ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified productivity Safety 3/5

agent-hq

Deploy the Agent HQ mission-control stack (Express + React + Telegram notifier / Jarvis summary) so other Clawdbot teams can spin up the same board, high-priority watcher, and alert automation. Includes setup, telemetry, and automation hooks.

Why use this skill?

Deploy the Agent HQ stack to manage tasks, automate Jarvis summaries, and sync mission-critical alerts via Telegram for your OpenClaw teams.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/thibautrey/agent-hq
Or

What This Skill Does

Agent HQ is a robust mission-control stack designed for OpenClaw teams to manage projects, track tasks, and automate communication. It provides a full-stack solution featuring an Express backend, a Vite/React frontend, and an integrated SQLite database. Beyond project management, the skill functions as an automation engine for your team, handling Jarvis-style summaries and high-priority Telegram notifications. It serves as a central hub for mission status, allowing users to organize agents, cards, and mission objectives while ensuring that critical alerts reach team members via external messaging services.

Installation

To deploy Agent HQ, ensure you have Node.js installed in your environment. First, clone the source repository from openclaw/skills and run npm install in both the root directory and the frontend-react folder to resolve all dependencies. Configuration is handled via config/telegram.json or environment variables; you must provide a valid botToken and chatId to enable the notification suite. Once configured, build the frontend using npm --prefix frontend-react run build and launch the application with npm run start:agent-hq. The UI will be accessible on the default port 4000, while API endpoints are exposed under the /api route. For production use, configure the included shell scripts as cron jobs to automate heartbeat monitoring and Telegram reporting.

Use Cases

Agent HQ is ideal for autonomous teams requiring persistent state management and proactive notification systems. It is effectively used for tracking project lifecycle stages, managing high-priority task queues that require immediate developer attention, and generating periodic progress reports via Jarvis-connector scripts. It is the perfect tool for teams that need a self-hosted 'mission control' that doesn't rely on third-party SaaS project management tools, ensuring all team data remains strictly within your own infrastructure.

Example Prompts

  1. "OpenClaw, please install the Agent HQ mission-control stack using the clawhub installer."
  2. "Jarvis, run the summary script and post the latest mission updates to the team Telegram channel."
  3. "Create a quick card with the text 'Security audit for database' and assign it to the high-priority queue."

Tips & Limitations

For optimal performance, seed your project data by populating data/board.json before starting the service for the first time. The SQLite integration uses a high_priority_jobs table specifically to prevent notification fatigue by suppressing duplicate alerts. Always secure your API by setting an AGENT_HQ_API_TOKEN to prevent unauthorized modification of your board. Note that while this tool is excellent for local mission control, it requires manual maintenance of cron jobs for full automation features, and it is strictly limited to the data structures defined in the SQLite schema.

Metadata

Stars946
Views0
Updated2026-02-13
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-thibautrey-agent-hq": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#automation#management#telegram#dashboard#workflow
Safety Score: 3/5

Flags: network-access, file-write, file-read, external-api, code-execution