# AgentShelf HTML Tag Regex Extractor

> AgentShelf HTML Tag Regex Extractor is a paid API for AI agents from agentshelf.syntexa.ch, paid per call via x402, $0.002/call, status unknown (last checked 2026-10-19).

Extracts up to 20 HTML tag matches from input text using regex, returning matched tags as a list.

## Facts

- Endpoint: POST https://agentshelf.syntexa.ch/v1/regex-html-tag?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-19
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentshelf-html-tag-regex-extractor-04f1a2b1
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_soS5DcWthLYpZo1zcmjnM

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-html-tag-regex-extractor-04f1a2b1 -d '<json body>'
```

Example prompt: Can you extract all the HTML tags from this text for me: '<div class="header"><h1>Hello</h1><p>World</p></div>'?

## When to prefer this

Use this endpoint when you need a quick, lightweight regex-based extraction of HTML tags from a text string without setting up a full HTML parser. Ideal for agents that need to detect, audit, or inventory HTML tags in snippets or user-supplied content. If cost is a concern and a free sandbox alternative exists at POST /v1/sandbox/regex-html-tag, prefer that first. Not suitable for structured DOM traversal or attribute extraction beyond tag names.

## Known failure modes

- Empty match list returned when no HTML tags are found in the input (still billed)
- Input text exceeds 100,000 character limit — request rejected
- Match count capped at 20 — only first 20 HTML tags returned even if more exist
- Malformed or non-HTML input may yield zero matches without error

## How this service works

Call when an agent needs HTML tags extracted from text, capped at 20 matches. An empty match list is billed. No network. Exact $0.002 USDC. Prefer unpaid POST /v1/sandbox/regex-html-tag first.

## Output

A list of up to 20 matched HTML tag strings found within the input text, extracted via regex. If no HTML tags are present, an empty match list is returned. Note: an empty result is still billed at $0.002 USDC.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "examples": [
    "<p>"
   ],
   "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-html-tag-regex-extractor-04f1a2b1/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)