# Learn

Source: https://routineos.org/learn

> Plain guides to Claude scheduled tasks, connectors, artifacts, Claude Code plugins and agentic workflows, each tagged by how we know it.

Learn

# Learn how Claude routines work.

Short guides in plain words. They cover Claude scheduled tasks (also called routines), connectors, artifacts, Claude Code plugins and agentic workflows (jobs where Claude makes judgment calls inside a process). Each one says which claims come from Anthropic's docs and which we checked by running them.

[Get started](https://routineos.org/#start)[Start with the basics](https://routineos.org/learn/what-are-claude-routines)

Free (MIT). Needs a paid Claude plan.tagged by source

The guides

## Nine guides, in the order to read them

Start with the first if Claude scheduled tasks are new to you. The rest stand alone.

 [

### What are Claude routines?

A saved Claude Code setup that runs on Anthropic's cloud on a schedule. What it can do and where it stops.
Read ](https://routineos.org/learn/what-are-claude-routines) [

### Schedule Claude Code

Run Claude Code every day without a laptop open. Cron is in UTC and the shortest gap is one hour.
Read ](https://routineos.org/learn/schedule-claude-code) [

### Claude connectors

How a routine reaches mail, calendars and other services, and why every write needs a gate.
Read ](https://routineos.org/learn/claude-connectors) [

### Claude artifacts as apps

An artifact with a database can hold a routine's results. The Desk is one worked example.
Read ](https://routineos.org/learn/claude-artifacts-as-apps) [

### Claude Code plugins

How to install a plugin from a marketplace, and what the RoutineOS plugin contains.
Read ](https://routineos.org/learn/claude-code-plugins) [

### Agentic workflows

What to leave to code, what to leave to Claude, and how to keep it safe: report first, ask before acting.
Read ](https://routineos.org/learn/agentic-workflows) [

### Human in the loop AI

Approval gates for routines: what asks you first, and what a reply can and cannot do.
Open ](https://routineos.org/learn/human-in-the-loop-ai) [

### Claude MCP servers

What an MCP server is, with a free one to add today.
Open ](https://routineos.org/learn/claude-mcp) [

### Claude skills on a schedule

How a skill is delivered to a scheduled run, and which routes are verified.
Open ](https://routineos.org/learn/claude-skills-in-routines)

How we tag claims

## Where each fact comes from

| Tag | Means |
|---|---|
| pilot-verified | A real run checked it. |
| docs-stated | It comes from Anthropic's public docs and was not run by us. |
| owner-verified | Checked by the maintainer of RoutineOS. It is not a documented pilot. |
| unverified | Not checked. Do not rely on it. Check Anthropic's docs for the current answer. |

Claude scheduled tasks are a research preview, so Anthropic's behavior and limits can change. The full list is on [honest limits](https://routineos.org/honest-limits).

## Read, then build one

Install the plugin in Claude Code and start from a template. RoutineOS is free (MIT) and needs a paid Claude plan.

[Get started](https://routineos.org/#start)[Read the docs](https://docs.routineos.org)