The board
opt-inEveryone who ran tokenchit publish, or a bare tokenchit generate, which ends by calling it. A usage count over the selected window, not a skill score.
Get your own card →filtersthis year · claude code
GitHub sign-in proves the handleself-reported, handle unprovedNeither audits the figures — see the notes below the table.
| rank | developer | agent mix | last 30d | tokens | equiv. cost | streak |
|---|---|---|---|---|---|---|
| 1– | — | 337B | $653,816 | 0d | ||
| 2– | 41.3B | $15,236 | 0d | |||
| 3– | 25.8B | $12,312 | 0d | |||
| 4– | 23.9B | $6,525 | 0d | |||
| 5▲3 | 16.8B | $3,130 | 0d | |||
| 6▼1 | — | 14.8B | $11,162 | 0d | ||
| 7▼1 | 14.3B | $8,070 | 30d | |||
| 8▼1 | — | 12.1B | $9,113 | 0d | ||
| 9▲1 | 10.5B | $4,912 | 0d | |||
| 10▼1 | 10.1B | $4,790 | 0d | |||
| 11– | — | 8.27B | $5,647 | 0d | ||
| 12– | 7.72B | $6,972 | 0d | |||
| 13– | — | 7.58B | $5,728 | 0d | ||
| 14– | 5.37B | $1,798 | 0d | |||
| 15– | 4.60B | $2,028 | 0d | |||
| 16– | 3.49B | $2,684 | 0d | |||
| 17– | 2.63B | $993 | 0d | |||
| 18– | 2.60B | $683 | 0d | |||
| 19– | — | 2.03B | $2,071 | 0d | ||
| 20– | — | 1.89B | $787 | 0d | ||
| 21– | 1.85B | $607 | 0d | |||
| 22– | — | 1.76B | $1,227 | 0d | ||
| 23– | 1.70B | $1,339 | 0d | |||
| 24– | — | 1.49B | $1,282 | 0d | ||
| 25– | 1.48B | $1,118 | 0d |
- claude-code
How this is ranked
Verified rows first, then tokens over the selected window. Signing in is the only thing that ties a row to a GitHub account, so it is the only thing that can carry a position — an unverified row still appears with its figures, it just cannot outrank a verified one. Every column covers the same window as the rank.
A cli badge means the numbers were self-reported without a GitHub sign-in; those rows stay on the board rather than being hidden, because a visible unverified row is more honest than a quietly filtered one. Streak is the current run of active days, which is not a windowed figure. Submissions far outside the range of real usage are held for review and do not appear until a person has looked. Figures are self-reported and bounded for plausibility, not audited.