Track AI coding-agent token usage with TokenTracker
Use TokenTracker to auto-collect local token, cost, and rate-limit telemetry across Claude Code, Codex, Cursor, Gemini, OpenCode, OpenClaw, and other AI coding tools.
npx skills add agentskillexchange/skills --skill track-ai-coding-agent-token-usage-with-tokentracker
Use TokenTracker when an operator needs local-first visibility into token usage, cost trends, model breakdowns, rate-limit windows, and tool-specific activity across many AI coding agents. Invoke it instead of manually checking each coding tool or provider bill when the workflow requires one dashboard plus machine-readable status for Claude Code, Codex, Cursor, Gemini, OpenCode, OpenClaw, Copilot, Goose, Zed Agent, and related tools. The scope boundary is token and cost telemetry for agent CLI/editor sessions through tokentracker, sync, status, and dashboard flows; it is not a generic analytics dashboard, billing SaaS, or model-pricing library.
What this skill actually does
Inputs and prerequisites: Node.js 20+, tokentracker-cli or native desktop app, local AI coding tools to monitor, optional sqlite3 for Cursor token reading.
Setup notes: Run npx tokentracker-cli for first-time setup, or install globally with npm i -g tokentracker-cli and run tokentracker, tokentracker sync, tokentracker status, or tokentracker doctor to collect and inspect local AI-tool usage.
Source and verification boundary: use https://www.tokentracker.cc as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.