Track opencode token usage
Counted through burnlog wrap. No adapter, no waiting for burnlog to add support for the model you switched to this morning.
Counting opencode in under a minute
- 01Run it under wrap$ burnlog wrap -- opencode
The proxy covers 14 providers at once, so a mid-session model switch stays counted.
- 02Sync and check your rank$ burnlog sync && burnlog status
sync uploads; status prints where you landed on the board.
Why the proxy beats an adapter here
A log-reading adapter has to be written per tool, and it breaks whenever that tool changes its format. The wire does not change: providers keep reporting usage in the same field because their own billing depends on it.
So burnlog reads logs where a stable format exists — Claude Code, Codex, Hermes — and reads the wire for everything else. New agent, new model, new provider endpoint: still counted, still without a release.
Or skip both
Anything that writes to ~/.burnlog/events/*.jsonl is picked up on the next sync, in any language, without waiting for a burnlog release. That open sink is how a tool burnlog has never heard of still lands on the board.
That is a documented file format, not an internal detail: append a line, run burnlog sync, and it's on the board.
What burnlog can't see
Put opencode on the board
One command. It scans, shows you your numbers, and only then asks for an account.