Openclaw Control Center
Run a local-first dashboard to watch OpenClaw agent health, token spend, tasks, collaboration handoffs, and memory without enabling risky writes by default.
Overview
OpenClaw Control Center is an agent skill most often used in Operate (also Build agent-tooling) that provides a local-first, security-first dashboard for OpenClaw visibility, token attribution, collaboration tracing, and
Install
npx skills add https://github.com/aradotso/trending-skills --skill openclaw-control-centerWhat is this skill?
- Readonly-by-default security posture with explicit opt-in for mutations
- Token attribution with daily, 7-day, and 30-day usage views plus quota pressure
- Collaboration tracing for parent-child sessions and verified cross-session messages
- Task board with approvals, execution chains, and run evidence
- Memory and document panels tied to actual source files for searchability and editing
Adoption & trust: 4.1k installs on skills.sh; 31 GitHub stars; 1/3 security scanners passed (skills.sh audits).
What problem does it solve?
You run OpenClaw agents but cannot see spend, handoffs, task approval state, or memory sources in one trustworthy local place.
Who is it for?
Solo builders operating OpenClaw locally who need spend attribution, session collaboration proof, and task/memory governance without a hosted black box.
Skip if: Teams that only need one-off prompts with no ongoing agent fleet, or builders who refuse any local filesystem access for agent observability tools.
When should I use this skill?
User asks for OpenClaw control center, dashboard, agent monitoring, token usage, collaboration tracing, task approval, memory management, or a local OpenClaw control panel.
What do I get? / Deliverables
You get a readonly-default control panel with auditable activity, usage breakdowns, and safe paths to approve tasks or edit memory and documents when you choose to enable writes.
- Configured local OpenClaw control center with overview, usage, tasks, and collaboration views
- Auditable visibility into token spend and cross-session message verification
- Optional gated write flows for approvals, memory edits, and document updates
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Primary shelf is production operations because the skill is built for ongoing visibility, approvals, and audit of live agent fleets. Monitoring is the canonical fit: health summaries, usage windows, staff activity, and risk signals are observability-first concerns.
Where it fits
After wiring OpenClaw staff roles, open the control center to confirm who is queued versus actively executing before you ship automations.
Before enabling write APIs, verify readonly defaults and review risk signals on the overview pane.
Check daily and 7-day token spend when context pressure spikes on a subscription window.
Edit per-agent memory source files from the memory panel after a bad collaboration trace surfaces bad state.
How it compares
Use as a local operations console for OpenClaw fleets, not as a generic MCP server or a one-shot codegen skill.
Common Questions / FAQ
Who is openclaw-control-center for?
It is for indie and solo builders running OpenClaw agents who want a security-first, local dashboard for monitoring, tokens, tasks, and collaboration instead of inferring state from chat logs alone.
When should I use openclaw-control-center?
Use it in Operate when you need health and risk signals; during Build when wiring agent-tooling you want visible in production; and whenever you must trace token spend, staff execution, or cross-session handoffs before approving automated work.
Is openclaw-control-center safe to install?
It is designed readonly-first with mutations disabled by default, but you should still review the Security Audits panel on this Prism page and confirm which write paths you enable locally.
SKILL.md
READMESKILL.md - Openclaw Control Center
# openclaw-control-center > Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection OpenClaw Control Center transforms OpenClaw from a black box into a local, auditable control center. It provides visibility into agent activity, token spend, task execution chains, cross-session collaboration, memory state, and document sources — with security-first defaults that keep all mutations off by default. ## What It Does - **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 ## Installation ```bash git clone https://github.com/TianyiDataScience/openclaw-control-center.git cd openclaw-control-center npm install cp .env.example .env npm run build npm test npm run smoke:ui npm run dev:ui ``` Open: - `http://127.0.0.1:4310/?section=overview&lang=zh` - `http://127.0.0.1:4310/?section=overview&lang=en` > Use `npm run dev:ui` over `UI_MODE=true npm run dev` — more stable, especially on Windows shells. ## Project Structure ``` openclaw-control-center/ ├── control-center/ # All modifications must stay within this directory │ ├── src/ │ │ ├── runtime/ # Core runtime, connectors, monitors │ │ └── ui/ # Frontend UI components │ ├── .env.example │ └── package.json ├── docs/ │ └── assets/ # Screenshots and documentation images ├── README.md └── README.en.md ``` > **Critical constraint**: Only modify files inside `control-center/`. Never modify `~/.openclaw/openclaw.json`. ## Environment Configuration Copy `.env.example` to `.env` and configure: ```env # Security defaults — do NOT change without understanding implications READONLY_MODE=true LOCAL_TOKEN_AUTH_REQUIRED=true IMPORT_MUTATION_ENABLED=false IMPORT_MUTATION_DRY_RUN=false APPROVAL_ACTIONS_ENABLED=false APPROVAL_ACTIONS_DRY_RUN=true # Connection OPENCLAW_GATEWAY_URL=http://127.0.0.1:PORT OPENCLAW_HOME=~/.openclaw # UI PORT=4310 DEFAULT_LANG=zh ``` ### Security Flag Meanings | Flag | Default | Effect | |------|---------|--------| | `READONLY_MODE` | `true` | All state-changing endpoints disabled | | `LOCAL_TOKEN_AUTH_REQUIRED` | `true` | Import/export and write APIs require local token | | `IMPORT_MUTATION_ENABLED` | `false` | Import mutations blocked entirely | | `IMPORT_MUTATION_DRY_RUN` | `false` | Dry-run mode for imports when enabled | | `APPROVAL_ACTIONS_ENABLED` | `false` | Approval actions hard-disabled | | `APPROVAL_ACTIONS_DRY_RUN` | `true` | Approval actions run as dry-run when enabled | ## Key Commands ```bash # Development npm run dev:ui # Start UI server (recommended) npm run dev # One-shot monitor run, no HTTP UI # Build & Test npm run build # TypeScript compile npm test # Run test suite npm run smoke:ui # Smoke test the UI endpoints # Lint npm run lint # ESLint check npm run lint:fix # Auto-fix lint issues ``` ## TypeScript Code Examples ### Connecting to the Runtime