Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

agent-manager-skill — Claude Code skill: what it does, how to install

A procedure for driving several local CLI agents in tmux sessions: start, stop, tail logs, hand out tasks. Useful when work runs in parallel.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add sickn33/agentic-awesome-skills --skill agent-manager-skill -a claude-code
Open on GitHub

What agent-manager-skill does

Install it and your agent gets written steps for running several local CLI agents at once in separate tmux sessions. Start one, stop another, follow a log, assign a task. Handy when parallel work means you need to see each session instead of guessing from one shared output.

The steps call the manager runtime's CLI: doctor, list, start <id>, monitor <id> --follow, and assign fed through a heredoc. You need tmux and python3, with agents configured under an agents/ directory. No cron job or scheduler ships with it, so repeated plans are prepared only when scheduling is asked for explicitly.

The runtime itself is not part of the skill. The upstream repository address was unreachable, and the script path in the examples, agent-manager/scripts/main.py, does not match the clone directory. Find the real path and read its help first. The skill is flagged critical: it wants authorization for each task and target, so list configured agents and live sessions before starting anything, leave unrelated sessions alone, and redact logs before sharing. A live session does not prove the task finished — check the result.

What it helps with

  • run several CLI agents in parallel tmux sessions
  • tail an agent's log while it works
  • hand a task to an agent with assign
  • stop one agent without touching the others
  • list configured agents before starting anything

Example prompts for the agent

  • Start three agents in separate tmux sessions and show me their logs.
  • Run `python3 agent-manager/scripts/main.py list` and tell me which agents are configured under `agents/`.
  • Assign the workflow from `teams/fractalmind-ai-maintenance.md` to the second agent and watch the output.

How to install agent-manager-skill

1Skills CLI (Vercel)

npx skills add sickn33/agentic-awesome-skills --skill agent-manager-skill -a claude-code

2Manually: put the files in place

~/.claude/skills/agent-manager-skill/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/agent-manager-skill/

From the same set80

The whole set →
docker-expert sickn33 A skill that turns your AI agent into a Docker reviewer for Dockerfiles, multi-stage builds and container security. Useful when images and Compose files need a second look. Claude Code CX Codex Cursor +1 27,200installs typescript-expert sickn33 A skill for TypeScript and JavaScript work: it reads your project setup, fixes type errors and speeds up type checking. Useful once a TS codebase gets big. Claude Code CX Codex Cursor +1 12,600installs browser-automation sickn33 This skill builds browser checks around observed UI state and explicit outcomes. Use it for UI workflows, timing failures, or authorised page-data collection. Claude Code CX Codex Cursor +1 6,700installs nextjs-supabase-auth sickn33 This skill wires Supabase Auth into the Next.js App Router with clients, middleware, OAuth callbacks, and Server Actions. Use it when you need protected routes and session handling. Claude Code CX Codex Cursor +1 6,500installs 3d-web-experience sickn33 Helps build and debug web 3D scenes, product configurators, and portfolios. Covers stack choice, model loading, scroll interaction, and performance checks. Claude Code CX Codex Cursor +1 5,200installs prisma-expert sickn33 This skill helps inspect Prisma schemas, migrations, and queries. Use it to investigate an error or review database changes before deployment. Claude Code CX Codex Cursor +1 4,200installs playwright-skill sickn33 Write and run Playwright browser tests directly in Claude Code: responsive design checks, login flows, form submissions, screenshots. Executes locally via Node with a visible browser window. Claude Code CX Codex Cursor +1 3,900installs game-development sickn33 Guides game architecture decisions, platform choices, and core loop structure. Directs the assistant to specialized sub-skills for web, mobile, PC, or VR. Claude Code CX Codex Cursor +1 3,800installs

Similar

router gamedev-skills Dispatches game development tasks to specialized skills by detecting the project engine and classifying gameplay or shipping workflows. Claude Code CX Codex Cursor +1 6,400installs solid vercel-labs Skill to render JSON-specs into reactive SolidJS components. Use it when building UI catalogs, wiring providers, or debugging Solid reactivity patterns. Claude Code CX Codex Cursor +1 1,100installs redux vercel-labs A Redux adapter for json-render: it points the renderer at a store slice instead of its own state. Useful when app state already lives in Redux. Claude Code CX Codex Cursor +1 1,100installs remember Yeachan-Heo A skill to decide where discovered knowledge belongs: project memory for durable facts, notepad for short-lived context, docs for instructions. Keeps findings from getting lost in chat. Claude Code CX Codex Cursor +1 617installs mantis-meta-agent official google A campaign supervisor for Mantis security review: it keeps the loop running pass after pass and holds state and snapshots. Built for reviews that run long unattended. Claude Code CX Codex Cursor +1 1,500installs mantis-reflect official google Extracts insights, failures, and false assumptions from Mantis agent transcripts, appending them to workspace/learnings.jsonl. Claude Code CX Codex Cursor +1 1,500installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. Claude Code 1,052,851installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. Claude Code 711,230installs

Questions about agent-manager-skill

How do I install agent-manager-skill in Claude Code?

Run npx skills add sickn33/agentic-awesome-skills --skill agent-manager-skill -a claude-code. The skill file lands at ~/.claude/skills/agent-manager-skill/SKILL.md.

What does agent-manager-skill do?

It tells the agent how to manage local CLI agents through tmux: start, stop, monitor logs, assign tasks, and stay inside an explicitly authorized workspace.

What do I need for it to work?

tmux and python3, plus agents configured in an agents/ directory. The manager runtime is separate, and the example script path differs from the clone directory, so check the help of whatever file is actually installed.

Source text

SKILL.md · MIT 
---
name: agent-manager-skill
description: "Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) in an explicitly authorized workspace."
risk: critical
source: community
date_added: "2026-02-27"
---

# 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
- prepare a scoped plan for repeated agent work only when scheduling is explicitly requested

## Prerequisites

This AAS entrypoint does not bundle the manager runtime. The historical upstream URL was unavailable during this review; do not execute its examples until an actual reviewed installation and CLI help confirm them. The original install option is retained as attribution, not an automatic setup step:

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

## Historical Upstream Command Shapes

The clone directory above differs from the `agent-manager/` path below. Resolve the actual installed script path rather than assuming these examples work from the current directory. Employee IDs and team files are examples and must be replaced with verified workspace configuration.

```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
```

## Bounded Operation

List the actual configured agents and existing tmux sessions first. Starting, assigning or stopping an agent requires authorization for that task and target. Preserve unrelated sessions, record the specific session/PID and inspected command, and redact logs before sharing. A session being alive does not prove its task completed; verify the requested result. No cron installer or automatic scheduler is bundled, so this guide does not claim cron support.

## 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.

© sickn33 · MIT · sickn33/agentic-awesome-skills

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor