Umami keeps analytics private and lightweight, but the dashboard still assumes you know what a referrer or a bounce is. This summary speaks to people who don't.
sonnet2 daysUmami APIOpenAITelegramCron
Claude
78ROI
73Scale
$2.1k82Saved
ROI for
README.md
Why this subagent
Umami keeps analytics private and lightweight, but the dashboard still assumes you know what a referrer or a bounce is. This summary speaks to people who don't.
It reads your Umami stats and writes a friendly recap: how many people visited, where they came from, which pages they read, and what changed. Founders and clients get a clear paragraph emailed to them instead of a panel they never open.
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.
Compute the changes against the previous period and highlight what shifted.
pending
Write the result for someone who has never opened an analytics tool.
pending
Send the short summary to email or Telegram on a recurring schedule.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Turn the Umami stats into a friendly summary for a non-analyst: how many visitors, where they came from, top pages, and what changed since last period.
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.