@michael-tiller· 3h
One-shot session on dirigible2D
Dirigible
FULL SEND
977.1x your typical session
3.5M tokens vs typical 3.5K
3.5Mtokens
14prompts
4:03:06time
644lines
Claude Codeclaude-fable-5Markdown$94.55
mostly delegating
3m coding session using gpt-5.6-luna. 145K tokens across 1 prompts.
Tokens / prompt247.0k
Cost / line$0.147
Cache hit93%
Burn rate$23.34/hr
Derived from this session's token and cost data. Not shown on the feed.
Building 8%Thinking 9%Delegating 83%
Comments