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/xberg-io/crawlberg/serving-the-apinpx skills add xberg-io/crawlberg --skill serving-the-apigit clone --depth 1 https://github.com/xberg-io/crawlbergWrote 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/xberg-io/crawlberg/serving-the-api)<a href="https://agentmods.dev/skills/xberg-io/crawlberg/serving-the-api"><img src="https://agentmods.dev/badge/skills/xberg-io/crawlberg/serving-the-api.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 | $0.00071 | $0.01300 |
| Opus 5 | $0.00036 | $0.00650 |
| Sonnet 5 | $0.00014 | $0.00260 |
| Haiku 4.5 | $0.00007 | $0.00130 |
Grade A, and why
serving-the-api 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 5d 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 -s http://127.0.0.1:3000/v1/scrape \ How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Serving the API
crawlberg serve starts a long-running REST API server exposing the crawl
engine over HTTP. The endpoints are Firecrawl v1-compatible, so existing
Firecrawl clients and SDKs can point at a local crawlberg instance.
This subcommand requires the binary to be built with the optional api
feature (non-default). The Homebrew tap is built with all features, so serve
is available there; a from-source build needs
cargo install crawlberg-cli --features api
(or --features all) to include it.
Quick recipe
crawlberg serve --host 127.0.0.1 --port 3000
It logs Starting REST API server on <host>:<port> to stderr and blocks until
terminated. Hit GET /health to confirm it is up.
Flags
| Flag | Default | Purpose |
|---|---|---|
--host |
0.0.0.0 |
Address to bind to. |
--port |
3000 |
Port to listen on. |
serve does not take the per-request crawl flags — it boots with the default
CrawlConfig and accepts per-request options in each HTTP request body.
Endpoints
Firecrawl v1 surface:
| Method + path | Purpose |
|---|---|
POST /v1/scrape |
Scrape a single URL (synchronous). |
POST /v1/crawl |
Start an asynchronous crawl job → returns a job id. |
GET /v1/crawl/{id} |
Poll crawl job status and collect results. |
DELETE /v1/crawl/{id} |
Cancel a running crawl job. |
POST /v1/map |
Discover URLs on a site (synchronous). |
POST /v1/batch/scrape |
Start an asynchronous batch-scrape job → job id. |
GET /v1/batch/scrape/{id} |
Poll batch-scrape job status and results. |
POST /v1/download |
Download a document from a URL. |
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.
- 5d ago First seen · 122 lines · 71 tokens per session scan A 2e0bf68c114a
serving-the-api is a skill published in the GitHub repository xberg-io/crawlberg (168 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 1,300 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
scrapling-official
Scrape web pages using Scrapling with anti-bot bypass (like Cloudflare Turnstile), stealth headless browsing, spiders framework, adaptive scraping, and JavaScript rendering. Use when asked to scrape, crawl, or extract data from websites; webfetch fails; the site has anti-bot protections; write Python code to…
abx-dl
Use this when working on the standalone ArchiveBox downloader CLI, extractor orchestration, plugin execution, config, and output verification.
openclaw-ultra-scraping
Powerful web scraping, crawling, and data extraction with stealth anti-bot bypass. Bypasses anti-bot systems (Cloudflare Turnstile, CAPTCHAs) out of the box. Use when: (1) scraping websites that block normal requests, (2) extracting structured data from web pages, (3) crawling multiple pages with concurrency, (4)…
web-intelligence
Web intelligence routing authority — choose Exa for discovery, Firecrawl for extraction and crawling, and Bright Data for dynamic or geo-sensitive collection; normalize outputs, costs, and fallback policy for agentic research workflows.
firecrawl-scrape
Web scraping & crawling for AI using Firecrawl.
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…