Skip to main content
affpapa.org
RU EN
skill CX Codex

openclaw-control-center — Claude Code skill: install and use

A local control panel for OpenClaw agents, covering tasks, token usage, session handoffs, memory, and documents. It keeps write actions restricted by default.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add reason-machines/trending-skills --skill openclaw-control-center -a claude-code
Open on GitHub

What openclaw-control-center does

This skill covers a local OpenClaw control center for inspecting agent activity. Its views include system status, pending work, active staff, task execution chains, parent-child handoffs, and verified messages between sessions. It also tracks token spend, quota windows, context pressure, agent memory, source documents, and connector status.

The project uses TypeScript runtime connectors and a UI, with commands for building, testing, linting, and checking the UI endpoints. Settings live in .env; the gateway address comes from OPENCLAW_GATEWAY_URL, while local token authentication is enabled by default. Running the application requires npm install, a build, and npm run dev:ui.

Keep project changes inside control-center/. The file ~/.openclaw/openclaw.json must not be edited. Readonly mode blocks state-changing endpoints, and approval actions stay disabled unless the security settings are changed.

What it helps with

  • inspect the current OpenClaw agent roster
  • attribute token use to individual tasks
  • trace handoffs across sessions
  • review task runs and approval state
  • open agent memory and source documents

Example prompts for the agent

  • Show the OpenClaw system overview and active agents.
  • Break down token usage by task and report context pressure.
  • Trace the handoff from a parent session to its child session.

How to install openclaw-control-center

1Skills CLI (Vercel)

npx skills add reason-machines/trending-skills --skill openclaw-control-center -a claude-code

2Manually: put the files in place

~/.claude/skills/openclaw-control-center/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/openclaw-control-center/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about openclaw-control-center

How do I install openclaw-control-center in Claude Code?

Run npx skills add reason-machines/trending-skills --skill openclaw-control-center -a claude-code, then check ~/.claude/skills/openclaw-control-center/SKILL.md.

What does openclaw-control-center do?

It describes a local OpenClaw dashboard for inspecting agents, tasks, token spending, session collaboration, memory, and documents. State-changing operations are restricted by the default security settings.

Which platforms support this skill?

The skill supports Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode.

Similar skills

All skills for Agent setup: memory, context, orchestration →
setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. 1,052,851installs ask-matt Matt Pocock Routes you to the right Matt Pocock skill or flow for the task at hand. Use it when you need a starting point for a feature, prototype, incoming issue, or hard bug. 766,587installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. 711,230installs writing-plans Jesse Vincent This skill turns requirements for a multi-step task into an implementation plan before code changes begin. It helps when another engineer needs exact files, interfaces, and checks. CX Codex 282,859installs caveman-review JuliusBrussee Turns code review comments into one line per finding: location, problem, fix. Useful when a diff or PR needs a fast pass without the filler. CX Codex +1 411,800installs caveman-compress JuliusBrussee Compresses CLAUDE.md, todo lists, and other prose files into a shorter format while retaining a readable backup. CX Codex +1 411,500installs

From the same set139

inkos-multi-agent-novel-writing Coordinates a multi-agent CLI pipeline to draft, validate, and audit novel chapters. Useful for managing long-form fiction projects with strict continuity. CX Codex +1 2,800installs claude-hud-statusline Keeps a status line under your prompt showing how full the context window is, which tools and subagents are running, and how far the todo list has got. CX Codex +1 2,700installs understand-anything-knowledge-graph Runs a multi-agent pass over your project, builds a graph of files, functions and dependencies, then opens an interactive dashboard for exploring it. CX Codex +1 2,400installs agent-browser-automation This skill gives AI agents a headless browser through a Rust CLI and Chrome DevTools Protocol. Use it for pages, forms, snapshots, and screenshots. CX Codex +1 2,100installs agency-agents-ai-specialists Swap in a specialist persona — frontend, backend, reviewer, UX — and let it carry the task with its own workflow. CX Codex +1 2,100installs daily-stock-analysis Automates stock analysis across US, Hong Kong, and Chinese markets using LLMs. It calculates entry targets, stop-losses, and delivers reports via chat webhooks. CX Codex +1 2,000installs ui-ux-pro-max-skill Describe a product to get a proposed page structure, visual style, palette, and font pairing. Use it to shape interface decisions before implementation. CX Codex +1 2,000installs everything-claude-code-harness The skill builds out an agent harness: subagents, slash commands, memory hooks and a security scan. Useful when every Claude session starts from a blank slate. CX Codex +1 1,800installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor