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
- Source
- https://agent-receipts-five.vercel.app/
- Measured
- Oct 22, 2026
- Check
- Number found on the source page by our checker
- Stamp
- w5H4zZScAptjReQTwOTdHqZ7ELh2hJd_
- 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
- .claude/skills/agent-team-restart/SKILL.md2 KB
- README.md3 KB
- roles/numbers/ROLE.md2 KB
- roles/x-reply/ROLE.md3 KB
- schedule.example.json4 KB
- shared/LEARNING-LOOP.md1 KB
- shared/RULES.md3 KB
- tools/start-browsers.ps11 KB
--- name: agent-team-restart description: Restart the whole outreach agent team in a fresh Claude Code session. Starts the browsers, checks each account is signed in, and recreates every scheduled agent job from outreach/agents/schedule.json. Use when the user types /agent-team-restart or asks to restart, resume or bring back the agents, the outreach, or "the jobs we had running". --- # Restart the agent team Everything lives on disk in `outreach/`. Claude Code scheduled jobs are session-only and expire after 7 days, so recreate them in every new session and at least weekly. Do the steps in order, then report in a few lines. ## 1. Start the browsers Run `outreach/agents/tools/start-browsers.ps1` (PowerShell). It starts each Chrome profile only if its CDP port is not already answering. ## 2. Check logins (read-only; never sign out, never switch accounts) - For each browser, open the account's home page in an existing tab and confirm the signed-in profile is the expected one (for example the X sidebar profile link, or the inbox address in Gmail). - If something is signed out, tell the user which window to sign into. Passwords are never stored on disk; never type one. ## 3. Recreate the jobs 1. List existing scheduled jobs first; do not duplicate any. 2. Read `outreach/agents/schedule.json`. For every item in `recurring`, create a recurring scheduled job with cron = item.cron and prompt = item.prompt. 3. For `one_shots`, create only those whose time is still in the future. 4. Skip everything under `disabled`. ## 4. Report 4 to 6 lines: browsers up, logins OK or what needs signing in, jobs recreated (ids), the latest dashboard numbers (last entry of `dashboard/history.json`), and a reminder that jobs die when the window closes and expire after 7 days. ## Where things live - `outreach/agents/schedule.json`: the live job list. If you change a role's timing or prompt, change it here too, or the next restart brings back the old version. - `outreach/agents/README.md` + `agents/<role>/ROLE.md` + `NOTES.md`: role instructions (top headers override older text). - `outreach/VOICE.md`, `PLAYBOOK.md`; every action logged in `outreach/posts.json`.
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-restartScheduled 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/