jrichlen/eval-ladder
v0.0.1MIT
Design and audit an agent system's eval ladder — the cheapest rung that catches each regression, the blind spot beside every green, judges validated by TPR/TNR, pass^k for irreversible actions. Use when designing or auditing a test/eval strategy.
plugin.json
- name
- eval-ladder
- version
- 0.0.1
- description
- Design and audit an agent system's eval ladder — the cheapest rung that catches each regression, the blind spot beside every green, judges validated by TPR/TNR, pass^k for irreversible actions. Use when designing or auditing a test/eval strategy.
- author
- Jordan Richlen
- license
- MIT
plugin.json
{
"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
"name": "eval-ladder",
"version": "0.0.1",
"description": "Design and audit an agent system's eval ladder — the cheapest rung that catches each regression, the blind spot beside every green, judges validated by TPR/TNR, pass^k for irreversible actions. Use when designing or auditing a test/eval strategy.",
"author": {
"name": "Jordan Richlen"
},
"homepage": "https://github.com/JRichlen/agent-plugins/tree/main/plugins/eval-ladder",
"repository": "https://github.com/JRichlen/agent-plugins",
"license": "MIT",
"keywords": [
"evals",
"testing-strategy",
"llm-as-judge",
"coverage-audit",
"pass-at-k",
"test-tiers"
]
}