Openclaw Control Center

Overview: System health, pending items, risk signals, and operational summary
Usage: Daily/7d/30d token spend, quota, context pressure, subscription window
Staff: Who is actively executing vs. queued — not just "has tasks"
Collaboration: Parent-child session handoffs and verified cross-session messages (e.g. Main ⇄ Pandas )
Tasks: Task board, approvals, execution chains, run evidence
Memory: Per-agent memory health, searchability, and source file editing
Documents: Shared and agent-core documents opened from actual source files
Settings: Connector wiring status, security risk summary, update status

This is a local dashboard for OpenClaw agents that gives you visibility into what they're doing and how much they're spending. You get token attribution across tasks, cross-session collaboration tracing (like tracking handoffs between Main and Pandas agents), memory health per agent, and a read-only-first security model where mutations are off by default. It's TypeScript with a web UI, runs on localhost:4310, and explicitly constrains you to only touch files inside the control-center directory. The install is straightforward npm commands. Honestly most useful if you're running multiple OpenClaw agents and need to understand where your tokens are going or trace task execution chains without ssh-ing into config files.

skills.sh installs: 4.3K
GitHub stars: 61
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add aradotso/trending-skills --skill openclaw-control-center --agent claude-code

Installs into .claude/skills of the current project.

Files