# # 158 Claude Code Routines Clearly Explained (and why it matters)

Page: https://stenobird.com/podcast/build-with-ai-6407453/158-claude-code-routines-clearly-explained-and-why-it-matters
Text version: https://stenobird.com/podcast/build-with-ai-6407453/158-claude-code-routines-clearly-explained-and-why-it-matters.md
Podcast: [Build With AI](https://stenobird.com/podcast/build-with-ai-6407453)
Published: 2026-04-14T21:59:19+00:00
Episode link: https://share.transistor.fm/s/6972a421
Audio file: https://media.transistor.fm/6972a421/b97f5f42.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/build-with-ai-6407453/episodes/158-claude-code-routines-clearly-explained-and-why-it-matters
Duration seconds: 311

## Resource

Claude Code just dropped routines, and when I first saw the three options — routine, schedule, and loop — I had no idea when to use which. In this video, I break down all three modes in plain language and then demo building a routine from scratch using an X trend scanner I already had in my skill library. You'll see the full setup: GitHub connection, system prompt config, trigger options, and connector permissions. By the end, you'll know exactly which mode to use for any automation you want to build and how to get your first routine live.Links Mentioned:Claude Code Routines: https://claude.ai/code/routinesGitHub: https://github.comTimestamps00:00 – Intro: The confusion with Claude Code's new features00:20 – The three modes: routine, schedule, and loop00:50 – When to use each mode (simple breakdown)01:10 – Using Claude Code to find a skill to demo01:45 – Selecting the X scan routine02:00 – GitHub requirement for routines explained02:18 – Creating a new routine at claude.ai/code/routines02:35 – Naming your routine and connecting your GitHub repo02:50 – Dropping in your system prompt03:05 – Setting the schedule trigger (10am Eastern daily)03:20 – Configuring connectors and permission sets03:40 – Running on demand and reviewing the output04:10 – Full recap of all three modesKey Points* Claude Code has three automation modes — routine (runs on Anthropic's cloud, set it and forget it), schedule (needs local access, also available in Cowork), and loop (immediate execution in the CLI). Picking the wrong one means your automation won't work the way you expect.* Routines require a GitHub repository. You can't create one without it, so get your repo connected before you start.* The whole setup happens at claude.ai/code/routines — no coding required beyond having a system prompt…

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/build-with-ai-6407453/episodes/158-claude-code-routines-clearly-explained-and-why-it-matters/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/build-with-ai-6407453/158-claude-code-routines-clearly-explained-and-why-it-matters.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.