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 agentmods add skills/melodic-software/claude-code-plugins/firecrawlnpx skills add melodic-software/claude-code-plugins --skill firecrawlgit clone --depth 1 https://github.com/melodic-software/claude-code-pluginsWrote 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/melodic-software/claude-code-plugins/firecrawl)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/firecrawl"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/firecrawl.svg" alt="Measured on agentmods" 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 | $0.00186 | $0.03014 |
| Opus 5 | $0.00093 | $0.01507 |
| Sonnet 5 | $0.00037 | $0.00603 |
| Haiku 4.5 | $0.00019 | $0.00301 |
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 yesterday.
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.
- **Transient DNS 503 on `api.firecrawl.dev` from sandboxed sessions.** Some cloud egress proxies intermittently return "DNS cache overflow". Retry after ~30s. This affects both the CLI and direct curl; it's an egress is How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-computed context
Status: !command -v firecrawl >/dev/null 2>&1 && { firecrawl --status 2>/dev/null | head -10; :; } || echo "NOT INSTALLED — run: npm install -g firecrawl-cli"
The firecrawl --status line above includes auth state. If it shows unauthenticated (or the CLI is missing), the fix is: obtain a key from the https://firecrawl.dev dashboard and set FIRECRAWL_API_KEY as an OS user environment variable.
Purpose
firecrawl-cli is the CLI alternative to the firecrawl-mcp MCP server. It wraps api.firecrawl.dev with agent defaults: retry/rotation on anti-bot blocks, JS rendering, and an -o <path> flag that writes results to disk instead of streaming into the conversation.
When WebFetch fails on a large page and an MCP equivalent would dump 30K tokens of raw markdown into context, this skill writes to a tempfile and lets the agent Read only the slice it needs. Scalekit benchmark measured 32–35× token savings vs the MCP on comparable tasks.
When to reach for this skill
| Situation | Command | Why |
|---|---|---|
| WebFetch returned 403/429 (Cloudflare, PerimeterX, rate limit) | firecrawl scrape |
Managed IP rotation + headless browser |
| Page is a SPA or requires JS rendering | firecrawl scrape |
WebFetch is a plain HTTP client. No JS |
| Page needs clicks, form fills, or login | firecrawl interact |
Full browser actions, not just fetch |
| Need web search, not a known URL | firecrawl search |
Search-and-scrape in one call |
| Discovering all URLs on a site | firecrawl map |
Cheap URL-only discovery |
| Bulk extraction across a site | firecrawl crawl |
Follows links, respects depth |
| Local PDF / DOCX / XLSX / HTML file on disk → markdown | firecrawl parse |
Server-side text extraction; no local Office tooling required |
| Natural-language "find me X on the web" | firecrawl agent |
Hosted agent with Spark models |
When NOT to use this skill
- WebFetch works. WebFetch burns no Firecrawl credits and is faster for simple, unprotected pages.
- A doc-site-specialist tool is a better fit for official docs. If the session has a documentation MCP with a headless-browser backend and caching (e.g. Ref), try it before Firecrawl on known docs hosts.
- You want a training-data summary, not primary source. A synthesis tool (e.g. a Perplexity MCP, if available) is designed for that.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 144 lines · 186 tokens per session scan A 7bcddf9fd287
firecrawl is a skill published in the GitHub repository melodic-software/claude-code-plugins (14 stars, last pushed yesterday), licensed MIT. It adds 186 tokens to every session and 3,014 once invoked, about $0.0009 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 2026-09-03.
Other skills, from other repositories
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
stealth-browser-mcp
Use this skill when operating stealth-browser-mcp from an AI agent or MCP client for browser automation, page inspection, element interaction, screenshots, file uploads, CDP commands, network debugging, cookies/storage, stealth setup, or reliable multi-step browser workflows. It provides the correct tool order, state…
octocode-chrome-devtools
Use when a live page needs Chrome DevTools/CDP evidence: network failures, console errors, performance, DOM/CSS actionability, screenshots/PDF, cookies/storage, click/fill/search, HAR, or auth-gated pages. Phrases like debug in Chrome, live page health, CDP snapshot, cookie bridge. Not for static crawl or bulk extract…
site-cookie-login
Open a target website, wait for user login, verify login with required cookies plus an HTTP probe, and save cookies into .env for later automation. Use this when a site needs controlled browser login, cookie persistence, and automatic login-state checks.
legal-iros-registry-automation
대법원 인터넷등기소(IROS, iros.go.kr)에서 법인·부동산 등기부등본(등기사항증명서)을 여러 건 일괄 발급할 때 안전한 작업 순서와 로컬 자동화 방법을 안내합니다. 로그인·인증·결제는 사용자가 브라우저에서 직접 처리하고, 본 스킬은 장바구니 담기· 결제 후 열람·저장·종합 리포트 생성을 보조합니다. 다음과 같은 요청 시 반드시 이 스킬을 사용하세요: "법인등기부등본 100개 한번에 떼야 해", "회사 100개 등기부 정리해줘" "고객사 등기부등본 일괄 발급", "실사 대상 법인 등기 묶음 처리" "인터넷등기소 자동화", "iros.go.kr 일괄 발급"…