Click or speak on any web page. ShareWithAgent anchors every comment to a real DOM element and hands your coding agent “button .hero__cta, contrast too low” — not “something near (840, 312).”
No screenshots. A frozen, interactive DOM snapshot — so every pin carries a real selector.
Extension or npx sharewithagent freezes the page exactly as you see it — logged in, JS-rendered, fonts and all — into one self-contained file.
Drop pins, draw boxes, write comments. Or (soon) just talk while you click around and let ShareWithAgent transcribe and anchor it.
Export structured JSON + a markdown digest. As a CLI/skill it streams straight back into your agent’s session — no copy-paste.
Each note carries a CSS selector, bounding box, element HTML and computed styles. The agent knows exactly what you meant.
A local CLI/skill (like plannotator) that returns feedback in-session — and a hosted website for sharing. Same viewer, same schema.
Snapshots render on your machine. Share links live in the URL fragment — never sent to a server. Self-host the whole thing.
Speak aloud while you browse; an LLM pass turns the ramble into discrete, element-anchored usability issues.
A screenshot tells an agent where. A DOM snapshot tells it what. That difference is the whole product.
“There’s a problem near coordinate (840, 312).” The agent has to guess which element, then hunt for it in the codebase.
“main > section.hero > a.hero__cta, padding 8px, background #6b7280, contrast too low.” The agent opens the file and fixes it.
ShareWithAgent is free and open-source forever — self-host it for nothing. The optional hosted instance costs $5/month, and every penny (after card fees) is donated. It’s a tool I built for myself; if it earns, a charity should keep it.