Mission Control

macOS-native web dashboard for monitoring and controlling your OpenClaw agent. Live chat, cron management, task workshop, scout engine, cost tracking, and more.

Security Scan

The dashboard's instructions ask the agent to read local OpenClaw credentials and to clone/run remote code, but the skill metadata does not declare those config accesses or required secrets and there are other inconsistencies (macOS vs systemd, undeclared Brave Search key).

Purpose & Capability

The stated purpose (macOS-native dashboard) reasonably explains needing node/npm and connecting to an OpenClaw gateway, but the SKILL.md also references running a systemd service (Linux) which contradicts the macOS claim. The repo clone/run workflow is plausible for a dashboard, but some capabilities (auto-detecting gateway token, reading IDENTITY.md) are not declared in metadata.

Instruction Scope

Runtime instructions explicitly tell the agent/operator to clone a GitHub repo and run its server, and say the app auto-detects and reads sensitive local files (~/.openclaw/openclaw.json and IDENTITY.md) to obtain a gateway token and agent identity. Those file accesses and the handling of gateway tokens are not declared in requires.config and represent scope creep relative to the registry metadata.

Install Mechanism

There is no formal install spec (instruction-only), which limits packaged risk. However, the SKILL.md instructs cloning and executing code from a third‑party GitHub repo (node server.js), which is expected for this type of tool but still means remote code will run on the host — review the repository before executing.

Credentials

The SKILL.md mentions needing a Brave Search API key (for Scout) and accessing the OpenClaw gateway token file, yet the registry metadata lists no required environment variables or config paths. Requesting (or auto-reading) gateway credentials is sensitive and should be explicitly declared; the current mismatch is disproportionate and unexpected.

Persistence & Privilege

The skill is not marked always:true and is user-invocable only. It does not request permanent platform presence or claim to modify other skills; autonomy defaults are unchanged.

What to consider before installing

This skill will clone and run a third‑party web dashboard and (per its instructions) auto-detect and read your OpenClaw gateway token (~/.openclaw/openclaw.json) and IDENTITY.md. The registry metadata does not declare these file/credential accesses, and the README inconsistently mentions macOS and systemd. Before installing: (1) review the GitHub repo code to confirm how it uses and stores your gateway token and any API keys; (2) avoid running it with your real gateway token until you’ve audited it (use a test agent or sandboxed environment); (3) be cautious about supplying Brave Search or AWS credentials — add them only if you understand where they will be sent; (4) prefer running in an isolated VM/container and check mc-config.json for external endpoints and credential storage locations. If you want me to, I can enumerate the exact places in the repo to inspect (startup/server code, config parsing, outbound network calls) — but you must provide the repo contents or a link for review.

Mission Control — Dashboard for OpenClaw

A sleek, macOS-native-feel web dashboard for your OpenClaw agent. Monitor sessions, manage cron jobs, chat in real-time, delegate tasks to sub-agents, discover opportunities, and track costs — all from one beautiful interface.

Quick Install

# Clone the repo into your workspace
cd "$CLAWD_WORKSPACE" 2>/dev/null || cd ~/clawd
git clone https://github.com/Jzineldin/mission-control.git
cd mission-control

# Install dependencies + build frontend
npm install
cd frontend && npm install && npm run build && cd ..

# Create your config
cp mc-config.default.json mc-config.json

# Start (dev)
node server.js

# Or use systemd for production:
sudo cp mission-control.service /etc/systemd/system/
# Edit paths in the service file, then:
sudo systemctl enable --now mission-control

Visit http://localhost:3333 — the Setup Wizard auto-detects your OpenClaw config.

What You Get

Page	Description
Dashboard	Agent status, quick actions (email/calendar/heartbeat), activity feed, channels
Conversations	Browse all sessions, view history, continue conversations
Workshop	Kanban task board — queue tasks, sub-agents research, you review reports
Cost Tracker	Token usage per model, daily charts, budget alerts
Cron Monitor	Toggle, run, create, delete scheduled jobs visually
Scout	Auto-discover opportunities — gigs, skills, grants, bounties, news
Agent Hub	All agents/sessions with token counts and management
Settings	Model routing (main/sub-agent/heartbeat), config export/import
Skills	Browse installed + available skills
AWS	(Optional) Real costs, Bedrock models, image generation

Requirements

• OpenClaw running with gateway HTTP enabled
• Node.js 18+
• Brave Search API key (for Scout — free tier)

Configuration

Auto-detected from your OpenClaw setup:

• Gateway token from ~/.openclaw/openclaw.json
• Agent name from IDENTITY.md
• Model + channels from OpenClaw config

Fine-tune via mc-config.json or the in-app Settings page.

Links

• GitHub: https://github.com/Jzineldin/mission-control
• Support: https://ko-fi.com/kevinelzarka
• License: BSL 1.1 (converts to MIT 2030)