YouTube Comments Agent with OpenCode
The morning pass is read, group, count, and write one message in four sections. The grouping is the part that earns its keep, because eleven people asking the same thing is one item with a number on it rather than eleven replies to write. A job with edges this clear is what OpenCode is light enough to carry, and the model underneath stays your choice.
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.
Comments digest, Tuesday 14 April
312,000 subscribers. Overnight there are 214 new comments across six videos, 90 of them on Sunday's dovetail jig tutorial, which has passed 180,000 views. Eleven people ask which router bit was used and the video never says, four ask whether the jig fits an imperial base, and one account named for a Spanish tool brand asks who handles paid collaborations.
Set up in minutes
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect YouTube
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.
Channel rules
What your channel wants surfaced and how you sound when you answer: which questions deserve a reply, who handles sponsorship and press, what you treat as spam, and any subject you never discuss in the comments. Draft replies copy the tone you describe here.
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
Counting turns comments into a brief
A question asked eleven times is not eleven replies, it is one decision about the next upload or a pinned comment. The count is what makes that obvious.
Spam reported as a wave
Impersonation scams arrive in bulk and target viewers rather than the channel. The pattern, the count and the videos hit turn a fortnight of one by one deletion into a single clear out.
Before you fork
Our comments come in four languages. What happens to those?
Comments are quoted in the language they were typed in and drafts are written in that language too, so nobody ends up pasting an English reply under a Spanish question. How well that reads depends on the model you connect, which is one field to change rather than a rebuild. Try two on the same morning batch before committing.
Run it with a different agent
Put YouTube Comments Agent to work on OpenCode
Free to start. Guided setup, a test run against staged conversations, and it's live.