← Back to Skills Marketplace
neothelobster

Ghostfetch

by Neo The Lobster · GitHub ↗ · v1.1.0
cross-platform ✓ Security Clean
403
Downloads
1
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install ghostfetch
Description
CLI web search and page fetcher for LLM agents. Search DuckDuckGo/Brave/Bing/Google, fetch pages as markdown, and extract links — single binary, no browser r...
README (SKILL.md)

Ghostfetch

Web search and page fetcher for AI agents. Single binary, no browser needed. Fetches pages with browser-like TLS fingerprints for reliable access.

Use for: web searches, fetching page content as markdown, extracting links, and gathering information from the web.

Commands

Search the web

ghostfetch "your search query"                    # Search DuckDuckGo (default)
ghostfetch "query" -e brave                       # Search with Brave
ghostfetch "query" -e google                      # Search with Google
ghostfetch "query" -e bing                        # Search with Bing
ghostfetch "query" -n 5                           # Limit to 5 results
ghostfetch "query" --json                         # JSON output with metadata

Search engines: duckduckgo (default), brave, bing, google

Fetch pages

ghostfetch fetch https://example.com              # Fetch page (raw HTML)
ghostfetch fetch https://example.com -m           # Fetch as markdown (reader mode — preferred)
ghostfetch fetch https://example.com --markdown-full  # Full page as markdown (not just main content)
ghostfetch fetch https://example.com --json       # JSON with body, status, headers, cookies
ghostfetch fetch https://example.com --raw        # Raw HTML without processing
ghostfetch fetch url1 url2 url3 -p 3              # Fetch multiple URLs in parallel

Always use -m (markdown mode) when reading page content — it extracts the main content and converts to clean markdown, saving tokens vs raw HTML.

Extract links

ghostfetch links https://example.com              # Extract all links from page
ghostfetch links https://example.com -f "github"  # Filter links by regex pattern
ghostfetch links https://example.com --json       # JSON output

Flags Reference

Flag Short Default What it does
--engine -e duckduckgo Search engine to use
--results -n 10 Number of search results
--markdown -m false Convert to markdown (reader mode)
--markdown-full false Full page markdown (not just main content)
--json -j false JSON output with metadata
--raw false Raw HTML output
--max-parallel -p 5 Max parallel fetches
--filter -f Filter links by regex
--timeout -t 30s Request timeout
--browser -b chrome Browser fingerprint: chrome, firefox
--no-cookies false Disable cookie persistence
--follow -L true Follow redirects
--verbose -v false Print request/response details
--captcha-service Captcha service: 2captcha, anticaptcha
--captcha-key Captcha service API key

Decision Guide

I want to... Use this
Search the web ghostfetch "query"
Search with specific engine ghostfetch "query" -e brave
Read a web page ghostfetch fetch \x3Curl> -m
Read multiple pages at once ghostfetch fetch url1 url2 url3 -m -p 3
Find links on a page ghostfetch links \x3Curl>
Find specific links ghostfetch links \x3Curl> -f "pattern"
Get structured data ghostfetch fetch \x3Curl> --json

Examples

Research a topic

ghostfetch "rust async runtime comparison 2026" -n 5
ghostfetch fetch https://tokio.rs -m

Scrape structured data

ghostfetch fetch https://api.example.com/data --json

Find all GitHub links on a page

ghostfetch links https://awesome-list.com -f "github.com"

Installation

The ghostfetch binary must be in your PATH. Build from source:

git clone https://github.com/neothelobster/ghostfetch.git
cd ghostfetch
go build -o ghostfetch .
cp ghostfetch ~/.openclaw/workspace/tools/

Or run the included setup.sh which clones at a pinned commit with verification.

Requires Go 1.21+ to build. No runtime dependencies.

Security

  • Read-only tool — output goes to stdout only, no file write capability
  • No custom headers or POST bodies — cannot leak secrets to external endpoints
  • No data is stored except optional cookie jars (disabled with --no-cookies)
  • All network requests go directly from your machine — no proxy or third-party service
  • The setup script clones from GitHub at a pinned commit with verification
  • Source code: https://github.com/neothelobster/ghostfetch
Capability Analysis
Type: OpenClaw Skill Name: ghostfetch Version: 1.1.0 The skill bundle provides a legitimate web search and page fetching tool for AI agents. The `SKILL.md` documentation clearly outlines its purpose and usage, includes a 'Security' section detailing its read-only nature and lack of data exfiltration capabilities, and contains no prompt injection attempts. The `setup.sh` script is robust, securely cloning the source code from a pinned GitHub commit, verifying the commit, and building/installing the binary without any malicious actions or vulnerabilities. While the tool offers powerful features like captcha solving, these are presented as legitimate functionalities for web interaction, not as mechanisms for inherent malice.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install ghostfetch
  3. After installation, invoke the skill by name or use /ghostfetch
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.0
Security hardening: removed -o (file write), -H (custom headers), -X (HTTP method), -d (POST body), -c (cookie jar path) flags to prevent data exfiltration and file overwrite. Added captcha support. Pinned setup.sh to commit 6e6876a.
v1.0.1
Pin setup.sh to commit eb2eac5 with verification, add security guidance for -o/-H/-d flags
v1.0.0
Initial release — CLI web search and page fetcher for LLM agents. Search DuckDuckGo/Brave/Bing/Google, fetch pages as markdown, extract links. Single Go binary, no browser required.
Metadata
Slug ghostfetch
Version 1.1.0
License
All-time Installs 0
Active Installs 0
Total Versions 3
Frequently Asked Questions

What is Ghostfetch?

CLI web search and page fetcher for LLM agents. Search DuckDuckGo/Brave/Bing/Google, fetch pages as markdown, and extract links — single binary, no browser r... It is an AI Agent Skill for Claude Code / OpenClaw, with 403 downloads so far.

How do I install Ghostfetch?

Run "/install ghostfetch" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Ghostfetch free?

Yes, Ghostfetch is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Ghostfetch support?

Ghostfetch is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Ghostfetch?

It is built and maintained by Neo The Lobster (@neothelobster); the current version is v1.1.0.

💬 Comments