Cloud and LLM bills creep up quietly, and you usually find out at the end of the month when the invoice lands. This watcher checks both every morning and tells you what changed.
Cloud and LLM bills creep up quietly, and you usually find out at the end of the month when the invoice lands. This watcher checks both every morning and tells you what changed.
It diffs yesterday's spend against a rolling average, flags real anomalies, and names the service or model behind each jump. You get a daily spend diff in Slack before small leaks turn into a budget problem.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Compare each line against its trailing 7-day average to find anything that moved sharply.
pending
Flag spikes above a set percentage and attribute them to the service, model, or account that grew.
pending
Send a daily diff to Slack and append the figures to BigQuery for the monthly rollup.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Compare today's per-service cloud and per-model LLM spend against the 7-day average, and return a diff listing every line that moved more than the threshold, with the dollar delta and likely driver.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.