Anakin Claude Code Plugin

Convert websites into clean data at scale: scrape, batch-scrape, search, and deep research.

Requirements

This plugin requires anakin-cli (Python 3.10+):

pip install anakin-cli
anakin login --api-key "ak-your-key-here"

Get your API key from anakin.io/dashboard.

Installation

From marketplace

First, add the Anakin marketplace to Claude Code:

/plugin marketplace add Anakin-Inc/anakin-claude-plugin

Then install the plugin:

/plugin install anakin@anakin

From local directory (development)

claude --plugin-dir ./anakin-claude-plugin

Validate locally

claude plugin validate .

Once installed, Claude will automatically use Anakin for web scraping, search, and research tasks.

Development note: After modifying plugin files, restart Claude Code to pick up changes.

Components

Skills

Skill	Invocation	Description
scrape-website	/anakin:scrape-website [url]	Scrape a single URL to markdown, JSON, or raw
scrape-batch	/anakin:scrape-batch [url1] [url2]	Scrape up to 10 URLs at once
search-web	/anakin:search-web [query]	AI-powered web search with instant results
deep-research	/anakin:deep-research [topic]	Deep agentic multi-step research (1-5 min)
setup	/anakin:setup	Install CLI, configure API key, set up output directory
anakin-cli	(auto)	Background knowledge: escalation workflow, CLI rules, output organization

Agents

Agent	Description
data-extraction-architect	Plan which anakin-cli commands to use for complex extraction tasks

Hooks

Hook	Event	Description
check-auth	PreToolUse (Bash)	Verify anakin-cli is installed and authenticated before running anakin commands

Scripts

Script	Used By	Description
check-auth.sh	hooks.json	Shell script that checks CLI installation and auth status

Usage Examples

Once the plugin is active, Claude will use Anakin automatically. You can also invoke skills directly:

/anakin:search-web latest React documentation

/anakin:scrape-website https://example.com

/anakin:deep-research pros and cons of microservices vs monolith

/anakin:scrape-batch https://a.com https://b.com https://c.com

All output is saved to the .anakin/ directory to keep your context window clean:

.anakin/
├── search-react-docs.json
├── example.com.md
├── batch-results.json
└── research-microservices.json

Architecture

anakin-claude-plugin/
├── .claude-plugin/
│   ├── plugin.json              # Plugin manifest
│   └── marketplace.json         # Marketplace catalog entry
├── skills/
│   ├── anakin-cli/
│   │   └── SKILL.md             # Background knowledge (auto-loaded, not user-invocable)
│   ├── scrape-website/
│   │   └── SKILL.md             # Single URL scraping
│   ├── scrape-batch/
│   │   └── SKILL.md             # Batch URL scraping
│   ├── search-web/
│   │   └── SKILL.md             # Web search
│   ├── deep-research/
│   │   └── SKILL.md             # Deep agentic research
│   └── setup/
│       └── SKILL.md             # CLI setup and authentication
├── agents/
│   └── data-extraction-architect.md  # Extraction strategy planner
├── hooks/
│   └── hooks.json               # PreToolUse auth verification
├── scripts/
│   └── check-auth.sh            # Auth check script for hooks
├── LICENSE
├── CHANGELOG.md
├── README.md
└── .gitignore

The CLI source code lives in a separate repo: Anakin-Inc/anakin-cli

Configuration

Variable	Description
ANAKIN_API_KEY	API key (env var, takes precedence over config file)
~/.anakin/config.json	Stored API key (set via anakin login)

License

MIT