# Seldon

> Run AI personas against your live product to find what breaks and why. QA baselines as code, persona usability experiments, and messaging tests — authored, run and read from inside your agent.

## Facts
- Page: https://tashan.sh/capability/plugin-blok-intelligence-seldon-claude-plugin-seldon
- tashan id: plugin:blok-intelligence/seldon-claude-plugin/seldon
- Source: https://github.com/blok-intelligence/seldon-claude-plugin
- Type: plugin
- Category: devtools
- tashan score: 35.0 / 100
- Adoption: 7.0
- Upkeep: 62.0
- Freshness: 94.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- GitHub stars: 0
- Official: no

## Install

```sh
/plugin marketplace add blok-intelligence/seldon-claude-plugin
/plugin install seldon@seldon
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-09-13 by tashan (https://tashan.sh) from public evidence. Scorer s5.