A command that imports an external website into a tinydot site, a site managed through tinydot's content files. It discovers pages from a sitemap, feed, or internal links, then converts selected pages into tinydot content.

Use it to bring an existing website into tinydot by supplying its URL, selecting discovered pages, and converting them into a tinydot site.

It removes the need to manually find every page and copy its title, date, description, and content into a new site. It also asks which pages and site name to use before creating the import.

import — Command by systemoperators

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/systemoperators/claude-plugins/import

Clone the repo

git clone --depth 1 https://github.com/systemoperators/claude-plugins

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 745 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.

Model	Per session	Once invoked
Fable 5	$0.00010	$0.00745
Opus 5	$0.00005	$0.00373
Sonnet 5	$0.00002	$0.00149
Haiku 4.5	$0.00001	$0.00075

Measured yesterday against content hash 0bab557d12ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

import 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 yesterday.

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.

tinydot/commands/import.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

import a website into tinydot

Convert an external website into a tinydot site. Follow these steps:

1. get the source URL

Use $ARGUMENTS as the URL. If empty, ask the user for the URL to import.

2. discover pages

Fetch the site and look for pages to import:

try {url}/sitemap.xml - parse all <loc> URLs
if no sitemap, try {url}/rss.xml or {url}/feed or {url}/feed.xml - parse all <link> entries
if neither exists, fetch the homepage and extract internal links from navigation (header, footer, sidebar) and content

Show the user the list of discovered pages and ask which to import (all, or select specific ones).

3. determine site name

Suggest a site name based on the domain (e.g., example.com -> example). Ask the user to confirm or change it. The site folder will be created at ~/Library/CloudStorage/Tinydot/{sitename}/.

4. fetch and convert each page

For each page:

fetch with WebFetch, asking it to extract the main content as markdown
extract from the page:
- title (from <title>, <h1>, or og:title)
- date (from meta tags, published date, or article:published_time)
- description (from meta description or og:description)
- author (from meta author if available)
find images in the content:
- download each image using WebFetch
- save to {sitename}/images/{filename} (use original filename or generate from URL)
- replace image URLs in markdown with local paths: images/filename.jpg (content block syntax)
convert internal links to wikilinks where the target page is being imported
preserve external links as regular markdown links
create the markdown file with frontmatter:

---
title: Page Title
date: 2026-01-15
description: Page description
tags: imported
---

From the source site's header/footer navigation:

create matching header_menu and footer_menu in the root index.md frontmatter
convert navigation links to local paths where pages were imported
keep external links as-is

Read the full file on GitHub · 86 lines

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.

yesterday First seen · 86 lines · 10 tokens per session scan A 0bab557d12ce

Subscribe to this mod's changes

import is a command published in the GitHub repository systemoperators/claude-plugins (6 stars, last pushed 7mo ago), licensed MIT. It adds 10 tokens to every session and 745 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-31.

Writing and docs claude claude-code claude-plugin claude-skills claude-work

import

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

import a website into tinydot

1. get the source URL

2. discover pages

3. determine site name

4. fetch and convert each page

5. create navigation

What this file has done since we first saw it

Other commands, from other repositories

seo-drift

brand-setup

save

ros-first-dollar

screens

graphify