codex-autoresearch
Run repeated, measured Git experiments toward a numeric target; keep improvements and revert failures. Use for autonomous optimization or managing an autoresearch run, not one-shot edits.
The English summary is being prepared. Showing the original description.
See how to installFiles included (39)
- SKILL.md2.5 KB
- .github/workflows/ci.yml1.0 KB
- .gitignore63 B
- agents/openai.yaml301 B
- CITATION.cff527 B
- CONTRIBUTING.md3.0 KB
- docs/EXAMPLES.md4.6 KB
- docs/GUIDE.md7.9 KB
- docs/i18n/README_DE.md3.9 KB
- docs/i18n/README_ES.md3.8 KB
- docs/i18n/README_FR.md4.0 KB
- docs/i18n/README_JA.md4.1 KB
- docs/i18n/README_KO.md3.9 KB
- docs/i18n/README_PT.md3.7 KB
- docs/i18n/README_RU.md5.7 KB
- docs/i18n/README_ZH.md3.6 KB
- docs/INSTALL.md2.1 KB
- image/autoresearch-report.png116.0 KB
- image/banner.png2.3 MB
- LICENSE1.0 KB
- README.md9.1 KB
- references/background.md2.2 KB
- references/workflow.md7.3 KB
- scripts/autoresearch_core.py46.1 KB
- scripts/autoresearch_report.py22.6 KB
- scripts/autoresearch.py56.4 KB
- scripts/run_contributor_gate.sh608 B
- scripts/run_skill_e2e.sh11.5 KB
- scripts/validate_skill_structure.sh198 B
- tests/e2e-fixtures/counter_reduction/.gitignore31 B
- tests/e2e-fixtures/counter_reduction/scripts/score.py97 B
- tests/e2e-fixtures/counter_reduction/src/value.txt2 B
- tests/e2e-fixtures/interactive_unittest_fix/.gitignore50 B
- tests/e2e-fixtures/interactive_unittest_fix/prompt.txt104 B
- tests/e2e-fixtures/interactive_unittest_fix/scripts/score.py373 B
- tests/e2e-fixtures/interactive_unittest_fix/src/math_utils.py49 B
- tests/e2e-fixtures/interactive_unittest_fix/tests/test_math_utils.py325 B
- tests/test_autoresearch.py38.8 KB
- tests/test_structure.py2.0 KB
SKILL.md (original)
Review the instructions the agent will receive before you install.
Codex Autoresearch
Improve a repository through repeated, reversible experiments:
hypothesize -> change -> measure -> learn -> keep or revert -> repeat
Codex chooses hypotheses and makes code changes. The control script owns measurement, commits, rollback, and the event history.
Respond To The Request
Resolve <control> to this skill's own scripts/autoresearch.py; do not assume it is installed in the target repository.
For a status or results request, run the corresponding command directly:
| Request | Command |
|---|---|
| Status | python3 <control> status --repo <repo> |
| History | python3 <control> history --repo <repo> |
| TSV export | python3 <control> history --repo <repo> --format tsv |
| HTML report | python3 <control> report --repo <repo> |
Report the requested result without starting or resuming experiments. Return the generated path for an HTML report.
Before starting or resuming an experiment, read the applicable workflow unless it is already in context:
- Workflow: starting, continuing, resuming, or changing an experiment.
- Background: launching or controlling a detached run.
Experiment Boundary
- One run owns one Git repository, one numeric metric, one confirmed target, and approved path scopes.
- For a new foreground run, initialize successfully before creating its Goal; the Goal identifies the returned run id. If initialization reports
complete, no Goal is needed. - Use
finishto finalize each coherent experiment. Do not manually commit, revert, or edit run artifacts during an active run. - Only a verified target can mean
complete; an iteration limit, error, or external blocker has its own status. - Validate state through the control script on entry or resume. Use recorded experiments rather than guessing from conversation.
- Surface command and state errors with their diagnostic paths. Never bypass validation, fabricate metrics, or reconstruct missing events.
Foreground continuation belongs to the official Codex Goal. Background continuation belongs to the detached controller. An already launched background worker follows its supplied experiment contract, without starting a new launch flow.
Reviews
No reviews yet. Tell others what you thought.
Comments
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.