@michael-tiller· Jun 18
Marathon debugging on dirigible2D
dirigible2D
MARATHON
3424.9x your typical session
12.8M tokens vs typical 3.7K
12.8Mtokens
48prompts
4:00:16time
1,266lines
Claude Codeclaude-opus-4-8[1m]Markdown$225.24
mostly thinking
4h session running commands and testing. 12.8M tokens across 48 prompts using claude-opus-4-8[1m].
Tokens / prompt267.2k
Cost / line$0.178
Cache hit95%
Burn rate$56.25/hr
Derived from this session's token and cost data. Not shown on the feed.
Building 28%Verifying 0%Thinking 50%Delegating 22%
Comments