Zero-token cron jobs for the chores around your AI coding agents

Description and use

Scripts for daily chores run via Clusto without LLM tokens; results are posted to a report feed, and failures appear as error cards on the phone.

Problem

Running routine scripts through an AI model wastes tokens and produces unread mail spool output.

Outcome

Daily marketing stats are collected and reported every morning at 08:30 Prague time with zero token cost, and failures are automatically reported as error cards on the phone.

Workflow

• Write chore as a script that exits 0 on success and non‑zero on failure.
• Schedule the script with Clusto’s task scheduler.
• Post a short result to the Clusto Reports feed.
• Call an LLM only for judgment steps, keeping it in the same schedule.

Evidence

Not every job you hand an AI coding agent needs the model. A lot of the daily chores around a project are plain scripts: pull some numbers, check that a site answers, run the test suite, write a summary.

Source

Every morning at 08:30 Prague time, a task on one of our servers runs a Node script. It snapshots the reactions and comments on our posts through public APIs, checks follower counts, checks that the website and release manifests respond, and writes a markdown summary. Then the shell posts that summary to the Clusto Reports feed. No LLM is involved, so the run costs zero tokens.

Source

The Reports feed collects what scripts and agents post: a title, a level (Info, Success, Warning, Error), a markdown body, and optional attachments such as a chart or a CSV.

Source