Is Auto Research safe and trustworthy?

tashan scores Auto Research on public evidence — tashan score 25.0/100, it is currently active, note: a single primary maintainer (bus-factor risk). Audit scope: OSV advisories, install-time scripts, build provenance and declared permission surface. We do not review source code or execute the capability.

How do I install Auto Research?

Configure it from its source repository — it is a remote / registry server.

Who maintains Auto Research?

1 GitHub contributors, source: gyoz-ai/auto-research.

‹ The Index

Auto Research

plugin

Autonomous skill improvement through parallel research agents. Inspired by Karpathy's autoresearch methodology, it spawns 5 parallel agents (domain expert, quality auditor, competitive analyst, gap analyst, tech scout), synthesizes findings into ranked proposals, then runs an iterative keep/discard experiment loop to improve any Claude Code skill. Scores skills on 7 quality dimensions and only keeps changes that genuinely improve the composite score.

Works with: Claude Code (native)
native: this artifact type is that client's own format

Category: Security — see all ranked ›

Install (Claude Code):

/plugin marketplace add anthropics/claude-plugins-community
/plugin install auto-research@claude-community

solid

“7 worked examples; short of deep on per-tool docs and a stated limitation and setup/auth”

This grade is wrong ›

tashan score: 25.0
Instruction depth: 65.0 (solid — documents the job properly, with examples you could follow)
Adoption: 1 repos
Upkeep: 43.0
Freshness: 54.0
Evidence coverage: 84% of the inputs this score can use — the rest are unknown, and the score is discounted for it
Health: active
GitHub stars: 3
Contributors: 1
License: MIT

Security audit

Not scanned yet. We audit npm-published capabilities for known advisories, install-time scripts and permission surface; this one has no npm package we can resolve, or has not reached the queue.

You searched for one. Check the rest of your stack:

npx tashan-cli doctor

Reads the config already on your machine and names what is dead, deprecated or running code at install time. No account, nothing uploaded.

tashan Pro$6/mo

Auto Research scores 25 today. Pro keeps the series, so you can see whether that is a project getting better or one on its way down.

The whole series behind any row, back to the first day we measured it
The replacement, named — not just the news that something died
tashan doctor over your own config, on your own machine

Start a 7-day trial › Everything measured on this page stays free.

Show your score

Measured this well? Put the live badge in your README — it updates as the score does.

[![tashan](https://tashan.sh/badge/plugin-gyoz-ai-auto-research-auto-research.svg)](https://tashan.sh/capability/plugin-gyoz-ai-auto-research-auto-research.html)

source ↗ · plugin:gyoz-ai/auto-research/auto-research

Everything on this page is public evidence and free. What it cannot know is whether you run this — check your whole config, free, in the browser. tashan Pro adds the series behind each row and names a replacement for anything dying.

Already running this? Check your whole config — free, in your browser, nothing installed. Or npx tashan-cli doctor locally, which sends nothing at all.

Measured 2026-09-13 · scorer s5 · how · something wrong here?