#397 by GitHub stars
leo-lilinxiao/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.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
0f54c5717074 → 0f54c5717074
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0f54c5717074
No earlier version was observed for comparison.
Heat
6.2- Star growth, last 7 daysAhead of 91% of tracked repositories
- Star growth, last 24 hoursAhead of 93% of tracked repositories
- Rank movement, last 7 daysAhead of 56% of tracked repositories
- Commits, last 30 daysAhead of 0% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
How it works
codex-autoresearch
When your agent uses it
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.
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
506 tokensWhen the skill is activated
Reference documents
15,871 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Respond To The Request
- Experiment Boundary
Scripts executed separately
scripts/autoresearch.pyscripts/autoresearch_core.pyscripts/autoresearch_report.pyscripts/run_contributor_gate.shscripts/run_skill_e2e.shscripts/validate_skill_structure.shtests/e2e-fixtures/counter_reduction/scripts/score.pytests/e2e-fixtures/interactive_unittest_fix/scripts/score.pytests/e2e-fixtures/interactive_unittest_fix/src/math_utils.pytests/e2e-fixtures/interactive_unittest_fix/tests/test_math_utils.pytests/test_autoresearch.pytests/test_structure.py
Files
.github/workflows/ci.ymlasset1,029 bytes.gitignoreasset63 bytesCITATION.cffasset527 bytesCONTRIBUTING.mddoc3,035 bytesLICENSEasset1,063 bytesREADME.mddoc9,349 bytesSKILL.mdcore2,549 bytesagents/openai.yamlasset301 bytesdocs/EXAMPLES.mddoc4,722 bytesdocs/GUIDE.mddoc8,135 bytesdocs/INSTALL.mddoc2,142 bytesdocs/i18n/README_DE.mddoc4,008 bytesdocs/i18n/README_ES.mddoc3,851 bytesdocs/i18n/README_FR.mddoc4,048 bytesdocs/i18n/README_JA.mddoc4,165 bytesdocs/i18n/README_KO.mddoc3,945 bytesdocs/i18n/README_PT.mddoc3,813 bytesdocs/i18n/README_RU.mddoc5,798 bytesdocs/i18n/README_ZH.mddoc3,677 bytesimage/autoresearch-report.pngasset118,814 bytesimage/banner.pngasset2,440,451 bytesreferences/background.mddoc2,229 bytesreferences/workflow.mddoc7,487 bytesscripts/autoresearch.pyruns57,740 bytesscripts/autoresearch_core.pyruns47,201 bytesscripts/autoresearch_report.pyruns23,156 bytesscripts/run_contributor_gate.shruns608 bytesscripts/run_skill_e2e.shruns11,800 bytesscripts/validate_skill_structure.shruns198 bytestests/e2e-fixtures/counter_reduction/.gitignoreasset31 bytestests/e2e-fixtures/counter_reduction/scripts/score.pyruns97 bytestests/e2e-fixtures/counter_reduction/src/value.txtdoc2 bytestests/e2e-fixtures/interactive_unittest_fix/.gitignoreasset50 bytestests/e2e-fixtures/interactive_unittest_fix/prompt.txtdoc104 bytestests/e2e-fixtures/interactive_unittest_fix/scripts/score.pyruns373 bytestests/e2e-fixtures/interactive_unittest_fix/src/math_utils.pyruns49 bytestests/e2e-fixtures/interactive_unittest_fix/tests/test_math_utils.pyruns325 bytestests/test_autoresearch.pyruns39,712 bytestests/test_structure.pyruns2,000 bytes
Read SKILL.md
# 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:
View the complete source on GitHubSkills included
- codex-autoresearch
Repository facts
- License
- MIT
- Created
- Mar 18, 2026
- Last pushed
- Sep 12, 2026
- Forks
- 130
- Open issues
- 1
- Project activity
- Active
Rank over the last 12 weeks
Now #397 · best #356 · down 30 in 30 days
- #389 on Nov 1
- #388 on Nov 2
- #390 on Nov 3
- #392 from Nov 4 to Nov 5
- #394 on Nov 6
