# Holomime

> Behavioral alignment for AI agents. Detect drift with 8 rule-based detectors, stress-test with adversarial benchmarks (grade A-F), visualize behavioral patterns in 3D, and run structured therapy sessions that generate DPO training data. Six slash commands — zero to aligned in one install.

## Facts
- Page: https://tashan.sh/capability/plugin-productstein-holomime-holomime
- tashan id: plugin:productstein/holomime/holomime
- Source: https://github.com/productstein/holomime
- Type: plugin
- Category: other
- tashan score: 29.0 / 100
- Adoption: 13.0
- Upkeep: 61.0
- Freshness: 55.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- GitHub stars: 2
- License: MIT
- Official: no

## Install

```sh
/plugin marketplace add anthropics/claude-plugins-community
/plugin install holomime@claude-community
```

## 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.