Skip to content
Agentmart
Submit a tool

crawl

Crawl a website to discover pages and map its structure.

Skill by inovacc

IndexedBSD-3-Clause★ 2
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/inovacc-crawl

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Crawl a website to discover pages and map its structure. Use when the user wants to explore, map, or discover all pages on a site.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/crawl

What's inside

Skill name
crawl
Description
Crawl a website to discover pages and map its structure. Use when the user wants to explore, map, or discover all pages on a site.
License
BSD-3-Clause
Instructions
27 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Crawl

Crawl a website to discover pages, map link structure, and build a sitemap.

**Input:** `$ARGUMENTS` should be a URL to crawl, optionally followed by parameters (e.g., `https://example.com workers:4 depth:3 max:100`).

## Workflow

1. **Crawl** the site using `mcp__scout__swarm_crawl` with:
   - `url`: the target URL from arguments
   - `workers`: number of parallel workers (default 2)
   - `depth`: crawl depth limit (default 2)
   - `maxPages`: maximum pages to visit (default 50)
2. **Report** the crawl results:
   - Total pages discovered
   - Page hierarchy / site structure
   - Broken links found
   - External links
   - Crawl statistics (time, pages/second)

## Guidelines

- Start with conservative defaults (2 workers, depth 2, 50 max pages) to be respectful.
- Increase workers/depth only when the user explicitly requests it.
- Group discovered pages by section or path prefix for readability.
- Highlight any errors or unreachable pages.

From inovacc/scout, BSD-3-Clause.

More from inovacc/scout

Signals

Stars
2
Forks
1
Open issues
0
Last commit (this folder)
Jul 3, 2026 (3 months ago)
Last release
Jun 15, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
BSD-3-Clause
Repository
github.com/inovacc/scout
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

Same skill elsewhere

Copies of this SKILL.md published by others; search shows only one of them.

More from inovacc

Cite this page

crawl skill. Agent Mart. https://agentmart.dev/skills/inovacc-crawl (last updated 2026-10-24)