# Speculator

> Speculator — spec quality scoring and a 7-gate pipeline (4 required + 3 opt-in: eval intent, eval quality, comprehension — each bindable to spec risk levels) with LLM-as-judge evaluation, git worktree isolation, and beads issue tracking. Includes asbuilt-quiz: a human-facing comprehension quiz generator built on the As-Built knowledge system. Quality In, Quality Out.

## Facts
- Page: https://tashan.sh/capability/plugin-dmokong-speculator-speculator
- tashan id: plugin:dmokong/speculator/speculator
- Source: https://github.com/DMokong/speculator
- Type: plugin
- Category: devtools
- tashan score: 35.0 / 100
- Adoption: 7.0
- Upkeep: 61.0
- Freshness: 92.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- GitHub stars: 0
- License: MIT
- Official: no

## Install

```sh
/plugin marketplace add DMokong/claude-plugins
/plugin install speculator@dmokong-plugins
```

## 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.