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/b2bforce/b2bforce/tool-firecrawlnpx skills add b2bforce/b2bforce --skill tool-firecrawlgit clone --depth 1 https://github.com/b2bforce/b2bforceWhat 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 | $0.00056 | $0.00464 |
| Opus 5 | $0.00028 | $0.00232 |
| Sonnet 5 | $0.00011 | $0.00093 |
| Haiku 4.5 | $0.00006 | $0.00046 |
Grade A, and why
tool-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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `curl` What it actually says
Tool: Firecrawl
Thin wrapper for the Firecrawl API — turn a URL into clean markdown, or discover a site's URLs. Other skills call this instead of re-describing the API.
Requirements
curljq.envcredentials listed below
Auth
.env:
FIRECRAWL_API_KEY=fc-...
Header: Authorization: Bearer $FIRECRAWL_API_KEY. Base: https://api.firecrawl.dev/v1.
Endpoints
| Action | Endpoint | Use |
|---|---|---|
| Scrape | POST /scrape |
One URL → markdown/html |
| Map | POST /map |
Discover URLs on a domain (sitemap-like) |
Scripts
# Scrape one URL to markdown (prints markdown to stdout)
bash .agents/skills/tool-firecrawl/scripts/scrape.sh https://example.com
# Map a site's URLs (prints JSON array of links)
bash .agents/skills/tool-firecrawl/scripts/map.sh https://example.com
Request shape (scrape)
{ "url": "https://example.com", "formats": ["markdown"], "onlyMainContent": true }
Rules
- Key comes from
.envonly — never inline it or ask for it in chat. - Truncate very large pages (~15000 chars) before feeding to an LLM.
- Handle non-200 / timeouts gracefully; report and let the calling skill degrade.
- Respect target sites' robots and rate limits.
Used by
marketing-company-profile, marketing-service,
intel-competitor-monitoring,
marketing-service-page.
What ships with it
2 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.
- 2d ago First seen · 70 lines · 56 tokens per session scan A 96ec57fc23a9
tool-firecrawl is a skill published in the GitHub repository b2bforce/b2bforce (2 stars, last pushed 11d ago), licensed MIT. It adds 56 tokens to every session and 464 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 2026-08-31.
Other skills, from other repositories
eval-graphics
Turn an eval study's numbers into on-brand, publish-ready figures using the Newsjack chart room (the eval design system), then validate them with Playwright. For producing the charts in a published eval/data study.
news-search
Search current news for a topic, company, competitor, or hook and return dated, attributed articles. Uses the newsjack CLI and Medialyst REST API when available, tries direct Medialyst MCP if the CLI is missing, and falls back to host web/browser search with explicit caveats only when neither cloud path is available.
frontend-verify
Verify frontend changes end to end after editing a web app, instead of manually clicking through pages. Use this whenever you have changed UI code and need to confirm nothing broke: "verify my frontend", "check the site after these edits", "did my UI break", "did my changes break anything", "make sure these routes…
content-publish
End-to-end content creation and publishing. Takes a topic (or generates one), drafts in the user's voice, gets approval via Telegram, and publishes to Medium via browser automation. Invoke with "publish a post about X", "write and publish to Medium", "content-publish", or when an ego-dispatched session needs to create…
cold-email-outreach
Run end-to-end B2B cold-email outreach through the Hyper MCP — enrich prospects with Apollo, scrape per-prospect signals from company sites and LinkedIn, draft personalized emails using proven hook frameworks, send via Gmail with safe defaults, and route replies into labeled folders. Use when the user wants to write…
competitor-intel
Run end-to-end competitor research and monitoring through the Hyper MCP — pick the set, scrape every public surface (site, blog, pricing, organic social, search rank, mentions, demand) via Firecrawl + HyperSEO + the Apify scrapers, diff against last run, and synthesize a brief. Use when the user wants to research…