Llm Monitoring Dashboard

If you're running LLM features in production and getting surprise API bills or wondering who's actually using the thing, this gives you the observability stack you probably should've built already. It uses Tokuin CLI to track tokens, costs, and latency across OpenAI, Anthropic, Gemini, and OpenRouter, stores everything in JSONL with user context, then generates either a full Next.js dashboard with per-user drilldowns or a single-file HTML version. The PM insights are genuinely useful: adoption rates, inactive user alerts, cost optimization recs, and weekly reports. It hashes prompts instead of storing raw text, which is the right call. Good for teams that need to justify LLM spend or figure out why their bill tripled last month.

Install to Claude Code

npx -y skills add supercent-io/skills-template --skill llm-monitoring-dashboard --agent claude-code