Blog Draft Agent with OpenCode
OpenCode's model field is the most consequential setting on this template, because the output is 1200 words a person will read rather than a table of numbers. This is the one job in the catalogue where paying for a stronger model shows up immediately in the artefact. Everything around it, the calendar, the voice guide and the draft-only write path, stays the same.
Watch it work before it's live
Run a staged conversation — no account needed. The agent handles it for real while a simulated world answers its tool calls; nothing touches real accounts, and nothing is actually sent.
Tuesday 10:00 draft slot
It is Tuesday 10:00 and the next unwritten row on the calendar is a guide to cutting warehouse pick errors, aimed at operations managers at distributors of 20 to 200 people, with notes covering the three causes the team sees most often and one customer story the founder wrote up last month. The four most recent published posts were two product updates and two customer stories.
Set up in minutes
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect WordPress
One sign-in. The agent acts through your account, scoped to what this template uses.
Connect Slack
One sign-in. The agent acts through your account, scoped to what this template uses.
Content calendar
The topics you want written, in the order you want them - for each one the angle, who it is for, the category it belongs in, the call to action, and any facts, numbers or customer details the post is allowed to state. The agent only writes what is here.
Voice guide
How your blog should read - person and tone, sentence and section length, how technical to get, the words and claims you never want to see, and one or two published posts you consider the standard.
Runs on OpenCode
Preselected for this page — connect your OpenCode account during setup, or switch to NoClick's built-in models with one click.
Watch it handle a test run
A staged conversation against a simulated world — then it’s live.
Why OpenCode for this agent
Prose rewards model strength
Unlike a digest, the difference between two models here is visible in the first paragraph. Read them side by side and pick.
Voice guide does the steering
Tone, person, sentence length and banned words all come from your variable, so a model swap changes fluency rather than style.
Before you fork
Can I try two models on the same topic?
Yes, and it is the cleanest comparison available: run Calendar Topic Ready on one model, change the field, run it again, and read both drafts. Neither run publishes anything, so the experiment costs you two drafts. Keep the voice guide identical between them so you are comparing the model rather than the brief.
Run it with a different agent
Put Blog Draft Agent to work on OpenCode
Free to start. Guided setup, a test run against staged conversations, and it's live.