firecrawl

firecrawl is a skill for Claude Code, Codex from intentic/intentic. It costs 52 tokens per session (965 once invoked), scanned A, original, MIT.

A web-research tool that turns pages and websites into clean Markdown text. It can read one page, find a site's URLs, collect multiple pages, or search the web.

In plain words
What is it for?
Use it to scrape a known page, map a website before choosing pages, crawl a site when many pages are needed, or search the web for research.
Why use it?
It avoids manually copying web pages and helps separate the useful page content from navigation and other boilerplate.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it to scrape a known page, map a website before choosing pages, crawl a site when many pages are needed, or search the web for research.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/intentic/intentic/firecrawl
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.

Any agent
npx skills add intentic/intentic --skill firecrawl
Clone the repo
git clone --depth 1 https://github.com/intentic/intentic

Made for: Claude Code, Codex.

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 firecrawl

README.md
[![agentmods](https://agentmods.dev/badge/skills/intentic/intentic/firecrawl.svg)](https://agentmods.dev/skills/intentic/intentic/firecrawl)
Your own site
<a href="https://agentmods.dev/skills/intentic/intentic/firecrawl"><img src="https://agentmods.dev/badge/skills/intentic/intentic/firecrawl.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 965 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00052 $0.00965
Opus 5 $0.00026 $0.00483
Sonnet 5 $0.00010 $0.00193
Haiku 4.5 $0.00005 $0.00097

Measured today against content hash 103e2b5e7bd7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

firecrawl scanned grade A with 1 finding 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 today.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

fc() { curl -s -X POST -H "Authorization: Bearer $FIRECRAWL_API_KEY" -H "Content-Type: application/json" \
_extensions/connectors/skills/firecrawl/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Firecrawl (connected)

Key in $FIRECRAWL_API_KEY, base in $FIRECRAWL_API_URL (https://api.firecrawl.dev unless self-hosted). Everything is POST /v2/<endpoint> with a JSON body. Define this helper once per shell: fc <path> '<json>':

fc() { curl -s -X POST -H "Authorization: Bearer $FIRECRAWL_API_KEY" -H "Content-Type: application/json" \
  -d "$2" "$FIRECRAWL_API_URL/v2/$1"; }

Responses are {success, data} (or {success:false, error}: read error, it says what was wrong). This is metered: one page ≈ one credit. Prefer scrape on a known URL and map to find one; reach for crawl only when whole-site content is genuinely wanted, and always pass limit.

  • Scrape one page: fc scrape '{"url":"<URL>","formats":["markdown"]}' | jq -r '.data.markdown', .data.metadata carries {title, description, sourceURL, statusCode}
  • Keep the page's own boilerplate out (default) or bring it back: "onlyMainContent": false. For a JS-heavy page add "waitFor": 3000
  • Just the links / a summary: "formats":["links"].data.links · "formats":["summary"].data.summary
  • Structured fields out of a page: fc scrape '{"url":"<URL>","formats":[{"type":"json","prompt":"the price and the release date","schema":{"type":"object","properties":{"price":{"type":"string"},"released":{"type":"string"}}}}]}' | jq '.data.json'
  • Map a site's URLs, cheap, and the right first move on an unfamiliar site: fc map '{"url":"<URL>","limit":100}' | jq -r '.links[] | .url' (add "search":"<TERM>" to order by relevance)
  • Search the web: fc search '{"query":"<QUERY>","limit":5}' | jq -c '.data.web[] | {title, url, description}', add "scrapeOptions":{"formats":["markdown"]} to get each hit's text in the same call, and narrow with "includeDomains":["example.com"], "categories":[{"type":"research"}] or "tbs":"qdr:w" (past week)
  • Several known URLs at once: fc batch/scrape '{"urls":["<URL1>","<URL2>"],"formats":["markdown"]}', async, polls like a crawl below

Read the full file on GitHub · 45 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. today First seen · 45 lines · 52 tokens per session scan A 103e2b5e7bd7

Subscribe to this mod's changes

firecrawl is a skill published in the GitHub repository intentic/intentic (32 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 965 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.

Related

Other skills, from other repositories

telegram

Owner-only Telegram text bridge and Mini App gateway for the existing Ouroboros interface.

razzant/ouroboros · 19 tokens

claudexor

Use the local Claudexor control plane for harness-agnostic coding work across Claude Code, Codex, Cursor, and OpenCode. Use when a task benefits from route-aware harness and account selection, quota-aware account rotation, shared thread context, read-only planning or research, best-of-N execution, or cross-harness…

razzant/claudexor · 73 tokens

openai-docs

Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, latest/current/default-model prompting guidance, or model upgrade and prompt-upgrade guidance; use…

rojim666/SztuCode · 105 tokens

cursor-delegate

Delegate bounded light-to-medium implementation, investigation, documentation, configuration, testing, and tooling work to Cursor Bridge after the primary agent owns direction and risk boundaries. Also use when the user explicitly asks to create, keep, continue, inspect, or close the same Cursor execution session…

Vanyangyang/cursor-bridge · 151 tokens

discovery-process

Run a full discovery cycle from problem hypothesis to validated solution. Use when a team needs a structured path through framing, interviews, synthesis, and experiments.

getcrew44/crew44 · 34 tokens

company-research

Create a company research brief with executive quotes, product strategy, and org context. Use when preparing for interviews, competitive analysis, partnerships, or market-entry work.

getcrew44/crew44 · 36 tokens