I added real-time activity logging and security scoring to my Claude Code dashboard

A developer built a real-time activity logging and security scoring dashboard for Claude Code that tracks every file read, command executed, and API call with risk labels and timestamps. The tool, available as an npm package called claude-token-dashboard, assigns a security score out of 100 by checking seven risk factors such as unrestricted sudo or curl commands and unprotected .env files. The developer scored 90/100 on their own environment and released the project on GitHub as an observability layer for AI agents.

Knowing how much you spent is useful. But it's not enough. The real question is: what is your AI actually doing? Which files did it read? Which commands did it run? Is your environment even safe to run it in? I couldn't answer any of those. So I built the answers in. Claude Code logs everything via hooks. Every file read. Every command executed. Every API call. Risk-labeled. Timestamped. Live. Set it up once in ~/.claude/settings.json : { "hooks": { "PostToolUse": { "matcher": ". ", "hooks": { "type": "command", "command": "curl -sf -X POST http://localhost:3000/api/actions -H 'Content-Type: application/json' --data-binary @- 2 /dev/null || true" } } } } Then open http://localhost:3000/activity . Watch your AI's actions stream in real-time. This is the audit layer AI agents have been missing. Scored out of 100. Checks 7 things: Bash sudo in your allow list? -20 ~/.ssh/ in your deny list? -20 Bash curl unrestricted? -15 .env files protected? -15 strictMode enabled? -10 Bash rm restricted? -10 I scored 90/100. What's yours? The point isn't to shame anyone. It's to make the invisible visible — so you can make informed decisions about what your AI is allowed to do. npm install -g @notenkidev/claude-token-dashboard claude-token-dashboard Open http://localhost:3000 GitHub: https://github.com/notenkitoclient-cpu/claude-token-dashboard https://github.com/notenkitoclient-cpu/claude-token-dashboard This started as a simple token counter. It's becoming something bigger — an observability layer for AI agents. More coming.