Slack Support Agent with OpenCode
An internal support bot is the one place you can be blunt about cost, because nobody outside the company ever sees it. OpenCode is model-agnostic, so you can leave it watching every channel on a modest model and reach for something stronger only if the answers start reading thin. Being an open harness inside an engineering org also tends to be an easier conversation than a closed one.
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.
Contractor access without billing visibility
Marta Nowak
@support how do I give a contractor access to one project only, without them seeing billing? A client asked this morning and I could not find it anywhere in the docs.
Set up in minutes
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect Slack
One sign-in. The agent acts through your account, scoped to what this template uses.
Connect Linear
One sign-in. The agent acts through your account, scoped to what this template uses.
Product context
What your product does, the words your team uses for its parts, and where the real documentation lives. Paste the links you want people sent to.
Escalation rules
What the agent must not answer alone and who takes it instead. Name the person or channel for billing, security, outages, and anything a customer will see.
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
Cheap enough to leave on
Choosing the model yourself is what makes it reasonable to have the agent listening in six channels instead of one carefully rationed one.
Open in an engineering org
Teams that already prefer open tooling do not have to carve out an exception for the thing answering their own questions.
Before you fork
Does the model choice change how it handles Linear?
The tools stay identical, the judgment does not. Every harness gets the same Linear search and create operations from the node you wire in, but a weaker model is likelier to file a duplicate or write a vague description. Read the first week of issues before you widen the channels it listens to.
Run it with a different agent
Put Slack Support Agent to work on OpenCode
Free to start. Guided setup, a test run against staged conversations, and it's live.