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.
Loading preview…
Free to start · guided setup · switch agents any time.

Live demo

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

Nordfrakt export jobacme-ingest-eu

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.

What you'll need

Set up in minutes

Using this template drops you into a guided setup. It asks exactly this, nothing else:

  1. Connect Google Cloud Storage

    One sign-in. The agent acts through your account, scoped to what this template uses.

  2. Connect Slack

    One sign-in. The agent acts through your account, scoped to what this template uses.

  3. 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.

  4. Runs on OpenCode

    Preselected for this page — connect your OpenCode account during setup, or switch to NoClick's built-in models with one click.

  5. Watch it handle a test run

    A staged conversation against a simulated world — then it’s live.

A considered pairing

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.

Good to know

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.

Other editions

Run it with a different agent

claude-codeClaude CodeOpenAICodexopenclawhermesMore OpenCode agents

Make it yours

Put Cloud Storage Object Watch to work on OpenCode.

Free to start. Guided setup, a staged test run, and a workflow you can change at every step.