OpenClaw Usage Dashboard

Interactive local dashboard for OpenClaw API usage. Shows token consumption, request counts, and system health across all configured LLM models — broken down...

This skill appears to do what it says: run a local Node server that reads ~/.openclaw/agents/*/sessions/*.jsonl and shows usage metrics on http://localhost:PORT. Before installing/running: (1) Inspect server.js yourself (it is bundled) to verify you are comfortable with the file I/O and the fixed system commands it runs; (2) Run it unprivileged (your normal user), not as root/admin; (3) Confirm the server binds only to localhost (SKILL.md and code default to 127.0.0.1) or explicitly pass --host 127.0.0.1; (4) If you are concerned about secrets in logs, either review a few session files manually or run the server in a sandbox to confirm no raw secrets are exposed; (5) Because the server uses execSync for system health commands, make sure your platform's commands are safe and that the machine is otherwise secure. If you need additional assurance, you can run node server.js in an isolated environment and monitor outbound network activity to confirm nothing leaves your machine.

Type: OpenClaw Skill Name: openclaw-usage-dashboard Version: 2.0.2 The bundle provides a local Node.js dashboard for monitoring OpenClaw token usage and system health by parsing session logs in the `~/.openclaw` directory. The implementation in `server.js` includes several security best practices, such as regex-based redaction of API keys (e.g., Anthropic and OpenAI tokens), a memory budget for log parsing, and a restrictive Content Security Policy (CSP) for the web interface. System information is gathered using hardcoded shell commands (e.g., `vm_stat`, `df`, `powershell`) without user-input interpolation, and the server is restricted to `localhost`. The included `AUDIT.md` further documents a self-correction process for minor security and functional issues, reinforcing the tool's legitimate purpose.