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.

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)
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

shared/RULES.mdraw
# Team rules (every role reads this first, every run)

These sit at the top of agents/README.md. Newer headers go on top and override older text below them; date each one so agents can tell which wins.

## Browsers and accounts
- Real Chrome only. Never launch a browser (no chromium.launch, launchPersistentContext, puppeteer.launch, headless). Attach to the running Chrome on its CDP port with Playwright connectOverCDP and pass {timeout: 60000}. If a port is down, stop and report.
- Never sign out. Never click Sign out, Log out, Switch account, Remove account or an account chooser on any site.
- Never close a tab you did not open, never close a window or the browser, never call browser.close() or context.close(), never clear cookies or storage, never open incognito.
- Reuse open tabs. Before opening anything, list the tabs on your port (http://127.0.0.1:PORT/json/list) and drive the one already on the site you need. Each role keeps one persistent tab of its own and leaves it open at the end.
- Chrome freezes idle background tabs and connectOverCDP can then hang. Wake the tab first (switch to it and back) before attaching.
- Before posting from an account, confirm the signed-in profile is the one you expect (for example the sidebar profile link). If it is not, skip and report.
- If an account looks signed out, stop and report which window needs a human. Never type passwords.

## Credentials
- No credential hunting. On a 401 or 403, stop and report. Never go looking for another key, token or account.

## Pacing
- Every cadence is checked against posts.json before acting (for example: skip if this account already replied in the last 50 minutes; skip any handle this account replied to in the last 24 hours).
- Stop the run on the first 429 or rate-limit page. Do not retry in a loop.
- Never re-post after an error until you have checked whether the first attempt went live.

## Logging
- Get the real time with `date` before logging anything. Never guess or copy times from other notes.
- A post counts only when its live URL is recorded in posts.json (platform, ts, url, target, text).
- Append your run to your role's NOTES.md (see LEARNING-LOOP.md).

## Content floor
- Real facts, quotes and numbers must be true. Opinions and predictions are welcome when they read as opinion.
- No invented first-person experiences, quotes, screenshots or sources.
- No slurs, hate, sexual content about real people, threats, doxxing, or piling on private individuals. Skip tragedies.
- Reply to real people, not brand or news accounts. No plugs unless the thread asked for exactly what you make, and then disclose it is yours.

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/

0 comments

Log in to comment