Julius BrusseeandClaude Fable 5 d28be46e50 fix(#234): honest savings claim — ~50-65% measured output reduction, not ~75% ...

README headline now states the measured range with method (65% avg vs
verbose default from benchmarks/, ~50% median vs 'Answer concisely.'
control from evals/) plus explicit caveat: input tokens untouched,
session-level savings smaller. Stats box shows output vs input split,
drops the unmeasured ~3x speed row. Same ~75% claim corrected in
SKILL.md description (+ synced plugin copy and dist/caveman.skill),
plugin.json, marketplace.json, gemini-extension.json, caveman-init
rule frontmatter, skill README, and CLAUDE.md.

Note for maintainer: the GitHub repo description still says 'cuts 65%
of tokens' — should read 'cuts ~50-65% of output tokens (measured)'.
Not changeable from a local commit.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011kmm2umRGb5nLxdimrwweZ

2026-07-02 15:32:47 +02:00

..

caveman.skill

fix(#234): honest savings claim — ~50-65% measured output reduction, not ~75%

2026-07-02 15:32:47 +02:00