firecrawl-monitor Skill: Get Alerts When a Web Page Changes
Makes your coding assistant set up Firecrawl monitors that alert you by email or webhook when web pages change.
- Installs
- 33.4K
- on skills.sh
- Stars
- 676
- on GitHub
- Files
- 2
- besides SKILL.md
- Updated
- Oct 2026
- last repo commit
firecrawl-monitor teaches your assistant to run firecrawl monitor create for recurring checks. A monitor can watch one page, a list of URLs, a whole site, or the web for new results that match a goal. Firecrawl fetches, compares and judges the changes on its servers, then sends an email or webhook.
You must install the Firecrawl CLI and sign in. Every check uses credits, the shortest schedule is 5 minutes, and monitoring is not available for zero-data-retention teams.
Good for
- Product and pricing teams who watch competitor pricing pages
- Job seekers and recruiters who track new postings
- Developers who want alerts when docs or status pages change
- Researchers who want new web results for a goal sent to them
Install firecrawl-monitor
Claude Code
- 1
Copy this prompt.
Install the firecrawl-monitor skill in Claude Code. Run this command: npm install -g firecrawl-cli@latest firecrawl login --browser npx skills add https://github.com/firecrawl/cli --skill firecrawl-monitor -a claude-code Then check that it loaded and tell me how to use it.
- 2
Paste it into Claude Code. It shows the change and asks before running it.
Requires Node.js, A Firecrawl account (or the keyless free tier).
The skill only gives your assistant instructions. The Firecrawl command line tool does the work, so install it and sign in first. Monitor needs an account: the install rules list it among the commands that prompt a login when no credentials are set. The one-command route installs the CLI, signs you in through the browser and adds the core and workflow skills for every editor it detects, not just this skill.
From the vendor's docs. Source.
What's in the skill
When it loads
Alert by webhook/email on web changes — use for "monitor/watch/track/alert me when": recurring checks on known URLs (prefer over repeated one-off scrapes) or web-wide watches for new results (queries + goal).
Sections in SKILL.md
- Quick start
- Constraints & tips
- See also
Key facts
- Author
- firecrawl org
- Repo
- firecrawl/cli
- Installs on skills.sh
- 33,447 as of 2026-11-02
- GitHub stars
- 676 for the whole firecrawl/cli repo, 2026-11-02
- Last commit to the repo
- 2026-10-28
- Related skills
- firecrawl-scrape, firecrawl-crawl, firecrawl
- skills.sh audits
- Gen Agent Trust Hub pass, Socket pass, Snyk warn (2026-11-02)
What it includes
Watches one page for changes
Takes a name, a schedule in plain words, a goal and where to alert. Example in the skill: every 30 minutes, alert when a new blog post is published.
Try: “Monitor example.com/blog every 30 minutes and email me when a new post appears.”
Runs code ·
monitor create --page <url>Watches a list of URLs or every page of a site
URL batch mode takes comma-separated URLs. Whole-site mode takes a root URL and watches each page a crawl finds.
Runs code ·
--scrape-urls and --crawl-urlWatches the whole web for new matching results
Runs your queries each check and alerts on results it has not seen before. --goal is required with --queries.
Runs code ·
--queries and --goalSets where alerts go
External email recipients get a confirmation email first and only receive alerts after they confirm. Team-owned addresses are confirmed automatically.
Write ·
--email and --webhook-urlLists monitors and inspects their checks
Pages in a check are labeled same, new, changed, removed or error. --page-status filters them.
Runs code ·
monitor list, get, checks, checkRuns a check right now
The skill uses it to smoke-test a new monitor.
Runs code ·
monitor runPauses a monitor
Pause to silence a monitor; delete is for monitors that are done.
Runs code ·
monitor update --state pausedRemoves a monitor for good
The skill reserves it for monitors that are permanently done.
Delete ·
monitor deleteGuides for goals and per-field change tracking
goals.md explains how to write the --goal sentence. json-tracking.md covers structured diffs, such as a price changing from one value to another, set up with a JSON file.
