Skip to main content
skill CX Codex

9routerx-web-fetch — Claude Code skill: URL fetching and setup

The 9routerx-web-fetch Claude Code skill retrieves webpage content as Markdown, plain text, or HTML. The agent uses it to read an article or extract material from a URL.

MIT ★ 259 updated 2026-11-16

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add yanstd888/9routerx --skill 9routerx-web-fetch -a claude-code
Open on GitHub

What 9routerx-web-fetch does

The skill sends a URL to 9RouterX through POST /v1/web/fetch and returns the page content. Choose markdown, text, or html as the output format, and set a character limit if needed. Requests can use providers such as firecrawl, jina-reader, tavily, exa, or ollama.

The fetch-combo option chains providers and switches automatically when one fails. A running 9RouterX server and its address in 9ROUTERX_URL are required; when authentication is enabled, set 9ROUTERX_KEY as well. The ollama provider uses the key from an existing ollama connection. Requests cannot run without an accessible server.

What it helps with

  • extract text from a webpage URL
  • convert an article to Markdown or HTML
  • cap the length of extracted page content
  • fetch page content through a chosen provider

Example prompts for the agent

  • Read the article at this URL and return it as Markdown.
  • Extract this page's text and limit the result to the requested number of characters.
  • Fetch this page as HTML using firecrawl.

How to install 9routerx-web-fetch

1Skills CLI (Vercel)

npx skills add yanstd888/9routerx --skill 9routerx-web-fetch -a claude-code

2Manually: put the files in place

~/.claude/skills/9routerx-web-fetch/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/9routerx-web-fetch/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about 9routerx-web-fetch

How do I install 9routerx-web-fetch in Claude Code?

Run npx skills add yanstd888/9routerx --skill 9routerx-web-fetch -a claude-code. The skill file is located at ~/.claude/skills/9routerx-web-fetch/SKILL.md.

What does 9routerx-web-fetch do?

It retrieves content from a URL through 9RouterX and returns it as Markdown, plain text, or HTML.

What does 9routerx-web-fetch need to run?

It needs a running 9RouterX server and its address in 9ROUTERX_URL. Set 9ROUTERX_KEY when authentication is enabled; the ollama provider uses the key from an existing ollama connection.

Source text

SKILL.md · MIT
---
name: 9routerx-web-fetch
description: Fetch URL → markdown / text / HTML via 9RouterX /v1/web/fetch using Ollama Cloud / Firecrawl / Jina Reader / Tavily Extract / Exa Contents. Use when the user wants to scrape a webpage, extract URL content, read article, or convert a URL to markdown.
---

# 9RouterX — Web Fetch

Requires `9ROUTERX_URL` (and `9ROUTERX_KEY` if auth enabled). See https://raw.githubusercontent.com/yanstd888/9routerx/refs/heads/main/skills/9routerx/SKILL.md for setup.

## Discover

```bash
curl $9ROUTERX_URL/v1/models/web | jq '.data[] | select(.kind=="webFetch") | .id'
# Per-provider params
curl "$9ROUTERX_URL/v1/models/info?id=firecrawl/fetch"
```

IDs end in `/fetch` (e.g. `firecrawl/fetch`, `jina/fetch`). `fetch-combo` chains providers with auto-fallback.

## Endpoint

`POST $9ROUTERX_URL/v1/web/fetch`

| Field | Required | Notes |
|---|---|---|
| `model` (or `provider`) | yes | from `/v1/models/web` (e.g. `firecrawl` or `jina-reader`) |
| `url` | yes | URL to extract |
| `format` | no | `markdown` (default) / `text` / `html` |
| `max_characters` | no | truncate output |

## Examples

### Jina Reader
```bash
curl -X POST $9ROUTERX_URL/v1/web/fetch \
  -H "Authorization: Bearer $9ROUTERX_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"jina-reader","url":"https://9router.com","format":"markdown"}'
```

### Exa
```bash
curl -X POST $9ROUTERX_URL/v1/web/fetch \
  -H "Authorization: Bearer $9ROUTERX_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"exa","url":"https://example.com","format":"markdown","max_characters":0}'
```

