Orsik
@orsikSince Oct 5, 2026: 277M tokens, 194 h, 317 sessions, $4,267 at API prices (est.)
Every synced day
Agents
74%Claude Code, 29 h, 45.8M tokens
26%Codex, 10 h, 13.6M tokens
Details
11.9MInput tokens
11.1MOutput tokens
36.3MCache writes
2.39BCache reads, not in the headline
46 hAgent time, parallel sessions each count
9Most sessions at once
339Prompts
7 daysLongest streak
Automated runs, not in hours: 5 sessions, 7 min of their own wall-clock time, 0 min of it outside your interactive sessions. These are claude -p, Agent SDK and codex exec runs.
| Model | Tokens | Share | At API prices (est.) |
|---|---|---|---|
| claude-opus-5-5 | 25.7M | 43% | $457 |
| claude-sonnet-5-5 | 12.7M | 21% | $136 |
| gpt-6.1-sol | 12.7M | 21% | $159 |
| claude-haiku-5-5 | 6.9M | 12% | $3.11 |
| gpt-6-astra | 763K | 1% | $21 |
| claude-fable-5-1 | 443K | 1% | $12 |
| gpt-6.1-terra | 150K | <1% | $0.27 |
Make your own
One command. It reads your coding agent logs on your computer and makes this card.
$ npx codewrapped