Read ·
goals.md and json-tracking.md
From the official docs
Permissions
Medium risk
This skill creates recurring monitors that spend credits and send alerts to emails and webhooks you name. Check each monitor, and pause the ones you no longer need.
What it can do
- Read your data
- Create and change things
- Delete things
- Read-only mode
Watch out for
Monitors keep running and spending credits
Each check uses credits and a monitor can run as often as every 5 minutes. Pause a monitor with update --state paused, and review firecrawl monitor list. github.com
Alerts go to emails and webhooks you name
Check every address and URL the assistant adds. External email recipients must confirm before they receive alerts. github.com
Snapshots are stored for comparison
--retention-days controls how long snapshots are kept for diffing. Lower it for high-frequency monitors. github.com
Web pages can try to steer your assistant
The skill's own security note calls fetched web content untrusted and says it may contain prompt injection. Do not let the assistant follow instructions it finds on a page. github.com
Setup installs a global npm package
The CLI is installed with npm install -g. The one-command setup also adds skills to every coding editor it detects, so use the single-skill route if you want only this one. github.com
The CLI sends anonymous usage data
The README says it collects the CLI version, OS, Node.js version and which dev tools it detects during sign-in. Set FIRECRAWL_NO_TELEMETRY=1 to turn it off. github.com
Security advisories
No published security advisories as of Nov 2, 2026.
Technical details
| Turning on read-only | No read-only mode. The skill runs CLI commands that spend credits and write files. |
|---|---|
| Talks to | Firecrawl's API, or your own server if you set --api-url. Web pages the CLI fetches. Page content the assistant reads goes to your AI provider as part of the chat |
| Sign-in and keys | Browser sign-in stores credentials in the CLI. You can set FIRECRAWL_API_KEY instead. |
| Scopes |
|
Questions
What does firecrawl-monitor do?
It makes your assistant create Firecrawl monitors. A monitor checks pages or the web on a schedule and sends an email or webhook when something changes or something new appears.
How do I install firecrawl-monitor?
Use the install box at the top of this page. You need the Firecrawl CLI and a sign-in as well as the skill. The one-command route installs the whole core skill set.
Do I need a Firecrawl account?
Yes. The install rules list monitor among the commands that prompt a login when no credentials are set. Monitoring is also not available for zero-data-retention teams.
How often can a monitor run, and what does it cost?
The shortest schedule is 5 minutes. Each check uses credits for its scrape, crawl or search, plus optional judging. The SKILL.md links to the Firecrawl monitoring pricing page instead of listing prices.
Is firecrawl-monitor safe to use?
It creates recurring jobs that keep spending credits until you pause or delete them, and it sends alerts to the emails and webhook URLs you give. List your monitors now and then with firecrawl monitor list.
Why does it prefer a monitor over repeated scrapes?
The SKILL.md says to prefer one monitor whenever the same URL should be checked more than once, because Firecrawl does the fetching, diffing and notifying on its side.
Skill or Firecrawl MCP server?
They are two routes to Firecrawl. firecrawl-monitor is a SKILL.md that tells the assistant to run the Firecrawl CLI in your shell. The skill only allows Bash(firecrawl *) and Bash(npx firecrawl-cli *), so it needs an assistant that can run shell commands. The Firecrawl MCP server and the local Firecrawl MCP server give your client Firecrawl as tools it calls directly, with no skill involved. The README describes firecrawl setup mcp for adding the MCP server to your editors. You can use either route, or both.
Information
updated Nov 2, 2026
- Repository
- firecrawl/cli
- Folder
skills/firecrawl-monitor
Sources
Docs, issue trackers and discussions this page is built from.
Show all 7Hide
- Firecrawl CLI install rules · github.com
- firecrawl/cli README · github.com
- skills CLI commands · github.com
- firecrawl-monitor SKILL.md · github.com
- goals.md · github.com
- json-tracking.md · github.com
- Firecrawl security rules · github.com