scripts/data.py removed; the detectors' standalone CLIs go (categories.py runs them).
Benchmark identical to the baseline.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- cancel reverts only the run's commits (base..HEAD), never the caller's edits
- validator diffs base..HEAD, not the working tree
- fix commits carry their Co-Authored-By line; no redundant end benchmark
- score.py: clear error on a missing labels file; docstring says end is not passed
- usage lines; README and CLAUDE.md for the generic workflow
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Skill and agents no longer name Diagnostic-app paths (analyses, labeling/auto,
demande.json, summary location, git rules of the working repository).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>