rulebisect
Investigate reproducible Codex repository-instruction failures and check proposed instruction changes with RuleBisect. Use for AGENTS.md failure reduction, cross-task instruction regressions, experiment setup, or saved RuleBisect evidence; ordinary code debugging without an instruction experiment does not need this skill.
Pinned to revision 04c24b935448, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/rulebisect/SKILL.md
- skills/rulebisect/LICENSE
- skills/rulebisect/agents/openai.yaml
- skills/rulebisect/references/assertions.md
- skills/rulebisect/references/evidence.md
- skills/rulebisect/references/experiments.md
- skills/rulebisect/scripts/rulebisect_cli.py
- skills/rulebisect/scripts/runtime/LICENSE
- skills/rulebisect/scripts/runtime/rulebisect/__init__.py
- skills/rulebisect/scripts/runtime/rulebisect/__main__.py
- skills/rulebisect/scripts/runtime/rulebisect/assertions.py
- skills/rulebisect/scripts/runtime/rulebisect/checks.py
- skills/rulebisect/scripts/runtime/rulebisect/cli.py
- skills/rulebisect/scripts/runtime/rulebisect/comparison.py
- skills/rulebisect/scripts/runtime/rulebisect/core.py
- skills/rulebisect/scripts/runtime/rulebisect/demo.py
- skills/rulebisect/scripts/runtime/rulebisect/experiment.py
- skills/rulebisect/scripts/runtime/rulebisect/history.py
- skills/rulebisect/scripts/runtime/rulebisect/onboarding.py
- skills/rulebisect/scripts/runtime/rulebisect/report.py
- skills/rulebisect/scripts/runtime/rulebisect/report_ui.py
- skills/rulebisect/scripts/runtime/rulebisect/runner.py
- skills/rulebisect/scripts/runtime/rulebisect/setup.py
- skills/rulebisect/scripts/runtime/rulebisect/share.py
- skills/rulebisect/scripts/runtime/rulebisect/suite.py
- skills/rulebisect/scripts/runtime/rulebisect/ui.py
Every link opens the file at its source, pinned to the revision this page describes.