# Adversarial Spec

> Iteratively refine product specs through multi-model debate until consensus. Claude actively participates alongside GPT, Gemini, Grok, and other models. Includes interview mode, early agreement verification, and optional Telegram integration.

## Facts
- Page: https://tashan.sh/capability/plugin-zscole-adversarial-spec-adversarial-spec
- tashan id: plugin:zscole/adversarial-spec/adversarial-spec
- Source: https://github.com/zscole/adversarial-spec
- Type: plugin
- Category: ai
- tashan score: 52.0 / 100
- Adoption: 43.0
- Upkeep: 79.0
- Freshness: 55.0
- Evidence coverage: 84% of the inputs this score can use
- Health: stable
- Instruction depth: solid
- GitHub stars: 554
- License: MIT
- Official: no

## Install

```sh
/plugin marketplace add anthropics/claude-plugins-community
/plugin install adversarial-spec@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.