Not in the top 1,000 by GitHub stars

TheGreenCedar/codex-autoresearch

A codex plugin for running optimization loops inside a codebase. It is useful when you have a measurable target and many possible changes to try: test runtime, build speed, bundle size, model loss, Lighthouse scores, memory use, query latency, or any other metric you can print from a script.

Codex Testing

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

`plugins/codex-autoresearch/skills/codex-autoresearch/SKILL.md`

Week of Nov 2, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

fbc07c5f8ea4 → fbc07c5f8ea4

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → fbc07c5f8ea4

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit fbc07c5f8ea41cd756e59812d71b5b9948179dc6

Version-pinned installation · Codex

git clone --filter=blob:none --no-checkout https://github.com/TheGreenCedar/codex-autoresearch.git .hotskills/thegreencedar-codex-autoresearch && git -C .hotskills/thegreencedar-codex-autoresearch checkout --detach fbc07c5f8ea41cd756e59812d71b5b9948179dc6
# Copy each selected skill directory from .hotskills/thegreencedar-codex-autoresearch into .agents/skills/<skill-name>/

836GitHub stars

-1star in 7 days

1skill in this repository

0commits in 30 days

Heat

0.2

Star growth, last 7 daysNot available
Star growth, last 24 hoursNot available
Rank movement, last 7 daysNot available
Commits, last 30 daysNot available
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Individual skills in this repository

codex-autoresearch plugins/codex-autoresearch/skills/codex-autoresearch

How it works

codex-autoresearch

When your agent uses it

Triage improvement work and run or resume accepted measured loops in a local project. Architecture, documentation, UX, product study, open research, taste, and one-shot fixes stay direct unless the user explicitly requests repeated measurement with a complete experiment contract.

What it loads into context

Frontmatter

59 tokens

Always available to the agent

SKILL.md

2,882 tokens

When the skill is activated

Reference documents

16,153 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Route before discovery
Continue directly when the loop does not fit
Establish the accepted experiment
Resume from one canonical decision
Run one bounded packet
Recover logging exactly once
Keep execution boundaries intact
Finalize accepted work
Load only what the decision requires
Governed investigations

Files

../../docs/comparative-evaluation.mddoc6,648 bytes
../../docs/control-plane.mddoc7,737 bytes
../../docs/finish.mddoc5,289 bytes
../../docs/investigations.mddoc13,347 bytes
../../docs/operate.mddoc10,817 bytes
../../docs/start.mddoc6,130 bytes
../../docs/troubleshooting.mddoc10,647 bytes
../../docs/trust.mddoc10,583 bytes
SKILL.mdcore15,084 bytes
SKILL.mdcore15,084 bytes
SKILL.mdcore15,084 bytes
SKILL.mdcore15,084 bytes
SKILL.mdcore15,084 bytes
agents/openai.yamlasset402 bytes
references/dashboard-trust.mddoc3,040 bytes
references/loop-operations.mddoc4,348 bytes
references/research-finalize.mddoc3,309 bytes

Read SKILL.md


# Codex Autoresearch

Decide fit before exploring the repository. Autoresearch governs repeated measured experiments; it does not take over every task that mentions research, quality, or improvement.

Use this as the only Codex-facing Autoresearch skill. Do not route to retired subskills, slash commands, or MCP surfaces.

## Route before discovery

Make one read-only fit call before benchmark discovery, recipe lookup, repository scanning, default inference, or setup:

```bash
node scripts/autoresearch.mjs prompt-plan --cwd <project> --prompt "<request>"
```

View the complete source on GitHub

Skills included

codex-autoresearch

Repository facts

License: Apache-2.0
Created: Apr 20, 2026
Last pushed: Oct 11, 2026
Forks: 58
Open issues: 1
Project activity: Active

Rank over the last 12 weeks

Now #1,000 · best #647 · down 299 in 30 days

#973 on Oct 25
#987 on Oct 28
#989 on Oct 29
#993 on Oct 30
#998 on Oct 31
#1,000 since Nov 1

12 earlier periods

#615 on Aug 2
#647 on Aug 13
#649 on Aug 17
#660 on Aug 23
#666 on Aug 26
#700 on Aug 28
#650 on Aug 30
#721 on Sep 10
#701 on Sep 13
#762 on Oct 5
#806 on Oct 13
#849 on Oct 21

Before you install

Instructions only

Automated signals, not a guarantee

Checked Nov 4, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 4 notes

plugins/codex-autoresearch/skills/codex-autoresearch/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
plugins/codex-autoresearch/skills/codex-autoresearch/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
plugins/codex-autoresearch/skills/codex-autoresearch/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
plugins/codex-autoresearch/skills/codex-autoresearch/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

No broad tool permissions
No dangerous shell commands
No network access
No hidden or obfuscated text
No instruction overrides
No executable scripts
No access to secrets
No requests to vote in Hot

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.

No combined signals at this commit.

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Compatible	Standard SKILL.md plugins/codex-autoresearch/skills/codex-autoresearch/SKILL.md	`.claude/skills/<skill-name>/`
Codex	Native	Manifest AGENTS.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md plugins/codex-autoresearch/skills/codex-autoresearch/SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md plugins/codex-autoresearch/skills/codex-autoresearch/SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md plugins/codex-autoresearch/skills/codex-autoresearch/SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md plugins/codex-autoresearch/skills/codex-autoresearch/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.

TheGreenCedar/codex-autoresearch

History

plugins/codex-autoresearch/skills/codex-autoresearch/SKILL.md

Share this page