- #397 since Nov 7
77 earlier periods
- #360 on Aug 2
- #362 from Aug 8 to Aug 9
- #374 on Aug 10
- #372 on Aug 11
- #367 on Aug 12
- #371 on Aug 13
- #368 on Aug 14
- #367 on Aug 15
- #373 on Aug 16
- #370 on Aug 17
- #376 on Aug 18
- #372 on Aug 19
- #371 from Aug 20 to Aug 21
- #367 on Aug 22
- #372 on Aug 23
- #375 on Aug 24
- #373 on Aug 25
- #372 on Aug 26
- #373 on Aug 27
- #374 on Aug 28
- #367 on Aug 29
- #362 on Aug 30
- #370 on Aug 31
- #378 on Sep 1
- #371 on Sep 2
- #373 on Sep 3
- #363 on Sep 4
- #367 on Sep 5
- #365 on Sep 6
- #372 on Sep 7
- #369 from Sep 8 to Sep 9
- #370 on Sep 10
- #364 on Sep 11
- #368 on Sep 12
- #367 on Sep 13
- #372 on Sep 14
- #373 from Sep 15 to Sep 16
- #367 on Sep 17
- #369 on Sep 18
- #363 on Sep 19
- #374 on Sep 20
- #370 on Sep 21
- #374 on Sep 22
- #367 on Sep 23
- #365 on Sep 24
- #363 on Sep 25
- #356 on Sep 26
- #357 on Sep 27
- #359 on Sep 28
- #370 on Sep 29
- #366 on Sep 30
- #365 on Oct 1
- #366 on Oct 2
- #359 on Oct 3
- #357 on Oct 4
- #362 on Oct 5
- #361 on Oct 6
- #365 on Oct 7
- #367 on Oct 8
- #372 on Oct 9
- #362 on Oct 10
- #364 on Oct 11
- #369 from Oct 12 to Oct 13
- #371 on Oct 14
- #368 on Oct 15
- #372 on Oct 16
- #364 on Oct 17
- #372 from Oct 18 to Oct 19
- #375 on Oct 20
- #372 from Oct 21 to Oct 22
- #373 on Oct 23
- #367 on Oct 24
- #380 on Oct 25
- #387 on Oct 28
- #389 on Oct 29
- #390 on Oct 30
- #391 on Oct 31
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 2, 2026
- No broad tool permissions
- 4 dangerous shell commandsin 2 files: scripts/run_skill_e2e.sh:65 tests/e2e-fixtures/interactive_unittest_fix/scripts/score.py:9
- 38 network referencesin 11 files: README.md:11 CITATION.cff:6 docs/INSTALL.md:22 and 8 more
- No hidden or obfuscated text
- No instruction overrides
- 12 executable scriptsin 12 files: scripts/autoresearch.py:1 scripts/autoresearch_core.py:1 scripts/autoresearch_report.py:1 and 9 more
- 2 references to secretsin 1 file: scripts/autoresearch_core.py:663
- No requests to vote in Hot
Show all 56 signals by file
CITATION.cff
- Network accessline 6
- family-names: "Li" given-names: "Linxiao" repository-code: "https://github.com/leo-lilinxiao/codex-autoresearch" - Network accessline 7
given-names: "Linxiao" repository-code: "https://github.com/leo-lilinxiao/codex-autoresearch" url: "https://github.com/leo-lilinxiao/codex-autoresearch" - Network accessline 8
repository-code: "https://github.com/leo-lilinxiao/codex-autoresearch" - Network accessline 9
url: "https://github.com/leo-lilinxiao/codex-autoresearch"
README.md
- Network accessline 11
<p align="center"> <a href="https://developers.openai.com/codex/skills"><img src="https://img.shields.io/badge/Codex-Skill-blue?logo=openai&logoColor=white" alt="Codex Skill"></a> - Network accessline 12
<a href="https://developers.openai.com/codex/skills"><img src="https://img.shields.io/badge/Codex-Skill-blue?logo=openai&logoColor=white" alt="Codex Skill"></a> - Network accessline 13
<a href="https://github.com/leo-lilinxiao/codex-autoresearch"><img src="https://img.shields.io/github/stars/leo-lilinxiao/codex-autoresearch?style=social" alt="GitHub Stars"></a> - Network accessline 14
<a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-green.svg" alt="MIT License"></a> - Network accessline 40
$skill-installer install https://github.com/leo-lilinxiao/codex-autoresearch - Network accessline 223
Inspired by [Karpathy's autoresearch](https://github.com/karpathy/autoresearch), generalized for Codex and software repositories. - Network accessline 231
