agentcrawl SKILL.md skillB

agentcrawl from jorg18/agentcrawl is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add jorg18/agentcrawl/agentcrawl@v0.7.0

Pins v0.7.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
jorg18/agentcrawl
Path
skills/agentcrawl/SKILL.md
Versions recorded
7
Latest version
v0.7.0, committed Oct 25, 2026
First version recorded
Oct 15, 2026
Size
7,218 bytes
Repository stars
10
License
Apache-2.0

Read web pages and documentation as clean Markdown with AgentCrawl, locally. Use when you need the content of a URL, several URLs, or a whole docs site; when your built-in web fetch fails, returns raw HTML, or the page needs JavaScript; when a page is too long and you only need one section or the parts about a question; or when you want structured data from a page with CSS selectors and no LLM.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# AgentCrawl

AgentCrawl turns web pages into Markdown, links and metadata for agents. It runs on the user's machine: no account, no API key, no hosted scraper. It follows robots.txt, refuses private-network targets unless told otherwise, and reports a bot-check page it recognises instead of returning it as content.

**This is the official skill, by the AgentCrawl author.**

## Setup (once)

Check first: `agentcrawl --version`. If it is missing, install it (Python 3.10+):

```bash
pipx install "agentcrawl-ai[mcp]"      # or: python3 -m pip install "agentcrawl-ai[mcp]"
agentcrawl doctor                      # says what works and what is missing
```

Plain HTTP pages need nothing else. For pages that only render with JavaScript, add the browser (several hundred MB on disk, only when needed):

```bash
pipx inject agentcrawl-ai playwright && python3 -m playwright install chromium
# with pip: python3 -m pip install "agentcrawl-ai[browser]" && python3 -m playwright install chromium
```

Sites behind Cloudflare ("Just a moment…", `error_type: "client_challenge"`): add the stealth retry (Patchright):

```bash
pipx inject agentcrawl-ai patchright && python3 -m patchright install chromium
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add jorg18/agentcrawl/agentcrawl@sha256:9cac106ff36ba85d

The line at the top of this page pins the label v0.7.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_d7tejoq7eb624yzu.svg)](https://markdownregistry.com/a/art_d7tejoq7eb624yzu)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 7 versions of this file, between Oct 15, 2026 and Oct 25, 2026, about one every 2 days.

versioncommittedcommitsizeaudit
v0.7.0 latest2026-10-25 48186b8 7,218 BB view · diff
v0.6.02026-10-22 f9c204d 7,218 BB view · diff
v0.6.02026-10-18 03ebaa9 7,204 BB view · diff
v0.6.02026-10-16 d9134b2 7,123 BB view · diff
v0.5.62026-10-16 dab17cb 6,730 BB view · diff
v0.5.62026-10-15 26195e3 6,709 BB view · diff
v0.5.62026-10-15 34e59be 6,427 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No link to a raw IP address (matched: http://127.0.0.1:3000)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7218 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

jorg18/agentcrawl · 10 stars · license Apache-2.0 · pushed 2026-10-25 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_d7tejoq7eb624yzu
GET https://markdownregistry.com/api/v1/resolve?ref=jorg18/agentcrawl/agentcrawl
GET https://markdownregistry.com/api/v1/blob/9cac106ff36ba85de06564ad7093395e126993b2c4ba599b5033f5961ad4fb8f

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from jorg18/agentcrawl

AGENTS.md AGENTS.md file
jorg18/agentcrawl · AGENTS.md
git:20260929.87a3d30 · audit A · 10 stars
CLAUDE.md CLAUDE.md file
jorg18/agentcrawl · CLAUDE.md
git:20261006.21e63da · audit A · 10 stars

Every file in jorg18/agentcrawl

Browse by kind, by grade B, or by owner.