Docs

How TokenFlexing works

Three things make up the system: a local scanner (the CLI), a cloud sync API, and a public dashboard + leaderboard. None of them read your prompts or completions — only the usage blocks the AI tools themselves write to disk.

1. Scan

The CLI reads JSONL / SQLite session logs from Claude Code, Codex, Cursor, OpenCode, and 20+ other tools. Token counts and dollar costs are computed locally.

2. Sync

One-time browser login pairs the device. Snapshots are pushed to your tokenflex.ing profile keyed by (user, source) so multiple machines roll up cleanly.

3. Share

Public profile at /u/<handle>, optional leaderboard appearance, shareable ASCII flex cards. Privacy toggle: public / aggregate-only / private.

Deeper references

Full README ↗ — repo overview, architecture, env setup.
CLI README ↗ — every command, flag, and integration point.
npm package ↗

Deep API docs (REST + MCP) ship with the v2 leaderboard release. Until then the READMEs above are the source of truth.