# EvalGlass/evalglass-core

Evaluation discipline for agentic apps — a vendored, local-first LLM-evaluation framework operated through your coding agent, with typed authority and a single Verdict Engine that gates only what you approve. The pure core; you decide what to measure and it derives no metrics on its own.

## Repository

- [Catalog detail page](https://awesomeclaudeplugins.com/EvalGlass/evalglass-core)
- [GitHub repository](https://github.com/EvalGlass/evalglass-core)
- Stars: 0
- Forks: 0
- 1 plugin entries are reported.

## Catalog provenance

- Publication state: indexable
- Quality note: Canonical repository has a description and validated plugin count.
- Catalog snapshot: Aug 31, 2026
- Repository metadata source: public GitHub API when available

## Installation

When this repository exposes a Claude Code marketplace, add it with:

```bash
/plugin marketplace add EvalGlass/evalglass-core
```