Claude Code logo
Claude Code template
github.comclay.com

Clay Outbound Engine

Find 20 CEOs. Get work emails. Draft openers. Clay’s search→enrich loop, preinstalled on Claude Code — fork it, clay login, go. Your credits.

NewNew33.7 MB snapshotStarter VM

What's inside

Harness

Claude Code

Plan

Starter

vCPU

1

Memory

2 GiB

Snapshot

33.7 MB

Setup prompt + walkthrough

The Clay Outbound Engine setup prompt + walkthrough

Paste this into any capable agent and it walks you through the connections, the trigger, and a supervised first run — the whole setup, in your own words. Or skip the setup and run this exact agent hosted.

Set up an agent for me, in its own chat, that does the work of a Clay Outbound Engine. Work from the files and facts I actually give it, rank what matters by impact rather than by how many items it found, and stop short of sending, filing, posting, or changing anything live unless I ask for that in the same run. Walk me through connecting Clay. Have it run whenever I hand it the work, and every weekday morning on whatever I left unfinished. Ask me where the source material lives, who should receive the output, and what good enough looks like for a first pass. Run one pass while I watch, then save it.

Already built, running in ~3 min · 30-day money-back on first purchase

How it works · ~3 minutes

  1. 01 · Fork

    New isolated microVM on your subdomain — creator agent state included.

  2. 02 · Your keys

    Log into Claude Code with your own model credentials (BYOK).

  3. 03 · Ask it to work

    Open the terminal and give the agent a real job. You keep what ships.

Example first ask

Pull my open PRs, summarize risk, and draft a review checklist.

30-day money-back on your first purchase · no free trial · keys never leave the VM

About this template

Find 20 CEOs. Get the emails. Draft the openers.

You already know the Clay motion.

ICP. Company search. People search. Waterfall work emails. Personalization. Export. Sequencer.

What you do not want: another afternoon wiring the Clay agent plugin, hunting PATH, relearning Search vs Routines, and rewriting the same loop in a blank Claude chat.

This template is that loop, already on Claude Code.

Fork it. Log into your Claude. Run clay login with your Clay workspace. Then paste:

Find 20 Series B fintech companies in New York, get each CEO's work email, and draft a first-touch cold email for each.

You get a shortlist, fill rate, CSV + markdown under outputs/, and nothing auto-sends. You own the list. You own the send.

What you get

  • clay CLI pinned under ~/.agents/bin (survives fork — not a throwaway /tmp install)
  • Official Clay skills from clay-run/agent-plugins: search, routines, setup, cli, …
  • clay-outbound playbook — ICP → Search → email routine → score → draft openers
  • CLAUDE.md + MCP wiring so the agent knows the PATH and the job

First five minutes

  1. Fork this template → open the terminal.
  2. Log into Claude Code (claude or your Anthropic key).
  3. export PATH="$HOME/.agents/bin:$PATH" && clay login (browser OAuth — pick your workspace).
  4. Restart Claude Code once so Clay MCP sees the session.
  5. Paste the demo prompt above.

Clay credits/actions are yours — same as the Clay UI. No markup. No mystery keys in the snapshot.

Who this is for

  • GTM engineers and founders who already live in Clay
  • People who want Claude Code to drive Clay, not re-implement enrichment
  • Anyone tired of re-explaining “search then find work email” every session

Who this is not for

  • Teams that need the full Clay table UI as the control plane (use Clay’s product)
  • Anyone who wants auto-send to Instantly / Outreach on day one (human gate is intentional)
  • Free-tier tire-kickers with no Clay plan (searches burn real credits)

BYOK

You bringNotes
Claude Code login / ANTHROPIC_API_KEYRun-time only
Clay workspace (clay login)Browser OAuth; session stays on your VM

Upstream

The rule that keeps you safe

Never auto-send. This agent builds the list and the first line. You hit send in your sequencer.

Fork it. It’s yours.

Risk note

jurniti 30-day money-back on your first paid purchase. Clay credits and model spend are yours.

Fork it. clay login. Paste the 20-CEO prompt.

Inside this fork

Forking copies this template into a brand-new, fully isolated microVM on your own subdomain. Here's exactly what lands in it.

  • Claude Code agent

    The upstream harness, pre-installed — same version the creator ran.

  • Starter VM

    1 vCPU · 2 GiB RAM · 10 GiB disk.

  • Creator's /persist data

    The captured persist volume is copied byte-for-byte into your fork.

  • BYOK — your keys, your VM

    Add your model API keys after forking; they live only inside your microVM.

What this agent can do

9 skills

Scannable skill names — open full descriptions only if you need them.

  • clay
  • clay-outbound
  • cli
  • public-api
  • routines
  • search
  • setup
  • tables

What you'll configure after forking

Secrets are scrubbed from shared templates — these are the names you supply in your agent's terminal once it boots.

MCP connections

  • clay

Your turn

Your own Clay Outbound Engine, live in about 3 minutes.

Copy the setup prompt and build it yourself — or let this exact Claude Code agent run hosted, already built, on a brand-new, fully isolated microVM on your own subdomain. Add your own keys after it boots; they never leave the box. Don't love it? Your first jurniti purchase comes with 30 days to get every cent back.

New paid VM · BYOK · 30-day money-back on your first purchase · ~3 min to provision