firecrawl-agent: a Claude Code skill by Firecrawl
Official
For people who need structured data pulled from sites that take many pages to navigate. Skip it if one page scrape is enough or you won't pay for Firecrawl credits.
- Score
- 78of 100
- Rank
- #76of 239
- Installs
- 82Kon skills.sh
- Security
- Mixed 5 scanners
- Updated
- 2026
- Context
- ~47tokens always
Install
npx skills add https://github.com/firecrawl/cli --skill firecrawl-agent Run it in your terminal. View the source
Using the Claude app rather than Claude Code? You can add a skill there too. How to add it in the app
What does firecrawl-agent do?
firecrawl-agent is a Claude skill that runs firecrawl agent, a hosted job that browses sites on its own and returns structured data in two to five minutes. Claude first searches Alexandria, Firecrawl's catalog of ready-made data providers, and uses a match through firecrawl scrape --alexandria if it covers the task. Otherwise it runs the agent with a prompt, an optional JSON --schema, --urls, and --wait --json -o .firecrawl/<name>.json. It can return a job ID to poll or cancel, cap spend with --max-credits, and pause before paid provider calls with --require-approval. It can also send session feedback that refunds credits.
When should you use firecrawl-agent?
Use it when
- You need pricing or product lists from a whole site
- The data sits behind several clicks or pages
- You want output that fits a JSON schema
Skip it when
- A single page scrape will do
- You can't send target URLs to an outside service
What it needs and what it can touch
You need
- The Firecrawl CLI and a Firecrawl account with credits
What it can do
- Runs shell commands (firecrawl)
- Sends data to an outside service (Firecrawl)
- Writes JSON results to a .firecrawl folder
From reading its instructions, not from running it.
Why it scores 78
Strongest on upkeep (100 of 100), weakest on adoption (53).
Is firecrawl-agent safe to install?
At least one scanner raised a medium warning. Read the results below. Scanners often miss what other scanners catch, and a skill can change after a scan. Read its source before you install it.
| Scanner | Result | Date |
|---|---|---|
| Gen Agent Trust Hub | Passed | Oct 18, 2026 |
| Socket | Passed | Oct 18, 2026 |
| Snyk | Medium risk | Oct 18, 2026 |
| Runlayer | Passed | Mar 10, 2026 |
| ZeroLeaks | Passed | Apr 15, 2026 |
Details
- Installs
- 81,968
- Repository stars
- 684
- Last repository change
- Tokens always loaded
- about 47
- Tokens when used
- about 1,134
- License
- Not stated
- Data confidence
- High
Did it do the job for you?
Alternatives to firecrawl-agent
All skills for this job- Get firecrawl-scrape
firecrawl-scrape
For people who have a URL and want its content as markdown or typed JSON.
- Get firecrawl-search
firecrawl-search
For people who want Claude to search the web from the terminal and keep results with excerpts as JSON.
-
Get tavily-searchtavily-search
For anyone who wants Claude to check current facts, news or sources on the web through Tavily.
-
Get agent-browseragent-browser
For developers who want Claude to drive Chrome from the terminal to click, fill forms and take screenshots.
firecrawl-agent