# Double Check

> Make the AI rigorously review its own output before you ship: bidirectional reasoning + reverse rebuttal + domain checklists (13/21/18 questions). Catches AI hallucinations and false 'done'. Trigger with 2 / 'double-check' / 'review'.

## Facts
- Page: https://tashan.sh/capability/plugin-louislin0723-double-check-double-check
- tashan id: plugin:louislin0723/double-check/double-check
- Source: https://github.com/LouisLin0723/double-check
- Type: plugin
- Category: ai
- tashan score: 36.0 / 100
- Adoption: 13.0
- Upkeep: not measured
- Freshness: 77.0
- Evidence coverage: 59% 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 LouisLin0723/double-check
/plugin install double-check@double-check
```

## 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 2026-08-14 by tashan (https://tashan.sh) from public evidence. Scorer s5.
