Daily Engineering Digest Agent with OpenCode
A digest that runs 22 times a month has an unusual cost profile: few runs, each of them substantial. OpenCode lets you spend that budget where it helps, choosing something capable for a message the whole org reads, or something lean while you are still arguing about which sections to keep. Your team context and digest style sit underneath, unaffected by the swap.
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.
Weekday 08:00 digest tick
It is Tuesday 08:00 in Berlin and standup is at 09:15. Overnight the Platform and Payments teams closed nine issues and moved three into review, while the checkout migration has not changed state since Friday.
Set up in minutes
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect Linear
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.
Team context
Your Linear teams and projects, who owns this digest, and what your leadership actually asks about each morning.
Digest style
Which sections your team really reads, how blunt the tone should be, and how long the digest can run before people skim past it.
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
Few runs, so spend well
Unlike per-email agents this one fires once a morning. Model freedom means you can afford something strong for the message with the widest audience in the company.
Iterate on the format cheaply
Getting sections right takes several passes against the staged mornings. Running those on a lean model while you tune costs close to nothing.
Before you fork
Does the model I choose change how good the digest is?
It moves the judgment calls more than the facts. Facts are read straight from Linear and the sections are fixed, but deciding what belongs under STUCK rather than MOVING, and how a blocker gets phrased, is where a stronger model reads better. The three staged mornings, quiet Friday included, are the fastest way to compare two models on your own teams.
Run it with a different agent
Put Daily Engineering Digest Agent to work on OpenCode
Free to start. Guided setup, a test run against staged conversations, and it's live.