### Firecrawl
```bash
curl -X POST $9ROUTERX_URL/v1/web/fetch \
  -H "Authorization: Bearer $9ROUTERX_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"firecrawl","url":"https://example.com","format":"markdown","max_characters":0}'
```

### Tavily
```bash
curl -X POST $9ROUTERX_URL/v1/web/fetch \
  -H "Authorization: Bearer $9ROUTERX_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"tavily","url":"https://example.com","format":"markdown","max_characters":0}'
```

### Ollama Cloud

Uses the API key from the existing `ollama` connection.

```bash
curl -X POST $9ROUTERX_URL/v1/web/fetch \
  -H "Authorization: Bearer $9ROUTERX_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"ollama","url":"https://example.com","format":"markdown"}'
```


JS:

```js
const r = await fetch(`${process.env.9ROUTERX_URL}/v1/web/fetch`, {
  method: "POST",
  headers: { "Authorization": `Bearer ${process.env.9ROUTERX_KEY}`, "Content-Type": "application/json" },
  body: JSON.stringify({ model: "fetch-combo", url: "https://example.com", format: "markdown", max_characters: 5000 }),
});
const { data } = await r.json();
console.log(data.title, data.content.length);
```

## Response shape

```json
{
  "provider": "jina-reader",
  "url": "...",
  "title": "...",
  "content": { "format": "markdown", "text": "...", "length": 1234 },
  "links": ["https://example.com/related"],
  "metadata": { "author": null, "published_at": null, "language": null },
  "usage": { "fetch_cost_usd": 0 },
  "metrics": { "response_time_ms": 850, "upstream_latency_ms": 700 }
}
```

`links` is included when the upstream provider returns discovered page links (currently Ollama Cloud).

## Provider quirks

| Provider | Auth | Best for |
|---|---|---|
| `firecrawl` | Bearer | JS-rendered pages, `format=markdown/html` |
| `jina-reader` | Bearer (optional) | Free tier (~1M chars/mo); fastest plain markdown |
| `tavily` | Bearer | Bulk extract; returns `raw_content` |
| `exa` | `x-api-key` | Pre-indexed pages; fast text extraction |
| `ollama` | Bearer | Markdown plus page title and discovered links; uses the Ollama Cloud key |

© yanstd888 · MIT · yanstd888/9routerx

Similar skills

All skills for Browser and scraping →

From the same set9

9routerx-embeddings The 9routerx-embeddings Claude Code skill creates text embeddings through the 9RouterX API. The agent uses it for RAG, semantic search, and text similarity tasks. CX Codex +1 ★ 259repo stars 9routerx-chat The 9routerx-chat Claude Code skill sends language-model requests through 9RouterX. It activates for code generation, text summaries, and other prompts to a model. CX Codex +1 ★ 259repo stars 9routerx Claude Code skill connects your agent to the 9RouterX gateway. It routes OpenAI-compatible REST calls for chat, speech, embeddings, and web fetch to multiple AI models. CX Codex +1 ★ 259repo stars 9routerx-tts The 9routerx-tts Claude Code skill turns text into speech through the 9RouterX API. It runs for voiceovers, generated audio, or reading text aloud. CX Codex +1 ★ 259repo stars 9routerx-image The 9routerx-image Claude Code skill creates images through the 9RouterX API. It activates when a request asks for a picture or text-to-image generation. CX Codex +1 ★ 259repo stars 9routerx-stt 9routerx-stt — a skill for Claude Code and Codex that routes audio transcription requests through 9RouterX. Transcribes voice recordings and generates subtitle files across multiple model backends. CX Codex +1 ★ 259repo stars 9routerx-video The 9routerx-video Claude Code skill creates videos through xAI Grok Imagine. It runs when asked to generate a clip from text or an image. CX Codex +1 ★ 259repo stars 9routerx-web-search The 9routerx-web-search Claude Code skill searches the web and public X posts through 9RouterX. It runs when an agent is asked to find articles, information, or posts on X. CX Codex +1 ★ 259repo stars

Project sponsors

Companies that keep this analytics open