year = {2026}, publisher = {GitHub}, url = {https://github.com/leo-lilinxiao/codex-autoresearch} - Network accessline 232
publisher = {GitHub}, url = {https://github.com/leo-lilinxiao/codex-autoresearch} } - Network accessline 233
url = {https://github.com/leo-lilinxiao/codex-autoresearch} - Network accessline 241
<a href="https://www.star-history.com/?repos=leo-lilinxiao%2Fcodex-autoresearch&type=timeline&legend=top-left"> - Network accessline 242
<picture> <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/image?repos=leo-lilinxiao/codex-autoresearch&type=timeline&theme=dark&legend=top-left" /> <source media="(prefers-color-scheme: light)" srcset - Network accessline 243
<source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/image?repos=leo-lilinxiao/codex-autoresearch&type=timeline&theme=dark&legend=top-left" /> - Network accessline 244
<source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/image?repos=leo-lilinxiao/codex-autoresearch&type=timeline&legend=top-left" /> - Network accessline 245
<img alt="Star History Chart" src="https://api.star-history.com/image?repos=leo-lilinxiao/codex-autoresearch&type=timeline&legend=top-left" />
docs/INSTALL.md
- Network accessline 22
$skill-installer install https://github.com/leo-lilinxiao/codex-autoresearch - Network accessline 32
git clone https://github.com/leo-lilinxiao/codex-autoresearch.git - Network accessline 42
git clone https://github.com/leo-lilinxiao/codex-autoresearch.git - Network accessline 52
git clone https://github.com/leo-lilinxiao/codex-autoresearch.git
docs/i18n/README_DE.md
docs/i18n/README_ES.md
docs/i18n/README_FR.md
docs/i18n/README_JA.md
docs/i18n/README_KO.md
docs/i18n/README_PT.md
docs/i18n/README_RU.md
docs/i18n/README_ZH.md
scripts/autoresearch.py
- Executable scriptline 1
#!/usr/bin/env python3
scripts/autoresearch_core.py
scripts/autoresearch_report.py
- Executable scriptline 1
#!/usr/bin/env python3
scripts/run_contributor_gate.sh
- Executable scriptline 1
#!/usr/bin/env bash
scripts/run_skill_e2e.sh
scripts/validate_skill_structure.sh
- Executable scriptline 1
#!/usr/bin/env bash
tests/e2e-fixtures/counter_reduction/scripts/score.py
- Executable scriptline 1
Executable file
tests/e2e-fixtures/interactive_unittest_fix/scripts/score.py
tests/e2e-fixtures/interactive_unittest_fix/src/math_utils.py
- Executable scriptline 1
Executable file
tests/e2e-fixtures/interactive_unittest_fix/tests/test_math_utils.py
- Executable scriptline 1
Executable file
tests/test_autoresearch.py
- Executable scriptline 1
Executable file
tests/test_structure.py
- Executable scriptline 1
Executable file
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 52 facts
- Network access in prose of documentationREADME.md:11Low confidence
- Network access in prose of documentationREADME.md:12Low confidence
- Network access in prose of documentationREADME.md:13Low confidence
- Network access in prose of documentationREADME.md:14Low confidence
- Network access in code of documentationREADME.md:40Low confidence
- Network access in prose of documentationREADME.md:223Low confidence
- Network access in code of documentationREADME.md:231Low confidence
- Network access in code of documentationREADME.md:232Low confidence
- Network access in code of documentationREADME.md:233Low confidence
- Network access in prose of documentationREADME.md:241Low confidence
- Network access in prose of documentationREADME.md:242Low confidence
