Cleaned and decoded critical apparatus data for Greek texts — 4.2M tokens

Cleaned and decoded critical apparatus data for Greek texts

walking-corpus

DEEP WORK

First session on walking-corpus

First build tracked for this project

4.2Mtokens

33prompts

134:58:52time

2,146lines

Claude Codeclaude-opus-4-8Python$169.20

mostly building

Extracted and decoded apparatus variant data, converting legacy encoding to clean Unicode and resolving manuscript witnesses.

Tokens / prompt128.7k

Cost / line$0.079

Cache hit99%

Burn rate$1.25/hr

Derived from this session's token and cost data. Not shown on the feed.

Building 84%Verifying 4%Thinking 1%Delegating 11%