home / skills / sickn33 / antigravity-awesome-skills / agent-manager-skill

agent-manager-skill skill

safe

This skill helps you manage multiple local CLI agents via tmux, including start/stop, monitor, assign, and cron-like scheduling.

This is most likely a fork of the agent-manager-skill skill from xfstudio

npx playbooks add skill sickn33/antigravity-awesome-skills --skill agent-manager-skill

Review the files below or copy the command above to add this skill to your agents.

Files (1)

SKILL.md

1.0 KB

---
name: agent-manager-skill
description: Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
---

# Agent Manager Skill

## When to use

Use this skill when you need to:

- run multiple local CLI agents in parallel (separate tmux sessions)
- start/stop agents and tail their logs
- assign tasks to agents and monitor output
- schedule recurring agent work (cron)

## Prerequisites

Install `agent-manager-skill` in your workspace:

```bash
git clone https://github.com/fractalmind-ai/agent-manager-skill.git
```

## Common commands

```bash
python3 agent-manager/scripts/main.py doctor
python3 agent-manager/scripts/main.py list
python3 agent-manager/scripts/main.py start EMP_0001
python3 agent-manager/scripts/main.py monitor EMP_0001 --follow
python3 agent-manager/scripts/main.py assign EMP_0002 <<'EOF'
Follow teams/fractalmind-ai-maintenance.md Workflow
EOF
```

## Notes

- Requires `tmux` and `python3`.
- Agents are configured under an `agents/` directory (see the repo for examples).

Overview

This skill manages multiple local CLI agents using tmux sessions so you can run, monitor, and schedule autonomous workers on a single machine. It provides start/stop/monitor/assign commands and supports cron-friendly scheduling for recurring tasks. It is lightweight, Python-based, and designed for parallel local agent workflows.

How this skill works

The skill orchestrates each agent inside its own tmux session and exposes a CLI to list sessions, start or stop agents, tail logs, and assign textual tasks. It stores agent configurations in an agents/ directory and uses tmux to keep agents running detached. A scheduling layer allows cron-style recurring assignments and automated starts.

When to use it

Run many local CLI agents in parallel on one host
Keep agents running persistently across shells using tmux
Assign tasks to specific agents and monitor their realtime output
Automate recurring agent work using cron-friendly scheduling
Quickly debug agent logs and health with built-in monitoring commands

Best practices

Keep each agent’s configuration and working directory under agents/ for predictable management
Use descriptive agent IDs (EMP_0001 style) so CLI commands and cron entries remain readable
Run health checks (doctor command) after setup and before adding schedules
Pipe multi-line assignments via heredoc to preserve complex instructions when using assign
Use system cron or a lightweight scheduler to trigger assignment commands at fixed intervals

Example use cases

Run a fleet of code-assistant agents, each focused on a submodule, and monitor them independently
Schedule nightly maintenance tasks for security-auditing agents using cron-friendly assignment
Assign a bug triage task to a dedicated agent and follow its output live for real-time feedback
Start a group of data-processing agents in parallel, tail logs to diagnose failures, and restart failed sessions automatically
Maintain separate tmux sessions for experimental agents to isolate resource usage and logs

FAQ

What dependencies are required?

Requires python3 and tmux. Ensure tmux is installed and available in PATH.

Where do I define agents?

Agents are configured under an agents/ directory; each agent has its own folder and startup configuration used by the CLI.