⚙ Blueprint
Scam Checker
Get a plain verdict on suspicious emails and texts before anyone in the family clicks.
- Goal
- Get a plain verdict on suspicious emails and texts before anyone in the family clicks.
- Runs
- ⏱ Every morning, plus any time you forward something suspicious
- Watches
- 👁 New email (read-only), or messages you forward to it
What it does, step by step
- Reads new emails, or anything you forward.
- Looks for scam signs: fake sender, lookalike link, urgency, payment request.
- Gives a risk level and the exact red flags.
- Tells you the safe next step.
Paste these starter instructions
Copy, paste into your tool, and replace the [brackets] with your details.
You are my Scam Checker. For each message you check, answer in this format: VERDICT: Confirmed scam / High suspicion / Possible / Looks fine RED FLAGS: (sender address, links that don't match, urgency, requests for money, gift cards, passwords or codes) WHAT TO DO: one or two safe steps (for example: don't click, delete, report it, or call the company on a number from their official website). Rules: you are read-only. Never click links, open attachments, reply or delete.
Which tool to use
- agentGrok Bot (personal agents)Daily routine; templates shared publiclyCheck plan requirements in xAI's docs
- agentGemini SparkScheduled check over GmailGoogle AI Pro and Ultra subscribers in select countries
- chatChatGPTEasiest for parents: paste or screenshot the messageFree plan; paid plans add more
- chatClaudePaste the messageFree plan; paid plans add more
What this costs to run
If you run this bot yourself on an AI API: our assumption is 30 runs a month, each reading about 3,000 tokens and writing about 300 (one morning sweep of flagged messages plus the odd forwarded one, about 3,000 tokens a day). That's about 90,000 tokens in and 9,000 out a month.
| Model | Price per 1M tokens (in / out) | About per month |
|---|---|---|
| Anthropic Claude Haiku 5.5 | $0.10 / $0.50 | $0.01 |
| Google gemini-3.8-flash | $0.75 / $3.75 | $0.10 |
| Anthropic Claude Sonnet 5.5 | $2.00 / $10.00 | $0.27 |
| OpenAI gpt-6-astra | $10.00 / $50.00 | $1.35 |
Token counts are our editor's estimates, not measurements. Real use can be several times higher if the agent browses the web or uses tools: Anthropic says its browser toolset alone adds about 6,600 input tokens per request.
Try other models and numbers in the cost calculator →
Prices are standard API rates from each provider's official pricing page, checked Oct 21, 2026 (full price table). If you use an app plan (Grok Bot, ChatGPT, Claude, Gemini, Meta Muse) the bot runs inside your plan's limits instead of being billed per token. How to run your bots for less →
How to set it up
- Pick one boring job. Choose ONE small job you do every week, like reading school emails or checking a web page.
- Pick your tool. Use what you already have.
- Paste the instructions and fill in the [brackets]. Open a new chat in the tool.
- Say “Run this once now and show me the result”. Don't schedule anything yet.
- Then say “Do this every [day/time]” and lock it down. Once the result looks right, ask it to repeat on a schedule.
Safety notes
- Read-only, always.
- A 'looks fine' verdict isn't a guarantee. When money is involved, call the company on a number you already trust.