Cold campaigns burn domains when every email reads like a template and half the addresses bounce. This engine verifies each address first, then writes a genuinely personalized opener from a recent signal about the contact.
sonnet1 weekApolloClaudeInstantlyPostgreSQL
Claude
92ROI
83Scale
$4.1k94Saved
ROI for
README.md
Why this subagent
Cold campaigns burn domains when every email reads like a template and half the addresses bounce. This engine verifies each address first, then writes a genuinely personalized opener from a recent signal about the contact.
Sends spread across warmed inboxes with rate limits so you protect deliverability instead of torching it. Anyone who replies is pulled out of the sequence automatically, and the whole list state lives in Postgres for clean follow-up.
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.
Verify every address and drop catch-all or risky domains before any send.
pending
Generate a personalized first line and a short three-step sequence per contact.
pending
Schedule sends across warmed inboxes with rate limits and pause anyone who replies.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Write a cold email with a one-line personalized opener and a soft CTA; under 90 words, no fake compliments.
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.