the client's live site, the shop backend, the portal you are signed in to, with your own extensions and password manager, and it hands the result to whichever agent you use. Working on a web page with an AI assistant, you hit this constantly: "I mean the second box under the heading" is clear to a person and useless to a tool. LLMent Picker turns one click into an unambiguous reference in your clipboard: the full page URL a CSS selector that matches exactly this element, e.g. #bereiche .values > .value:nth-of-type(2) > p if you selected text first: that text in quotes – "this passage is meant" with Alt+click: a screenshot of the element and its surroundings, plus viewport and pixel ratio – for "this overlaps", "this is misaligned". By default the PNG goes to your downloads folder and its path into the clipboard text – token-friendly, readable by any chat, croppable at full size (setting: file, clipboard with image and text in one Ctrl+V, or both). Elements larger than the window (long tables, wide tables in scroll containers) are captured whole, stitched from several tiles. Or hold the left button and drag a region: the lasso captures exactly that area, the selector names the container that covers it best. with Ctrl+click: the element's HTML as currently rendered, saved as a file in your downloads folder, with the CSS context you would see in the inspector: matching rules with origin, specificity and what they lose in the cascade, effective values without default noise, CSS variables resolved, the children's box model, a spacing chain and the ancestors' deviations. The path goes into the clipboard – Claude Code reads it straight from disk. For content that only exists logged in or after rendering: timetables, tables, portals. Selectors are readable for humans and unambiguous for tools: IDs and meaningful class names serve as anchors, positional indices are used only where needed, state and animation classes are ignored, and every selector is verified against the page before copying (exactly one match). Usage • Select text, then icon or shortcut → element containing the selection + text copied immediately • Nothing selected: icon or shortcut → picker starts; the element under the cursor gets an outline; click copies • Alt+click → with screenshot · Ctrl+click → as HTML file · both → both · drag → lasso region as screenshot · R → record the interaction for 5 s (hover rules, transitions, state diff, DOM changes, frame timing, contact sheet) • Hold Shift → multi-selection: Shift+↑/↓ or Shift+click extend to neighbouring sections, any other element joins individually, a container becomes the context of the inner elements; Enter or a click copies everything with one screenshot • Tap Alt, Ctrl or R to arm a mode for the next click – no need to hold the key while aiming • Every copy starts with a label such as [LLMent: element, shot:file] and a context line (browser, viewport, pixel ratio, dark/reduced-motion) – an agent recognises the format instead of guessing; every part can be switched off • Right-click on the page → "Copy this element" / "Copy with screenshot" / "Save as HTML file" / "Record interaction here", without picker mode • Right-click the icon → start the picker with a preset • Videos and embedded players: a click copies the element instead of starting playback • Works inside iframes; the clipboard says which frame. Forms and widgets embedded from another site (HubSpot, Typeform, payment fields) become selectable after one optional permission in the settings; until then the picker marks such a frame and key O opens that setting Privacy: by default only the activeTab permission; the extension does nothing until you invoke it and has no access to other pages. One optional permission (access to all sites) is requested only if you switch on "Also allow elements inside embedded frames from other sites" in the settings, and can be withdrawn there at any time; it is used solely to run the picker inside such frames when you start it. Screenshots and HTML files are created only on your click and stay on your device (downloads folder or clipboard). No network access, no data collection. Source on GitHub, MIT licence.