A full inbox makes you do triage every time you open it. You scan the same fifty subject lines deciding what needs you, and the three messages that actually matter hide among the receipts and newsletters.
sonnet2 daysGmailOpenAI
Claude
71ROI
88Scale
$2.5k94Saved
ROI for
README.md
Why this subagent
A full inbox makes you do triage every time you open it. You scan the same fifty subject lines deciding what needs you, and the three messages that actually matter hide among the receipts and newsletters.
This agent pre-sorts new mail into reply, read, or archive so the work is done before you look. The noise gets filed, the read-later pile is set aside, and you get a short list of what truly needs an answer. You open your inbox to a clear next action instead of a pile to sift through.
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.
Sort every email into reply needed, read later, or archive.
pending
Apply the matching label or move so the inbox reflects the sort.
pending
Surface a short list of the reply-needed messages so you start with what matters.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
For each new email, return one of three buckets, reply, read, or archive, with a one-line reason for the choice.
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.