🔌

setup-eval

🔌Plugin

redhat-community-ai-tools/harness-eval-lab

What it does

Security check pending

Evaluate AI agent setups for best practices, redundancy, security, and cross-component issues. 43 lint rules, per-component rubric review, deep security audit, and single-skill evaluation.

🏪

Part of

redhat-community-ai-tools/harness-eval-lab

Installation

Add marketplace in Claude Code:

/plugin marketplace add redhat-community-ai-tools/harness-eval-lab

Step 2. Install plugin:

/plugin install setup-eval@harness-eval-lab

AddedJun 22, 2026

View on GitHub Back to Plugins

More from this repository1

🏪

redhat-community-ai-tools/harness-eval-lab🏪Marketplace

Evaluate AI code agent setup. Scores the full configuration (CLAUDE.md, skills, commands, hooks, agents). Available as a CLI and a Claude Code plugin