LaunchKit · 2026
Back to Skills

jarvis-mission-control

Set up JARVIS Mission Control — a free, open-source coordination hub where AI agents and humans work as a real team.

4
1.0k downloads
by @asif2bd

Setup & Installation

openclaw skills install @asif2bd/jarvis-mission-control

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install jarvis-mission-control

Version History

v2.0.7Mar 14, 2026 - Version note by skill developer:

Added security attestations to YAML frontmatter (verified, auditor, audit_date, instruction_only, no_code_execution, source_code). Matches token-optimizer pattern for ClawHub moderation clearance.

What This Skill Does

JARVIS Mission Control is a self-hosted dashboard for coordinating AI agents and humans on shared work. It provides a 5-column Kanban board, real-time team chat, Claude Code session tracking, GitHub Issues sync, and scheduled job visibility. All state is stored as Git-versioned JSON files with no external database or cloud account required.

Unlike cloud-based project management tools, all coordination state is stored as Git-versioned JSON files on disk, so task history is portable, auditable, and survives restarts without external dependencies.

When to use it

  • Tracking tasks across multiple AI agents working on a shared project
  • Monitoring Claude Code session token usage and cost per agent
  • Automatically syncing open GitHub Issues into team Kanban cards
  • Reviewing agent-generated reports from a browser without SSH access
  • Running OpenClaw CLI commands directly from the browser dashboard

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: Set up a shared task board for my team of AI agents

AGENT
  1. 1Fork and clone the JARVIS Mission Control repo from GitHub
  2. 2Run ./scripts/init-mission-control.sh to initialize the .mission-control data directory
  3. 3Start the server with cd server && npm install && npm start
  4. 4Open http://localhost:3000 — running agents are auto-discovered within 30 seconds
  5. 5Create tasks via the Kanban board or mc task:create from any agent terminal
OUTPUT

A live dashboard with all agents visible, task cards organized across INBOX, ASSIGNED, IN PROGRESS, REVIEW, and DONE columns, with real-time WebSocket sync across all connected clients