Is reaatech/agent-eval-harness safe to install?
End-to-end agent evaluation — trajectory eval, tool-use correctness, cost-per-task, latency budgets, regression suites with golden trajectories, LLM-as-judge with calibration. For full agent runs, not just classifiers.
6.4 / 10
Established • Skills Mode
Solid, but check the details before adopting.
Install verdict
Usable with caution. Check weak dimensions first.
Dimensions
Alive
9.4
Legit
3.2
Solid
6.8
Usable
7.0
Repository Stats
Embed this badge
Show users this server is actively trust-scored. Add the MCP Skills trust badge to your README to show current status.
Want the full signal breakdown?
Unlock safety scan findings, signal-level scores, and actionable recommendations.
Get the full report →