Agent Eval Harness
Generic agentic evaluation for skills and agents. Provides end-to-end skills to analyze, test, score, review, and iteratively improve agent skills with MLflow support for experiment tracking, tracing, and reporting.
Works with: Claude Code, Cursor, Claude Desktop, Codex CLI, Gemini CLI, Cline, Windsurf, VS Code
Category: Dev Tools & CI — see all ranked ›
Work: Model evaluation · Agent development
Who it is for: AI engineer
“Registry README about registry.yaml and nightly SHA pinning; this plugin is never named.”
- tashan score: 54.0
- Expertise: 40.0 (thin)
- Adoption: 1 repos
- Health: active
- GitHub stars: 5
- Contributors: 4
- License: Apache-2.0
Security audit
Not scanned yet. We audit npm-published capabilities for known advisories, install-time scripts and permission surface; this one has no npm package we can resolve, or has not reached the queue.
source ↗ · plugin:redhat-global-engineering/ge-public-skills/agent-eval-harness
Already running this? npx tashan-cli doctor checks your whole config against the Index — how it works ›