crawl-engineer

crawl-engineer is an agent for coding agents from xberg-io/crawlberg. It costs 8 tokens per session (505 once invoked), scanned A, original, MIT.

Development guidance for crawlberg's web-crawling system, including its crawler, web requests, page processing, browser mode, and research agent.

In plain words
What is it for?
It is for developing crawl loops, HTTP handling, robots.txt and sitemap support, rate limits, caching, user-agent rotation, HTML-to-Markdown conversion, browser crawling, and AI research features.
Why use it?
It helps an agent find the right parts of the codebase and follow the project's rules when changing crawling behavior.

Agent

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.

agentmods
npx agentmods add agents/xberg-io/crawlberg/crawl-engineer
Clone the repo
git clone --depth 1 https://github.com/xberg-io/crawlberg

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 crawl-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/xberg-io/crawlberg/crawl-engineer.svg)](https://agentmods.dev/agents/xberg-io/crawlberg/crawl-engineer)
Your own site
<a href="https://agentmods.dev/agents/xberg-io/crawlberg/crawl-engineer"><img src="https://agentmods.dev/badge/agents/xberg-io/crawlberg/crawl-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 505 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00008 $0.00505
Opus 5 $0.00004 $0.00253
Sonnet 5 $0.00002 $0.00101
Haiku 4.5 $0.00001 $0.00051

Measured 4d ago against content hash 06ca3514ac17, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

crawl-engineer 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 4d 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.

.ai-rulez/agents/crawl-engineer.md · 22 lines

What it actually says

When working on the crawling system:

  • The crawl engine lives in crates/crawlberg/src/engine/ with crawl_loop.rs (main crawl loop), builder.rs (engine configuration), and batch.rs (batch crawling). The engine orchestrates URL frontier management, HTTP fetching, and content extraction.
  • HTTP client and request handling is in crates/crawlberg/src/http.rs. Respect robots.txt rules via robots.rs and sitemap discovery via sitemap.rs.
  • Rate limiting, caching, user-agent rotation, and tracing middleware live in crates/crawlberg/src/tower/ as Tower service layers (rate_limit.rs, cache.rs, ua_rotation.rs, tracing_layer.rs).
  • HTML processing pipeline: parsing via tl crate, pruning (pruning.rs), normalization (normalize.rs), and markdown conversion (markdown.rs) using html-to-markdown-rs.
  • Browser-based crawling (feature-gated behind browser) uses chromiumoxide in browser.rs, browser_pool.rs, browser_profile.rs, and browser_detect.rs. Interactive page actions live in interact/.
  • AI-powered research agent (feature-gated behind ai) in research/ with agent.rs, planner.rs, and synthesizer.rs using liter-llm for LLM calls and minijinja for prompt templates.
  • MCP server integration (feature-gated behind mcp) in mcp/ exposes crawling as tool calls.
  • REST API (feature-gated behind api) in api/ provides HTTP endpoints via axum.
  • WARC archive output (feature-gated behind warc) in warc.rs.
  • Configuration types in types/config.rs, crawl results in types/results.rs, URL discovery in types/discovery.rs, page metadata in types/metadata.rs.
  • Bindings: Python (crawlberg-py), Node.js (crawlberg-node), PHP (crawlberg-php), WASM (crawlberg-wasm), C FFI (crawlberg-ffi), with shared binding utilities in crawlberg-bindings-common.
  • CLI entry point in crawlberg-cli.
  • All crawling logic stays in Rust core. Bindings are thin wrappers only.
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. 4d ago First seen · 22 lines · 8 tokens per session scan A 06ca3514ac17

Subscribe to this mod's changes

crawl-engineer is an agent published in the GitHub repository xberg-io/crawlberg (168 stars, last pushed today), licensed MIT. It adds 8 tokens to every session and 505 once invoked, about $0.0000 per session on Opus 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.

Related

Other agents, from other repositories

e2e-test-writer

E2E spec author — explores a live app via Playwright MCP (browsersnapshot → interact → assert), authors durable spec files, and mandates browser teardown with per-step deadlines. Invoke for the authoring phase of /swe-workbench:test --mode e2e; the verifier runs the specs after.

lugassawan/swe-workbench · 69 tokens

plinth-architect

Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.

jabrena/plinth · 38 tokens

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

praman-sap-planner-cli

SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.

mrkanitkar/playwright-praman · 36 tokens

FAI Browser Agent

Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.

frootai/frootai · 41 tokens

Agent Issues

The Agent will analyze and fix the issues in the repository.

microsoft/Generative-AI-for-beginners-dotnet · 14 tokens