Log inPost

Agent builds / AI agents

Agent build · v1

AI outreach agent team: short-lived role agents on a schedule (free sample)

What it does: The layout of a Claude Code agent team that runs replies, inbox and numbers on a schedule. Each role wakes up, does one run, writes down what it learned, and exits. Sample of the paid kit.

by @mattbuselupdated 2 h ago#ai-agents#growth#llms
Model
Claude Opus and Claude Sonnet (Claude Code background agents)
Runs in
Claude Code scheduled tasks, Playwright over CDP
Cost per run
not measured
License
MIT
Used by
0
Files
8 (20 KB)
Download .zipLog in to fork or star
curl -L https://tensorust.com/builds/ai-outreach-agent-team/download -o ai-outreach-agent-team.zip

Receipts

Receipt
962,969
X views on the team's posts and replies, as counted on the team's public receipts page
Source
https://agent-receipts-five.vercel.app/
Measured
Oct 22, 2026
Check
Number found on the source page by our checker
Stamp
w5H4zZScAptjReQTwOTdHqZ7ELh2hJd_
Receipt
845
actions (replies, posts, comments, articles) logged by the agents since 2026-10-09
Source
https://agent-receipts-five.vercel.app/
Measured
Oct 22, 2026
Check
Number found on the source page by our checker
Stamp
N8LcJHO392fsJGWy_O4kp8pjF7_h1543

Files

tools/start-browsers.ps1raw
# Starts the browsers the agent team attaches to. Safe to run any time:
# it only starts a profile whose CDP port is not already answering.
# Agents never launch browsers themselves; they attach with Playwright connectOverCDP.

$Chrome = "C:\Program Files\Google\Chrome\Application\chrome.exe"
$Profiles = @(
  @{ Port = 9336; Dir = "$env:USERPROFILE\agent-chrome\personal"; What = "personal X + LinkedIn" },
  @{ Port = 9335; Dir = "$env:USERPROFILE\agent-chrome\posting";  What = "article cross-posting (dev.to, Medium, GitHub)" },
  @{ Port = 9337; Dir = "$env:USERPROFILE\agent-chrome\accounts"; What = "brand X + business inbox" }
)

function Test-Cdp($port) {
  try { Invoke-WebRequest -UseBasicParsing -TimeoutSec 3 "http://127.0.0.1:$port/json/version" | Out-Null; return $true } catch { return $false }
}

foreach ($p in $Profiles) {
  if (Test-Cdp $p.Port) { Write-Output "$($p.What) ($($p.Port)): already running"; continue }
  Start-Process $Chrome -ArgumentList "--remote-debugging-port=$($p.Port)", "--user-data-dir=`"$($p.Dir)`"", "--no-first-run"
  Write-Output "$($p.What) ($($p.Port)): started"
}

Start-Sleep -Seconds 8
foreach ($p in $Profiles) { Write-Output ("{0} up: {1}" -f $p.Port, (Test-Cdp $p.Port)) }

# Clear browser locks left by a crashed agent (older than 15 minutes).
$Locks = Join-Path $PSScriptRoot "..\locks\*.lock"
Get-ChildItem $Locks -ErrorAction SilentlyContinue | Where-Object { $_.LastWriteTime -lt (Get-Date).AddMinutes(-15) } | Remove-Item -Force -ErrorAction SilentlyContinue

README

This is the structure behind the agent team that has run Tensorust's distribution since 2026-10-09: X replies, long-form articles, cold email, an inbox closer and a daily numbers agent. It runs on Claude Code. Nothing stays on. A scheduled job wakes up, spawns one short-lived background agent for one role, the agent does one run, and it exits.

Each role is two files. ROLE.md is the playbook: the job, what to read first, the steps, hard caps and what to log. NOTES.md is the role's memory: a LESSONS block at the top that the agent reads before acting, and a run log it appends to after (TRIED, RESULT, LESSON). Shared files hold the voice, the goals, and posts.json, a log of every action with its live URL. Cadence limits are checked against posts.json before anything is posted, so two runs can never double-post.

What is in this sample:

README.md: the architecture and how a run works.
shared/RULES.md: the rules every role reads first (real Chrome only, never sign out, reuse tabs, stop on 401 and 429, log the live URL).
shared/LEARNING-LOOP.md: how roles get better between runs.
roles/x-reply/ROLE.md and roles/numbers/ROLE.md: two of the role briefs.
schedule.example.json: three jobs with their exact prompts, including the precheck the main session runs before spawning anything.
.claude/skills/agent-team-restart/SKILL.md: a skill that brings the whole team back in a fresh session.
tools/start-browsers.ps1: starts the Chrome profiles agents attach to.

How to run it:

1. Start Chrome profiles with remote debugging (tools/start-browsers.ps1) and sign into each account by hand.
2. Put the files under outreach/ as laid out in README.md, write your own VOICE.md and PLAYBOOK.md, and fill the handles and ports in schedule.json.
3. In Claude Code, run the restart skill. It checks logins read-only and creates one scheduled job per entry in schedule.json.

/agent-team-restart

Scheduled jobs in Claude Code live only in the session and expire after 7 days, so run the restart skill in every new session and at least weekly.

What to change: your platforms, your ports, your voice, and the cadences. Start with low cadences; new accounts get rate-limited fast. Keep the shape: one run per agent, cheap prechecks in the main session, every action logged with a live URL, and a numbers agent that writes one change per role per day.

The full kit, The Agent-Run Outreach Team, adds the other roles (scout, LinkedIn, community, articles, revenue), the pacing gate and posts log enforced in code, the scorecard and learning scripts, and a setup guide: https://shop.tensorust.com/

JSONshare on X

0 comments

Log in to comment