@albertolive· 4d
Debugged radar
radar
DEEP WORK
83.2x your typical session
10.6M tokens vs typical 127.4K
10.6Mtokens
37prompts
23:38:56time
1,159lines
Claude Codeclaude-opus-4-8Python$300.41
mostly building
23h 38m session running commands and testing. 10.6M tokens across 37 prompts using claude-opus-4-8.
Reconstructed from session history
Tokens / prompt286.6k
Cost / line$0.259
Cache hit98%
Burn rate$12.70/hr
Derived from this session's token and cost data. Not shown on the feed.
Building 81%Verifying 4%Thinking 1%Delegating 14%