# AgentShelf Regex Mention Extractor

> AgentShelf Regex Mention Extractor is a paid API for AI agents from agentshelf.syntexa.ch, paid per call via x402, $0.009/call, status unknown (last checked 2026-10-02).

Extracts all @-mention strings from text using regex, returning up to 20 matches per call.

## Facts

- Endpoint: POST https://agentshelf.syntexa.ch/v1/regex-mention?utm_source=zero.xyz
- Price: $0.009/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentshelf-regex-mention-extractor-40382a0e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_7vup_nw7hyHGzQz7VnsaI

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability agentshelf-regex-mention-extractor-40382a0e -d '<json body>'
```

Example prompt: Can you extract all the @mentions from this text: 'Hey @alice and @bob, please review the PR — cc @devteam'?

## When to prefer this

Use this endpoint when you need fast, deterministic regex-based @mention extraction without any LLM or network overhead. It is ideal for structured pipelines processing social media text, notifications, or comments where cost predictability and speed matter. Prefer the free POST /v1/sandbox/regex-mention endpoint for testing or unpaid usage. Avoid this endpoint if your text reliably has no mentions, as empty results are still billed.

## Known failure modes

- Empty match list returned but still billed if no @mentions are present in text
- Input text exceeds 100,000 character limit causing a validation error
- Malformed or missing 'text' field in request body causes a bad request error
- More than 20 mentions in text results in truncation at 20 matches

## How this service works

Call when an agent needs at-mentions extracted from text, capped at 20 matches. An empty match list is billed. No network. Exact $0.009 USDC. Prefer unpaid POST /v1/sandbox/regex-mention first.

## Output

A list of up to 20 matched @-mention strings found in the input text, extracted via regex pattern matching. If no mentions are found, an empty list is returned — but the call is still billed at $0.009 USDC.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "examples": [
    "@hello"
   ],
   "maxLength": 100000,
   "minLength": 1,
   "description": "Input for this SKU. The route description says whether it is plain text, a URL, base64 bytes, or an already-encoded token."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentshelf-regex-mention-extractor-40382a0e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentshelf.syntexa.ch](https://www.zero.xyz/host/agentshelf.syntexa.ch/llms.txt)