From obul-search
USE THIS SKILL WHEN: the user wants to search the web and get scraped content from results. Provides web search with auto-scraped markdown via Firecrawl through the Obul proxy.
How this skill is triggered — by the user, by Claude, or both
Slash command
/obul-search:firecrawl-searchThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Firecrawl's web search endpoint — search the web and get clean, scraped content from the results in a single call.
Firecrawl's web search endpoint — search the web and get clean, scraped content from the results in a single call. Through the Obul proxy, each request is paid individually — no Firecrawl account or API key required.
All requests use the obulx CLI, which handles proxy routing and authentication automatically.
Install and log in (one-time setup):
npm install -g @obul.ai/obulx
obulx login
Base URL: https://firecrawl.x402endpoints.com
Search the web and get clean, scraped content from the results. Useful for finding and reading pages on a topic without knowing specific URLs.
Pricing: $0.002
obulx -X POST -H "Content-Type: application/json" \
-d '{"query": "firecrawl web scraping API", "limit": 5}' \
"https://firecrawl.x402endpoints.com/v1/search"
Response: Array of search results, each containing the page URL, title, and scraped content in clean markdown format.
Search and control how result pages are scraped — request specific formats, include only certain tags, or exclude elements like navigation.
Pricing: $0.002
obulx -X POST -H "Content-Type: application/json" \
-d '{"query": "x402 payment protocol", "limit": 3, "scrapeOptions": {"formats": ["markdown", "links"]}}' \
"https://firecrawl.x402endpoints.com/v1/search"
Response: Search results with content in the requested formats. The links format returns all URLs found on each
result page.
Restrict search results to a specific time period using the tbs parameter.
Pricing: $0.002
obulx -X POST -H "Content-Type: application/json" \
-d '{"query": "x402 ecosystem news", "tbs": "qdr:w", "lang": "en"}' \
"https://firecrawl.x402endpoints.com/v1/search"
Response: Search results filtered to the specified time period. tbs values: qdr:h (past hour), qdr:d (past
day), qdr:w (past week), qdr:m (past month).
| Endpoint | Price | Purpose |
|---|---|---|
POST /v1/search | $0.002 | Web search with scraped content |
limit to control cost — Default is 5 results. Increase for broader research, decrease for quick lookups.scrapeOptions — Control output formats (markdown, html, links) to get exactly what you need.tbs for time-sensitive queries to get fresh results.| Error | Cause | Solution |
|---|---|---|
402 Payment Required | Payment not processed or insufficient | Verify your account has sufficient balance at my.obul.ai. Run obulx login if not authenticated. |
400 Bad Request | Missing or invalid request body | Ensure the query field is present and non-empty. |
429 Too Many Requests | Rate limit exceeded | Add a short delay between requests. |
500 Internal Server Error | Upstream Firecrawl service issue | Wait a few seconds and retry. |
npx claudepluginhub polymerdao/pay-plugin --plugin obul-searchProvides web search with full page content extraction using Firecrawl CLI. Returns search results as JSON with optional markdown scraping. Use for research, finding articles, or discovering sources.
Performs web search and scraping with context isolation using Python subprocesses. Only curated output enters the context, saving 100-200x tokens. Triggered by 'search for', 'look up', 'find', 'research'.
Performs AI-optimized web searches via Tavily API, returning clean snippets for current information and news.