Agent Manager Skill
Run several local CLI coding agents in parallel with tmux sessions, task assignment, log monitoring, and optional cron scheduling.
Overview
agent-manager-skill is an agent skill most often used in Build (also Operate) that manages multiple local CLI agents through tmux sessions with start/stop, monitoring, assignment, and cron-friendly scheduling.
Install
npx skills add https://github.com/sickn33/antigravity-awesome-skills --skill agent-manager-skillWhat is this skill?
- Start, stop, list, and monitor CLI agents in separate tmux sessions
- Assign task prompts to agent IDs via main.py assign
- doctor command checks environment before running agents
- Cron-friendly scheduling for recurring agent work
- Requires tmux and python3; agents live under a configurable agents/ directory
Adoption & trust: 702 installs on skills.sh; 40.1k GitHub stars; 1/3 security scanners passed (skills.sh audits).
What problem does it solve?
You want several coding agents working in parallel locally but juggling terminals, logs, and recurring jobs manually does not scale.
Who is it for?
Solo builders running 2+ local CLI agents on one machine who already use tmux and want a small Python CLI instead of bespoke shell scripts.
Skip if: Teams needing cloud-hosted agent fleets, Kubernetes job runners, or orchestration without tmux and local shell access.
When should I use this skill?
You need to run multiple local CLI agents in parallel via tmux, start/stop them, tail logs, assign tasks, or schedule recurring agent work with cron.
What do I get? / Deliverables
Named agents run in managed tmux sessions with assignable tasks and followable logs, and you can wire recurring runs via cron without a separate orchestration product.
- Running tmux-backed agent sessions with streamed logs
- Task assignments delivered to configured agent IDs
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Primary shelf is Build agent-tooling because you install and orchestrate agents while developing; the same manager stays useful in Operate when agents run recurring maintenance. Parallel tmux sessions, assign workflows, and monitor output are core multi-agent developer ergonomics, not end-user product features.
Where it fits
Spin up EMP_0001 and EMP_0002 in parallel tmux sessions while one agent handles API work and another updates docs.
Assign a backend migration checklist to a dedicated agent and monitor --follow until migrations finish.
Schedule cron to restart a maintenance agent that follows teams/fractalmind-ai-maintenance.md nightly.
Route a pre-release review prompt to an isolated agent session without blocking your main coding agent.
How it compares
Local tmux-based agent foreman—not a substitute for CI pipelines or managed multi-tenant agent hosting.
Common Questions / FAQ
Who is agent-manager-skill for?
Solo and indie developers orchestrating multiple local CLI coding agents with tmux who want list/start/monitor/assign commands from one skill.
When should I use agent-manager-skill?
During Build when parallel agent sprints need separate sessions; during Operate when cron should restart agents on maintenance workflows; anytime you must tail agent logs without opening each tmux pane manually.
Is agent-manager-skill safe to install?
It runs shell and tmux locally—review the Security Audits panel on this page and inspect agent-manager scripts and agents/ configs before granting network or secret access.
SKILL.md
READMESKILL.md - Agent Manager Skill
# 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). ## Limitations - Use this skill only when the task clearly matches the scope described above. - Do not treat the output as a substitute for environment-specific validation, testing, or expert review. - Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.