voice-baseline

An agent writing in your voice does not only sample the median of the internet. It samples the median of you, from the pieces and rules and memory files in its context, and it regresses toward your most frequent choices because those are the highest probability tokens in your corpus. A word that was a choice at one use comes back at five. Then the fifth use teaches the next draft, and the tic becomes the style.

Generic ban lists cannot catch this, because the words are yours and they are not on anyone's list. Measure instead.

Run it

python3 scripts/census.py PATH/TO/YOUR/WRITING --out voice-baseline.md
python3 scripts/census.py PATH/TO/YOUR/WRITING --check DRAFT.md