rag-index-website

rag-index-website is a command for Claude Code from codingthefuturewithai/rag-retriever. It costs 0 tokens per session (436 once invoked), scanned A, original, MIT.

A command that crawls a website and adds its content to the RAG Retriever vector store, a database used for meaning-based document search. It accepts a URL and optional crawl depth and collection name.

In plain words
What is it for?
Use it to index documentation sites, choose how deeply links are followed, and store the results in a named or automatically created collection.
Why use it?
It turns website documentation into searchable material for later semantic queries instead of requiring users to search each page manually.

Command for Claude Code

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.

agentmods
npx agentmods add commands/codingthefuturewithai/rag-retriever/rag-index-website
Clone the repo
git clone --depth 1 https://github.com/codingthefuturewithai/rag-retriever

Made for: Claude Code.

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.

agentmods badge for rag-index-website

README.md
[![agentmods](https://agentmods.dev/badge/commands/codingthefuturewithai/rag-retriever/rag-index-website.svg)](https://agentmods.dev/commands/codingthefuturewithai/rag-retriever/rag-index-website)
Your own site
<a href="https://agentmods.dev/commands/codingthefuturewithai/rag-retriever/rag-index-website"><img src="https://agentmods.dev/badge/commands/codingthefuturewithai/rag-retriever/rag-index-website.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 436 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00436
Opus 5 $0.00000 $0.00218
Sonnet 5 $0.00000 $0.00087
Haiku 4.5 $0.00000 $0.00044

Measured 5d ago against content hash fef6fa951d06, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rag-index-website 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 5d 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.

.claude/commands/rag-index-website.md · 53 lines

What it actually says

Index Website into RAG Retriever

Crawl and index a website into the RAG Retriever vector store for future semantic search.

Prerequisites

This command requires the RAG Retriever MCP server to be configured in your Claude Code setup. The server handles web crawling and content indexing into vector store collections.

Arguments

Use $ARGUMENTS to specify crawling parameters:

  • URL (required)
  • Max depth (optional - defaults to 2)
  • Collection name (optional - creates new collection if not exists)

Examples:

Implementation Approach

This command uses direct implementation to coordinate website crawling and indexing.

Your Task

  1. Parse Arguments

    • Extract URL from $ARGUMENTS (required)
    • Parse optional max_depth (default: 2)
    • Parse optional collection_name (default: generates from URL)
  2. Pre-Crawl Analysis

    • Validate the URL is accessible
    • Estimate the scope of crawling based on max_depth
    • Suggest appropriate collection name if not provided
    • Use list_collections to check for existing collections
  3. Initiate Crawling

    • Use crawl_and_index_url to start the crawling process
    • Monitor progress and provide updates
    • Handle any errors or issues that arise
  4. Post-Crawl Verification

    • Use list_collections to verify the collection was created/updated
    • Perform a test search to validate indexed content
    • Provide summary of pages crawled and content indexed

Success Criteria

  • Website successfully crawled and indexed
  • Content stored in appropriate collection
  • Verification that search functionality works with new content
  • Clear summary of indexing results

Available MCP Tools

  • list_collections() - Check existing collections
  • crawl_and_index_url(url, max_depth, collection_name) - Index website content
  • vector_search(query, collection_name) - Verify indexed content
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.

  1. 5d ago First seen · 53 lines · 0 tokens per session scan A fef6fa951d06

Subscribe to this mod's changes

rag-index-website is a command published in the GitHub repository codingthefuturewithai/rag-retriever (27 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 436 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.