- Network access in prose of documentationREADME.md:243Low confidence
- Network access in prose of documentationREADME.md:244Low confidence
- Network access in prose of documentationREADME.md:245Low confidence
- Network access in code of documentationdocs/INSTALL.md:22Low confidence
- Network access in code of documentationdocs/INSTALL.md:32Low confidence
- Network access in code of documentationdocs/INSTALL.md:42Low confidence
- Network access in code of documentationdocs/INSTALL.md:52Low confidence
- Network access in code of documentationdocs/i18n/README_DE.md:16Low confidence
- Network access in prose of documentationdocs/i18n/README_DE.md:99Low confidence
- Network access in code of documentationdocs/i18n/README_ES.md:16Low confidence
- Network access in prose of documentationdocs/i18n/README_ES.md:99Low confidence
- Network access in code of documentationdocs/i18n/README_FR.md:16Low confidence
- Network access in prose of documentationdocs/i18n/README_FR.md:99Low confidence
- Network access in code of documentationdocs/i18n/README_JA.md:16Low confidence
- Network access in prose of documentationdocs/i18n/README_JA.md:99Low confidence
- Network access in code of documentationdocs/i18n/README_KO.md:16Low confidence
- Network access in prose of documentationdocs/i18n/README_KO.md:99Low confidence
- Network access in code of documentationdocs/i18n/README_PT.md:16Low confidence
- Network access in prose of documentationdocs/i18n/README_PT.md:99Low confidence
- Network access in code of documentationdocs/i18n/README_RU.md:16Low confidence
- Network access in prose of documentationdocs/i18n/README_RU.md:99Low confidence
- Network access in code of documentationdocs/i18n/README_ZH.md:16Low confidence
- Network access in prose of documentationdocs/i18n/README_ZH.md:99Low confidence
- Executable script in code of a file that runsscripts/autoresearch.py:1High confidence
- Executable script in code of a file that runsscripts/autoresearch_core.py:1High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/autoresearch_core.py:663Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/autoresearch_core.py:717Low confidence
- Executable script in code of a file that runsscripts/autoresearch_report.py:1High confidence
- Executable script in code of a file that runsscripts/run_contributor_gate.sh:1High confidence
- Executable script in code of a file that runsscripts/run_skill_e2e.sh:1High confidence
- Dangerous shell operation in code of a file that runsscripts/run_skill_e2e.sh:65High confidence
- Dangerous shell operation in code of a file that runsscripts/run_skill_e2e.sh:66High confidence
- Dangerous shell operation in code of a file that runsscripts/run_skill_e2e.sh:79High confidence
- Executable script in code of a file that runsscripts/validate_skill_structure.sh:1High confidence
- Executable script in code of a testtests/e2e-fixtures/counter_reduction/scripts/score.py:1Low confidence
- Executable script in code of a testtests/e2e-fixtures/interactive_unittest_fix/scripts/score.py:1Low confidence
- Dangerous shell operation in code of a testtests/e2e-fixtures/interactive_unittest_fix/scripts/score.py:9Low confidence
- Executable script in code of a testtests/e2e-fixtures/interactive_unittest_fix/src/math_utils.py:1Low confidence
- Executable script in code of a testtests/e2e-fixtures/interactive_unittest_fix/tests/test_math_utils.py:1Low confidence
and 2 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/leo-lilinxiao-codex-autoresearch/)