iris-eval
01Plugin Claude Code
Plugin marketplace listing 1 plugin: iris-eval.
7 8d ago A
tokens not measured
original MIT
The agent eval standard for MCP — score output quality, catch safety failures, enforce cost budgets
Plugin Claude Code
Plugin marketplace listing 1 plugin: iris-eval.
Plugin Claude Code
Stop shipping agents on vibes. Score every agent output for quality, safety, and cost.
Plugin Claude Code
Agent eval for any MCP workflow — score output quality, catch PII and prompt injection, verify citations, and enforce cost budgets. Adds the Iris MCP server (9 tools) plus an agent-eval skill that guides eval-driven development.