@zange· 2h
Marathon debugging on edgent
hawkes
DEEP WORK
123.9x your typical session
3.4M tokens vs typical 27.1K
3.4Mtokens
43prompts
7:36:44time
802lines
Claude Codeclaude-opus-5-5[1m]Python$132.27
mostly building
2h 19m session running commands and testing. 15.6M tokens across 56 prompts using claude-fable-5-1.
Tokens / prompt78.1k
Cost / line$0.165
Cache hit100%
Burn rate$17.38/hr
Derived from this session's token and cost data. Not shown on the feed.
Building 73%Verifying 22%Thinking 6%
Comments