Agent Manager Skill
- 563 installs
- 29.9k repo stars
- Updated July 27, 2026
- davila7/claude-code-templates
agent-manager-skill is a Claude Code skill that orchestrates multiple local CLI agents in parallel tmux sessions for developers who need to start, assign, monitor, and schedule agent work from one control surface.
About
Agent Manager Skill is a Python CLI tool that lets you run, assign work to, and supervise multiple local agents simultaneously. Each agent runs inside its own tmux session so they operate independently without interfering. You can start or stop agents, tail their logs in real time, run health checks, and hand them concrete tasks using simple commands. The skill is especially useful when you need parallel agent execution for research, maintenance, content generation, or monitoring workflows. It stores configuration under an agents/ directory and works with any CLI-based agent that can be launched from a script. Once installed via git clone, you gain a repeatable way to scale from one agent to many without losing visibility or control.
- Start, stop, list and monitor multiple local CLI agents in isolated tmux sessions
- Assign specific tasks to named agents with inline heredoc prompts
- Real-time log tailing and health checks via doctor and monitor commands
- Cron-friendly scheduling for recurring agent workloads
- Requires tmux and Python 3; stores agent configs in an agents/ directory
Agent Manager Skill by the numbers
- 563 all-time installs (skills.sh)
- +13 installs in the week ending Jun 23, 2026 (Skillselion tracking)
- Ranked #1,626 of 16,659 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: HIGH risk (skills.sh audit)
- Data as of Jul 28, 2026 (Skillselion catalog sync)
npx skills add https://github.com/davila7/claude-code-templates --skill agent-manager-skillAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 563 |
|---|---|
| repo stars | ★ 29.9k |
| Security audit | 2 / 3 scanners passed |
| Last updated | July 27, 2026 |
| Repository | davila7/claude-code-templates ↗ |
How do you run multiple CLI agents in parallel?
Orchestrate multiple local CLI agents running in parallel tmux sessions with task assignment and monitoring.
Who is it for?
Developers running several local CLI coding agents who need tmux-based parallelism with task assignment and log monitoring from Python scripts.
Skip if: Developers who only run one agent in a single terminal and do not need session orchestration or cron scheduling.
When should I use this skill?
Multiple local CLI agents must run in parallel tmux sessions with start/stop control, task assignment, log monitoring, or cron-friendly scheduling.
What you get
Running tmux agent sessions, assigned task queues, tailed agent logs, and optional cron schedules.
- running agent tmux sessions
- monitored agent logs
Files
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.gitCommon 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
EOFNotes
- Requires
tmuxandpython3. - Agents are configured under an
agents/directory (see the repo for examples).
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la462k185k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.379k15.8k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.378k92.5k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.375k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k8How it compares
Pick agent-manager-skill for local tmux-based multi-agent ops; use cloud agent platforms when sessions must run remotely with managed scaling.
FAQ
How do you install agent-manager-skill?
agent-manager-skill is installed by cloning the agent-manager-skill git repository into the workspace. After clone, run python3 agent-manager/scripts/main.py doctor to verify the environment before starting agents.
What does agent-manager-skill control?
agent-manager-skill controls multiple local CLI agents via tmux sessions: start and stop agents, list running sessions, assign tasks, monitor output logs, and configure cron-friendly recurring runs from Python entrypoints.
Is Agent Manager Skill safe to install?
skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.