CONTEXA - Claude prompts, without the writing

Claude replies. Press one button and CONTEXA reads your session, then writes up to four next messages. Pick one, you send it.

CONTEXA writes your next message, so you don't have to. CONTEXA is a free Chrome extension for Claude.ai. You are already deep in a conversation with Claude. You know roughly where you want it to go. The hard part is turning that into a message specific enough to get a good answer back — and that is a skill, not a mood. CONTEXA reads where the conversation has been going and offers you the messages you could send next. Each one is already written, in full. You pick one, read it, change anything you like, and send it yourself. NOTHING HAPPENS UNTIL YOU ASK When a Claude reply finishes, one small trigger appears above your message box. That is all. No model call, no request, nothing about your conversation leaves the page, and nothing counts against your daily allowance. Press it and CONTEXA reads your own messages from the conversation — what you have been building toward across the whole thread, not just the last thing you typed — and offers up to four next moves. FOUR MESSAGES, NOT FOUR TOPICS Each move is a complete message on its own. They do not run in order, they do not build on each other, and picking one throws the rest away. It is a menu, not a checklist — you only need one. Click the one you want and the whole message lands in your box. You can edit it. Nothing is ever sent without you pressing send. Where a message needs something only you have — a file, a link, a detail only you could know — CONTEXA marks the spot instead of inventing it. It may also add a line starting "Assume:" for anything the conversation already settled, so you can change it before you send rather than discovering it in the answer. WHEN IT HAS NOTHING TO SAY, IT SAYS NOTHING If the conversation has nothing worth taking further, CONTEXA shows you nothing at all. No filler, no padded row, no suggestion whose only virtue is that it could be shown. That is deliberate, and it is the part most of these tools get wrong. Every move has to be earned by something actually said in the conversation. Nothing earned, nothing offered. WHAT IT WILL NOT DO It does not grade your prompts or tell you how to write. It does not overlay your message box or interrupt your typing. It does not send anything on your behalf, ever. And when something goes wrong — a limit reached, a network failure — it tells you what actually happened instead of quietly showing you canned suggestions. HOW TO USE IT 1. Install it and open a conversation on claude.ai. 2. When a reply finishes, press the CONTEXA trigger above your message box. 3. Pick one of the messages it offers. It lands in your box, whole. 4. Edit if you want. Send when you are ready. No account. No sign-up. No API key needed. 20 replies a day are free — that is how many answers you can ask about, and picking a message costs nothing extra. If you have your own Anthropic API key you can add it in settings, which removes the daily limit — and in that mode requests go straight from your browser to Anthropic, so nothing passes through our server at all. PRIVACY, PLAINLY • CONTEXA runs only on claude.ai. It touches no other site. • Nothing is sent anywhere until you press the button. A reply you never ask about never leaves your browser. • When you do press it, CONTEXA sends your own messages from that conversation and the reply you just received. Claude's earlier replies are never sent. • There are hard limits on how much that can be: at most 40 of your messages, 12,000 characters in total, and 6,000 characters of the reply. The backend enforces these itself. • Your conversation text is never stored. It is used to write the suggestions and then discarded. • No accounts, no profiles, no tracking, no analytics, no advertising, and nothing sold or shared. • Your API key, if you provide one, stays on your device and goes only to Anthropic. Full policy: https://github.com/33kain/contexa/blob/main/publishing/PRIVACY.md CONTEXA is open source: https://github.com/33kain/contexa CONTEXA is an independent project. It is not affiliated with, endorsed by, or sponsored by Anthropic.