Cloud Storage Object Watch with OpenCode
Each run is a listing and a comparison. List the same prefix for the previous few days, read what those deliveries weighed, how many pieces they came in and when they arrived, put tonight's numbers beside that range, then decide whether a Slack line is warranted at all. OpenCode suits a loop this repetitive, and with the engine open the cost per object becomes a choice you make.
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.
partners/nordfrakt/2026-08-12/deliveries_0004.parquet
412 MB, written 04:07 UTC by the partner service account. Parts 0001 to 0003 landed between 04:02 and 04:06 at 380 to 430 MB each. The same prefix on the four previous days held six parts and a _MANIFEST file. No manifest has appeared for today.
Set up in minutes
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect Google Cloud Storage
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.
Bucket rules
What a correct delivery looks like in this bucket - the prefixes and naming shape you expect, who sends what and roughly when, how large a normal drop is, how many pieces a full one contains or which manifest closes it, and who to name in Slack when a delivery goes wrong.
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
List, compare, sometimes speak
Most objects land exactly as expected and produce silence. A loop that ends without a message on the ordinary nights is what keeps the channel worth reading on the bad ones.
Cheap per object matters here
This is one of the higher volume templates, so a small difference in model cost multiplies quickly. Sizing the engine down is a legitimate answer when the check is this mechanical.
Before you fork
Can it work out whether last night's data is complete?
Only in the sense the bucket can show: which parts are present, which are missing, whether the manifest arrived, and how tonight's size sits against the last few nights. Row counts, schema drift and duplicated batches live inside the file and it never opens one, so completeness in that sense stays with your pipeline's own validation.
Run it with a different agent
Put Cloud Storage Object Watch to work on OpenCode
Free to start. Guided setup, a test run against staged conversations, and it's live.