A browser-based tool that visits pages across a website, follows links on the same site, and saves the text it finds.

Use it to crawl documentation sites, single-page apps, or other websites, with limits on link depth, page count, and URL paths.

It can collect content from JavaScript-driven websites that a simple request may not render correctly.

deep-crawl — Skill for Claude Code and Codex by octos-org/octos

About the project

Octos is a self-hosted AI assistant that runs on a user's computer and can connect to different AI providers, execute code, browse the web, remember information, schedule jobs, and create documents through browser, terminal, and messaging interfaces. The catalogue entries extend or configure this assistant's workflows.

octos-org/octos · 766 stars · on GitHub

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.

Any agent

npx skills add octos-org/octos --skill deep-crawl

Clone the repo

git clone --depth 1 https://github.com/octos-org/octos

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/octos-org/octos/deep-crawl/github.svg)](https://agentmods.dev/skills/octos-org/octos/deep-crawl)

Your own site

<a href="https://agentmods.dev/skills/octos-org/octos/deep-crawl"><img src="https://agentmods.dev/badge/skills/octos-org/octos/deep-crawl/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/octos-org/octos/deep-crawl"><img src="https://agentmods.dev/badge/skills/octos-org/octos/deep-crawl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,321 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.01321
Opus 5.5	$0.00000	$0.00528
Sonnet 5.5	$0.00000	$0.00264
Haiku 4.5	$0.00000	$0.00132

Measured 29d ago against content hash 50f6fce3488d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

deep-crawl 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 29d 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.

crates/app-skills/deep-crawl/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

deep_crawl

Overview

The deep_crawl tool recursively crawls a website using a headless Chrome browser via the Chrome DevTools Protocol (CDP). It renders JavaScript, follows same-origin links via BFS, extracts text content from each page, and saves results to disk. This is ideal for crawling JS-rendered SPAs, documentation sites, and any site that requires a full browser environment.

Requirements

Google Chrome or Chromium must be installed and available in PATH, or at a standard system location.
- macOS: /Applications/Google Chrome.app/Contents/MacOS/Google Chrome
- Linux: google-chrome, google-chrome-stable, or chromium-browser

Usage

Call the deep_crawl tool with a starting URL. The crawler will follow same-origin links up to the specified depth and page limits.

Parameters

Parameter	Type	Required	Default	Description
`url`	string	yes	--	The seed URL to start crawling from
`max_depth`	integer	no	3	Maximum link-following depth (0-10; 0 reads only the seed)
`max_pages`	integer	no	50	Maximum number of pages to crawl (1-200)
`path_prefix`	string	no	--	Only follow links whose path starts with this prefix
`include_html`	boolean	no	false	Also return each page's rendered HTML and final URL in `pages`

Example

{
  "url": "https://docs.example.com/guide/",
  "max_depth": 3,
  "max_pages": 30,
  "path_prefix": "/guide/"
}

Output

The tool returns a JSON object on stdout:

{
  "output": "# Deep Crawl: https://docs.example.com/guide/\nCrawled 12 pages ...\n\n## Sitemap\n1. [depth=0] https://docs.example.com/guide/ (OK)\n...",
  "success": true
}

The output field contains:

A sitemap listing all crawled pages with their depth and status
A content preview (first ~2000 characters) for each page
The directory path where full page contents are saved as .md files

Read the full file on GitHub · 83 lines

Files

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.

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.

29d ago Changed · -1 lines 50f6fce3488d
1mo ago Changed a9e9bd5cfe03
1mo ago Changed · +12 lines 527e0de21f09
2mo ago First seen · 72 lines · 0 tokens per session scan A c3dd0c44b304

Subscribe to this mod's changes

deep-crawl is a skill published in the GitHub repository octos-org/octos (766 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,321 tokens. 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.

Browser automation

deep-crawl next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
deep-crawloctos-org/octos	Skill	766	today	Apache-2.0	A	0	Claude Code, Codex
interactive-loginyc-software/qm	Skill	16k	today	MIT	A	46	Claude Code, Codex
pinchtab-mcppinchtab/pinchtab	Skill	11k	10d ago	MIT	A	52	Claude Code, Codex
azure-messaging-webpubsub-javamicrosoft/skills	Skill	3.2k	yesterday	MIT	A	43	Claude Code
cua-driverdavidondrej/skills	Skill	4.3k	3d ago	MIT	A	68	Claude Code, Codex
open-design-browsercompozy/compozy	Skill	2.8k	today	MIT	A	56	Claude Code, Codex
southwestborski/travel-hacking-toolkit	Skill	895	today	MIT	A	40	Claude Code