Julian lechnerandClaude Opus 5.5 89bee27dd2 feat(benchmarks): add setup versus baseline A/B runner ...

Run tasks with and without the installed setup and compare pass rate, rework,
duration, tokens, cost, tool calls, and workflow checks; exclude runs that end
with a client or API error.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

2026-10-01 12:45:41 +02:00

..

benchmarks

feat(benchmarks): add setup versus baseline A/B runner

2026-10-01 12:45:41 +02:00

checks

fix(validate): check flat Claude rule skills

2026-10-01 11:13:01 +02:00

commands

feat(benchmarks): add setup versus baseline A/B runner

2026-10-01 12:45:41 +02:00

lib

feat(install): lock destinations during sync

2026-10-01 12:45:39 +02:00

tests

feat(install): lock destinations during sync

2026-10-01 12:45:39 +02:00