Listmonk Newsletter Agent

Claude Code agent that drafts the issue and drives self-hosted listmonk over its admin API: draft, test-send, schedule. Bring your listmonk token.

NewNew40.0 KB snapshotStarter VM

What's inside

Harness

Claude Code

Plan

Starter

vCPU

1

Memory

2 GiB

Snapshot

40.0 KB

Setup prompt + walkthrough

The Listmonk Newsletter Agent setup prompt + walkthrough

Paste this into any capable agent and it walks you through the connections, the trigger, and a supervised first run — the whole setup, in your own words. Or skip the setup and run this exact agent hosted.

Set up an agent for me, in its own chat, that does the work of a Listmonk Newsletter Agent. Work from the files and facts I actually give it, rank what matters by impact rather than by how many items it found, and stop short of sending, filing, posting, or changing anything live unless I ask for that in the same run. Walk me through connecting the keys this work needs. Have it run whenever I hand it the work, and every weekday morning on whatever I left unfinished. Ask me where the source material lives, who should receive the output, and what good enough looks like for a first pass. Run one pass while I watch, then save it.

Already built, running in ~3 min · 30-day money-back on first purchase

How it works · ~3 minutes

  1. 01 · Fork

    New isolated microVM on your subdomain — creator agent state included.

  2. 02 · Your keys

    Log into Claude Code with your own model credentials (BYOK).

  3. 03 · Ask it to work

    Open the terminal and give the agent a real job. You keep what ships.

Example first ask

Pull my open PRs, summarize risk, and draft a review checklist.

30-day money-back on your first purchase · no free trial · keys never leave the VM

About this template

Your newsletter, drafted and already sitting in listmonk

If you self-host listmonk and your writing workflow is still "Google Doc, then copy-paste at 11pm," this Claude Code agent closes that gap: it drafts the issue and creates the campaign over listmonk's admin API.

Draft. Test-send. Schedule.

What the listmonk skill actually does

The listmonk skill talks to your instance's admin REST API.

That means lists, subscribers, campaigns, templates, and test sends are things the agent reads and creates — not things it describes to you in chat. newsletter-write handles the craft: subject lines, structure, and the markdown or HTML body. campaign-ship runs the last mile — create the draft, test-send, schedule or start, then report status back.

You still press the button on the real send.

What lands in your fork

Five skills, wired together:

  • listmonk — admin REST API: lists, subscribers, campaigns, templates, test sends
  • newsletter-write — subject lines, structure, markdown/HTML body
  • campaign-ship — draft, test-send, schedule or start, report status
  • emails — welcome, drip, re-engagement and lifecycle sequences
  • copywriting — headlines, CTAs and page copy when an issue needs a landing page

What you supply (BYOK)

Three things, none of them baked into the template:

  • Claude Code credentials — the harness runtime
  • Your listmonk base URL and an admin API token
  • Sending infrastructure, configured on your listmonk instance (its SMTP, not ours)

You wire all three in yourself after forking, on your own VM.

Your first five minutes

Fork it, then open Claude Code on the VM.

Point the listmonk skill at your base URL and admin token. Ask for something specific:

Draft this week's issue about . Create a listmonk draft campaign and test-send it to me.

The proof is not the chat reply. It's a draft campaign sitting in your listmonk admin, and a test send in your inbox.

Honest limits

This template assumes listmonk.

There is no beehiiv, Substack or Mailchimp path in here — if you don't self-host listmonk, or won't, skip it. It runs on Claude Code, not another harness. And it stops short of autopilot on purpose: a human approves the real send, because an agent holding your whole list with no review step is how you burn a sending domain.

Your listmonk host and your model spend stay yours.

Risk

30-day money-back on your first jurniti purchase.

Fork it. Wire listmonk. Test-send one issue tonight.

Inside this fork

Forking copies this template into a brand-new, fully isolated microVM on your own subdomain. Here's exactly what lands in it.

  • Claude Code agent

    The upstream harness, pre-installed — same version the creator ran.

  • Starter VM

    1 vCPU · 2 GiB RAM · 10 GiB disk.

  • Creator's /persist data

    The captured persist volume is copied byte-for-byte into your fork.

  • BYOK — your keys, your VM

    Add your model API keys after forking; they live only inside your microVM.

What this agent can do

5 skills

  • campaign-ship

    Ship a finished newsletter through listmonk — create draft, test-send, schedule or start, and report status. Use when the user says ship,…

  • copywriting

    When the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature…

  • emails

    When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when…

  • listmonk

    Operate a self-hosted listmonk instance via its admin REST API — lists, subscribers, campaigns, templates, test sends. Use when the user…

  • newsletter-write

    Draft high-signal newsletter issues (subject lines, structure, markdown/HTML body) for listmonk campaigns. Use when the user asks to write…

Your turn

Your own Listmonk Newsletter Agent, live in about 3 minutes.

Copy the setup prompt and build it yourself — or let this exact Claude Codeagent run hosted, already built, on a brand-new, fully isolated microVM on your own subdomain. Add your own keys after it boots; they never leave the box. Don't love it? Your first jurniti purchase comes with 30 days to get every cent back.

New paid VM · BYOK · 30-day money-back on your first purchase · ~3 min to provision