AutoSciRub plugin for Codex
Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents
How to install AutoSciRub in Codex
1. Add the repo as a Codex plugin marketplace:
codex plugin marketplace add zjunlp/AutoSciRub2. Install the plugin from it:
codex plugin add autoscirub@autoscirub-localThis repo ships a Codex marketplace file (.agents/plugins/marketplace.json). The first command adds it as a marketplace (Codex CLI reference); the second installs the plugin 'autoscirub'. 'autoscirub-local' is the marketplace name from that file. Check the repo README too. Command format: Codex CLI reference.
What it contains
Plugins in this marketplace (1)
autoscirub— AutoSciRub skills for inducing executable scientific rubrics and guiding criterion-level research revision.
About this listing
AutoSciRub is a community plugin on GitHub by zjunlp, tagged codex-plugin. It passed the CodexStacks quality filter (at least 10 stars, pushed in the last 180 days, not a fork, has a description and a manifest or README). OpenAI hasn't reviewed it and we haven't tested it. From its files we found 1 plugin. It's one of 5 listings in the Scientific Research category (category assigned by CodexStacks from the repo's topics and description). It also appears in best Codex plugins for research.
Get new Codex plugins like AutoSciRub every week
The weekly CodexStacks drop: what's new and updated in the directory, in one short email.
You'll get a confirmation email first. Unsubscribe anytime.
AutoSciRub FAQ
How do I install AutoSciRub in Codex?
Add the repo as a Codex plugin marketplace with codex plugin marketplace add zjunlp/AutoSciRub, then install it with codex plugin add autoscirub@autoscirub-local. Both use the command format from the Codex CLI reference; check the repo README too.
Is AutoSciRub an official Codex plugin?
No. AutoSciRub is a community repo on GitHub by zjunlp. It passed the CodexStacks quality filter, but OpenAI hasn't reviewed it and we haven't tested it, so read the code before you install it.
What does AutoSciRub include?
From its manifest and repo files, AutoSciRub includes 1 plugin: autoscirub.
Details
- Type
- Plugin
- Category
- Scientific Research (assigned by us)
- Source
- Community
- Author
- zjunlp
- License
- MIT
- GitHub stars
- 41 (at last sync)
- Last push
- 2026-09-05
- Manifest
.agents/plugins/marketplace.json- GitHub topics
- agentic-ai, agents, autonomous-research, evaluation, llm-evaluation, plugins, research-agents, researchclawbench, scientific-agents
- Source
- https://github.com/zjunlp/AutoSciRub
- Listed via
- GitHub topic codex-plugin
- Tested by CodexStacks
- Not yet
Something wrong or missing? Submit or improve this listing. Listings also refresh automatically every night.
For maintainers: badge and embeds
Maintain AutoSciRub? Add the badge; it links to this page.
Markdown
[](https://codexstacks.com/p/autoscirub/)HTML
<a href="https://codexstacks.com/p/autoscirub/"><img src="https://codexstacks.com/badge.svg" alt="Listed on CodexStacks" width="172" height="28"></a>Embed card (static HTML and inline CSS, no JavaScript). Preview:
<a href="https://codexstacks.com/p/autoscirub/" style="display:block;max-width:380px;box-sizing:border-box;padding:14px 16px;border:1px solid #3a2c26;border-radius:12px;background:#0d0b0a;color:#f3ece6;font:14px/1.45 -apple-system,Segoe UI,Roboto,Helvetica,Arial,sans-serif;text-decoration:none"><span style="display:block;font-size:16px;font-weight:700;color:#f3ece6">AutoSciRub</span><span style="display:block;margin:2px 0 8px;font-size:12px;color:#b5a9a1">Community Codex plugin · 1 plugin</span><span style="display:block;margin:0 0 10px;color:#ddd3cc">Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents</span><span style="font-size:12px;font-weight:600;color:#ffb347">View on CodexStacks →</span></a>Markdown summary
**[AutoSciRub on CodexStacks](https://codexstacks.com/p/autoscirub/)**: Community Codex plugin with 1 plugin.More on badges, embeds and keeping your listing up to date: CodexStacks for plugin authors.
Also in Scientific Research
simulink-agentic-toolkit
The Simulink Agentic Toolkit gives your AI agent both the tools and the expertise to work effectively with Simulink and Model-Based Design.
matlab-agentic-toolkit
The MATLAB Agentic Toolkit brings proven MATLAB capabilities to AI agents, making engineering and scientific workflows agent-ready.
KERNEL
KERNEL is a Claude Code and Codex runtime for direct, decomposed execution with local memory and minimal hooks. Version 9.11.0 deploys the simplify deletion doctrine, preflight and verifier contract. Skills invoke as /kernel:<name> on Claude Code and $kernel:<name> on Codex; run /kernel:help first. Agent-readable summary: llms.txt.
Boltz
Use Boltz from Codex for biomolecular modeling workflows: predict structure and binding for protein, RNA, DNA, and ligand complexes; rank small-molecule or protein libraries against targets; and design novel small molecules, peptides, antibodies, nanobodies, or custom protein binders with structures and confidence metrics.