agent-manager-skill
A manager for running multiple local agents in parallel using tmux sessions.
Install
mkdir -p .claude/skills/agent-manager-skill && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/3720" && unzip -o skill.zip -d .claude/skills/agent-manager-skill && rm skill.zipInstalls to .claude/skills/agent-manager-skill
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.Key capabilities
- →Run multiple local CLI agents in parallel
- →Start and stop agent tmux sessions
- →Tail and monitor agent logs
- →Assign tasks to specific agents
- →Schedule recurring agent work via cron
How it works
The skill manages CLI agents by wrapping them in tmux sessions, allowing for persistent background execution, log monitoring, and task assignment.
Inputs & outputs
When to use agent-manager-skill
- →Running parallel CLI agents
- →Monitoring agent logs
- →Assigning tasks to agents
- →Scheduling recurring agent work
About this 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:
git clone https://github.com/fractalmind-ai/agent-manager-skill.git
Common commands
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
tmuxandpython3. - Agents are configured under an
agents/directory (see the repo for examples).
When not to use it
- →When tmux is not available in the environment
- →For agents that do not support CLI interaction
Prerequisites
Limitations
- →Requires agents to be configured in the agents/ directory
- →Limited to local execution environments
How it compares
It provides a structured management layer for local agents that would otherwise require manual tmux session handling.
Compared to similar skills
agent-manager-skill side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| agent-manager-skill (this skill) | 1 | 6mo | Review | Beginner |
| setup | 12 | 1mo | No flags | Beginner |
| resources | 1 | 2mo | Review | Intermediate |
| openrouter-team-setup | 0 | 27d | Caution | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by davila7
View all by davila7 →You might also like
setup
barefootford
Sets up a Mac for ButterCut. Installs all required dependencies (Homebrew, Ruby, Python, FFmpeg, WhisperX). Use when user says "install buttercut", "set up my mac", "get started", "first time setup", "install dependencies" or "check my installation".
resources
windmill-labs
MUST use when managing resources.
openrouter-team-setup
jeremylongshore
Configure OpenRouter for team and organizational use. Use when setting up multi-user access or department billing. Trigger with phrases like 'openrouter team', 'openrouter organization', 'multi-user openrouter', 'openrouter rbac'.
machine-learning-ops-ml-pipeline
sickn33
Design and implement a complete ML pipeline for: $ARGUMENTS
uv
mitsuhiko
Use `uv` instead of pip/python/venv. Run scripts with `uv run script.py`, add deps with `uv add`, use inline script metadata for standalone scripts.
vastai-core-workflow-b
jeremylongshore
Execute Vast.ai secondary workflow: Core Workflow B. Use when implementing secondary use case, or complementing primary workflow. Trigger with phrases like "vastai secondary workflow", "secondary task with vastai".