setup-firecrawl

setup-firecrawl is a command for Cursor from maccman/growth-agents. It costs 0 tokens per session (1,466 once invoked), scanned A, original, MIT.

A guided setup command for Firecrawl, a web data service that turns website content into text or structured information that software can process.

In plain words
What is it for?
Preparing a project to scrape pages, crawl websites, search the web, discover site URLs, extract selected information, or use an interactive browser through Firecrawl.
Why use it?
It removes the need to work out the installation, API key, and project configuration steps by hand. It also explains when to use its command-line tool or JavaScript library.

Command for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/maccman/growth-agents/setup-firecrawl
Clone the repo
git clone --depth 1 https://github.com/maccman/growth-agents

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for setup-firecrawl

README.md
[![agentmods](https://agentmods.dev/badge/commands/maccman/growth-agents/setup-firecrawl.svg)](https://agentmods.dev/commands/maccman/growth-agents/setup-firecrawl)
Your own site
<a href="https://agentmods.dev/commands/maccman/growth-agents/setup-firecrawl"><img src="https://agentmods.dev/badge/commands/maccman/growth-agents/setup-firecrawl.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,466 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01466
Opus 5 $0.00000 $0.00733
Sonnet 5 $0.00000 $0.00293
Haiku 4.5 $0.00000 $0.00147

Measured 4d ago against content hash 3fcd760623da, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup-firecrawl scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/commands/setup-firecrawl.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When the user triggers this action, walk them through setting up Firecrawl for this project. Run each step automatically. Speak in plain, friendly language.

What is Firecrawl?

Firecrawl is a web data API that turns any website into clean, LLM-ready markdown or structured data. It handles proxies, rate limits, JavaScript-rendered pages, and anti-bot mechanisms so you don't have to. Key capabilities:

  • Scrape — extract content from a single URL as markdown, HTML, JSON, screenshots, or links
  • Crawl — scrape all pages of a website automatically
  • Search — search the web and get full page content from results
  • Map — discover all URLs on a site instantly
  • Extract — get structured data from pages using AI prompts and schemas
  • Agent — gather data from the web using natural language prompts
  • Browser — launch cloud browser sessions for interactive scraping

When to use the CLI vs the SDK

  • CLI (firecrawl) — preferred for simple, one-off tasks: quick scrapes, searches, site maps, piping output to other tools. Use it whenever a shell one-liner will do.
  • SDK (@mendable/firecrawl-js) — use in TypeScript scripts when you need programmatic control, structured extraction with Zod schemas, or integration into larger workflows.

Steps

  1. Install the CLI and authenticate via browser — This single command installs the CLI globally and opens the browser for Firecrawl authentication:

    npx -y firecrawl-cli@latest init --agent cursor --browser
    
    • --agent cursor installs the Firecrawl skill only for Cursor
    • --browser opens the browser for authentication automatically

    If the browser auth doesn't work, fall back to manual login:

    npm install -g firecrawl-cli
    firecrawl login --browser
    

    Or if the user already has an API key (get one at firecrawl.dev/app/api-keys):

    firecrawl login --api-key <their key>
    

Read the full file on GitHub · 167 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 167 lines · 0 tokens per session scan A 3fcd760623da

Subscribe to this mod's changes

setup-firecrawl is a command published in the GitHub repository maccman/growth-agents (5 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,466 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.