SEO Performance Digest Agent with OpenCode
The dangerous output here is a confident one: two pages lost half their impressions after a core update, and the digest explains why. It cannot know why, and the template says to write that the data does not show why. Model choice decides whether that instruction survives contact with an obvious-looking story, which makes OpenCode's model field the setting to think about.
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.
Monday 09:00 weekly digest tick
It is Monday 09:00 in Bristol and this run covers the week to yesterday for velobrook.co.uk, a cycling gear shop. A gravel bike buying guide published nine days ago picked up its first 240 clicks, and the brand query has been flat at about 1,900 clicks a week all quarter.
Set up in minutes
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect Google Search Console
One sign-in. The agent acts through your account, scoped to what this template uses.
Connect Google Sheets
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.
Site context
Your verified property, what the site sells, who reads this digest each week, and who to tag when a number looks wrong or a source fails.
Focus queries
The queries and pages you actually care about, in your own words, plus any you want ignored. These get reported every week whether they moved or not.
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
Restraint is model dependent
Refusing to explain a movement is harder for a weak model than reporting one. This is the behaviour to test whenever you change models underneath.
Flexible spend per property
Agencies running a copy per client can put a cheaper model on quiet properties and a stronger one where the reporting gets scrutinised.
Before you fork
Can I run one copy per client?
That is the usual pattern: one workflow per verified property, with the client's queries in the variables and their own Slack channel. Model choice can differ per copy, which helps when one account is a small monthly invoice and another is a retainer. The tracked query list is the main thing you rewrite each time.
Run it with a different agent
Put SEO Performance Digest Agent to work on OpenCode
Free to start. Guided setup, a test run against staged conversations, and it's live.