In-browser real LLM token counter and cost estimation
Local tokenizer execution beats sending text to external counters.

Reads Copilot's internal session files for real token counts, not estimates.
VS Code users with GitHub Copilot subscriptions
Local tokenizer execution beats sending text to external counters.
Claude Code usage dashboard reading local files—fills exact gap Anthropic didn't address.
Like top for AI agents: tracks token costs across 6 coding agents, 100% offline.
Real-time cost tracking for Claude Code sessions; saves money intuition before you ship.
Cross-session visibility Claude Code should have built in.
Debugger for Claude Code session costs—step-by-step breakdown of tokens and tool calls.