Skip to content
TriedPrompts

More in Business admin & workflows.

Run email, calendar, and grocery ops from markdown with Claude Code

WorkedEvidence: Described by posterPosted Last checked

Rutger de Knijf's markdown Muninn secretary on Claude Code handles email, calendar, car charge, and groceries.

How to use this

  1. Tap Copy prompt.
  2. Open the tool the case used (or a similar one) and paste the prompt; results may differ from the original.
  3. Paste it into the message box.
  4. Send it, then read the answer before acting on it.
New to this? What's a prompt?

A prompt is the message you send to the AI tool. Copy the one on this page, put your own details where it asks, and read the answer before you act on it.

Prompt

Recreated prompt

The source didn't share its exact prompt, so we wrote one from what it describes. The result shown is the source's, not ours.

What the prompt labels mean

The person didn't share their exact words, so we wrote this from what they described. We haven't tested it, and they didn't use this exact version.

You are Muninn, my markdown-defined secretary. Read today's personal and work email, update the calendar, check the car charge level via Home Assistant, advance grocery/meal tasks from the cooking playbook, and brief me on sleep metrics. Follow the CLAUDE.md and domain playbooks. Ask before sending external messages or placing paid orders.

Try this in:

ChatGPT Gemini Grok Claude

Sends the Recreated prompt shown above. ChatGPT and Grok open with it filled in, and ChatGPT may send it straight away. Gemini and Claude open empty, so we copy the prompt for you to paste. Every button also copies it.

The source used Claude Code, which can take actions on your computer or in a browser. These are general chat tools, so results may differ, and a normal chat may only give you a plan.

Opens in a new tab. We don't see what you send.

These links are only a shortcut. We're not affiliated with OpenAI, Google, Anthropic or xAI, and your results may not match the source.

Optional stronger version

Our rewrite with extra checks. The poster didn't test it.

Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish.

Goal: Run my daily secretary loop from markdown playbooks without spending money on your own.

Questions to ask me first:
- Which agent folder and connectors are live?
- What is urgent vs later today?
- Any sends that need approval?

Inputs (fill in or confirm):
- Agent root: [~/ai/agents/muninn]
- Domains: [EMAIL / CALENDAR / HOME / COOKING]
- Approval: [SENDS / ORDERS]

Rules:
- Follow CLAUDE.md and domain files.
- Surface urgent items first.
- Never place paid orders without approval.
- Dictate-friendly short briefs.

Checkpoint: Give a 5-line brief before acting on sends.

If you get stuck: If an MCP is down, report it and continue with the rest.

Verify before you finish: Actions match playbooks; paid steps are pending my OK.

Output: Brief plus proposed actions.

Done when: I know what needs me without opening every app.

AI tool

Claude Code

Outcome

Rutger de Knijf's Claude Code "Muninn" secretary is defined entirely in markdown playbooks. It reads email, manages calendar, checks a car's charge level, orders groceries, and surfaces sleep data through MCP connectors. The poster dictates instructions by voice; Claude Code writes the CLAUDE.md files. OpenClaw was tried first and felt too dumb; Claude Code was smart enough to stick.

Evidence: Described by posterThe person describes what happened in words, without screenshots or video.

Source

Posted
by Rutger de Knijf
Last checked
Method:
How we verify

https://dev.to/rdeknijf/my-ai-secretary-217j

More in Business admin & workflows

Similar cases