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.
npx skills add fredabila/orcbot --skill firecrawl-cligit clone --depth 1 https://github.com/fredabila/orcbotWrote 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.
[](https://agentmods.dev/skills/fredabila/orcbot/firecrawl-cli)<a href="https://agentmods.dev/skills/fredabila/orcbot/firecrawl-cli"><img src="https://agentmods.dev/badge/skills/fredabila/orcbot/firecrawl-cli/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fredabila/orcbot/firecrawl-cli"><img src="https://agentmods.dev/badge/skills/fredabila/orcbot/firecrawl-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00081 | $0.01488 |
| Opus 5.5 | $0.00032 | $0.00595 |
| Sonnet 5.5 | $0.00016 | $0.00298 |
| Haiku 4.5 | $0.00008 | $0.00149 |
Grade A, and why
firecrawl-cli 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Firecrawl CLI Skill
Overview
Firecrawl provides a cloud browser and AI extraction layer on top of any website. Unlike OrcBot's local Playwright browser, Firecrawl runs browser sessions on remote infrastructure, handles bot-protection (Cloudflare, reCAPTCHA, etc.), and can return pre-formatted markdown or structured JSON without you parsing HTML.
Browser Decision Guide
Always choose the right browser for the job:
| Situation | Use |
|---|---|
| Simple page, just need to read content | browser_navigate (Playwright, free, fast) |
| Need to click buttons, fill forms, interact | browser_navigate + browser_click + browser_type |
| Page is bot-protected, Cloudflare, requires JS | firecrawl_scrape |
| Need clean markdown without any DOM work | firecrawl_scrape |
| Need bulk content from many pages | firecrawl_crawl |
| Need structured JSON from web data | firecrawl_agent |
| Need to drive a session step by step in cloud | firecrawl_browser |
Do NOT replace working browser_navigate calls with firecrawl_scrape just because firecrawl is installed. Use firecrawl when local Playwright fails or when the task specifically benefits from cloud execution.
Setup
# Install the CLI globally
npm install -g firecrawl-cli
# Authenticate (choose one)
firecrawl login # interactive browser login
firecrawl login --api-key fc-YOUR-KEY # direct API key
# Verify
firecrawl --status
For a self-hosted Firecrawl instance (no API key needed):
export FIRECRAWL_API_URL=http://localhost:3002
Skills Available
After this skill is activated OrcBot has access to these callable tools:
firecrawl_scrape(url, format?, options?)
Extract content from a URL via cloud browser. Default format is markdown.
# Get clean markdown
firecrawl_scrape("https://example.com")
# Get all links from a page
firecrawl_scrape("https://example.com", "links")
# Extract main content only, skip navs and footers
firecrawl_scrape("https://example.com", "markdown", {only_main_content: true})
# Wait 3s for JS to render, then scrape
firecrawl_scrape("https://spa.example.com", "markdown", {wait_for: 3000})
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.
- 1mo ago First seen · 175 lines · 81 tokens per session scan A 5e789ae969e6
firecrawl-cli is a skill published in the GitHub repository fredabila/orcbot (11 stars, last pushed 8d ago), licensed MIT. It adds 81 tokens to every session and 1,488 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
browser-automation
Use when controlling web pages with the OpenClaw browser tool, especially multi-step flows, login checks, tab management, or recovery from stale refs/timeouts.
crabbox-apps
Use when asked to open, run, test, or show an app in Crabbox, including native desktops, web previews, and computer use on a temporary machine.
computer-use
Drives the GUI of a visible local app window through orca computer: accessibility tree, clicks, typing, menus, dialogs, and screenshots in native apps and external browser windows (Chrome, Edge, Safari) or webviews. Prefer a programmatic path (shell, filesystem, git, HTTP, existing CLIs) whenever it can complete the…
chrome-browser
Read this skill before the first step that uses Claude in Chrome, the browser extension whose tools are named mcpclaude-in-chrome (also called Chrome, the browser extension, or the external browser) and which acts in the person's real Chrome with their own sign-ins; before those tools are turned on there may be a…
browser-app-delivery
Deliver a runnable local browser app so the user can operate it on the first handoff. This delivery skill does not choose whether a requested local system should be a browser app. On a current turn that explicitly says to implement a brand-new browser project now, load bundled:greenfield-project-scaffolding before…
built-in-browser
Read this skill before the first step that uses the built-in browser, the browser pane inside the Claude desktop app (also called the in-app browser, the browser pane, Claude's browser, or "your own browser"), whose tools are named mcpClaudeBrowser when the session runs in the desktop app and…