# Market scanner The scanner runs every two hours against 60+ crypto pairs. Each pair gets a 0-10 opportunity score, a rating (`STRONG_BUY` / `BUY` / `HOLD` / `AVOID`), and a one-line rationale based on the technical pattern that drove it. The whole scan takes under a minute and lands on the `/scanner` page automatically. ## What you see Each row shows the symbol, current price, score, rating, the top signal that drove the score (e.g. "RSI divergence on 1h" or "squeeze break + volume"), 24h change, and the most recent RSI reading. Click any row to open a fuller analysis pass or add the token to your watchlist. At the top of the page, a single-line **market mood** tells you whether the scanner is seeing risk-on, chop, rotation, or something else — useful context before you act on any individual row. Any pick that scores 8 or higher becomes an **alpha alert** — it enters the alert lifecycle system and CLAUDIA will track it until it closes. Alpha alerts also post to the feed and to connected Telegram channels. ## Manual refresh Automatic scans are free and run every two hours. If you need a fresh read sooner, click the manual refresh button. * **Cost: 3 credits** * **Cooldown: once every 10 minutes globally** * Manual refreshes use the same engine as automatic ones, so the output is identical — you're just getting it sooner. ## Accuracy page Every published pick is graded 24 hours, 72 hours, and 7 days after the call. The `/scanner/accuracy` page shows the rolling win rate per rating tier — so a `STRONG_BUY` across the last 30 days might show as 71% accurate, while `BUY` might show 54%. That number isn't spun: wins, losses, and unresolved picks are all counted. Use it to calibrate. A 70% `STRONG_BUY` record means treating those picks as tradeable. A 45% `BUY` record means treating those picks as starting points for your own research, not trade signals. ## Access The scanner is part of the Dashboard tier (1M `$CLAUDIA`). Auto-scans and reading the latest result are free — only manual refresh spends credits. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.claudia.wtf/using-the-platform/scanner.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.