Agent
An agent for evaluating security-related work using defined inputs and assessment criteria.
265 4mo ago A 0 tokens
265Stars on the repository
24Mods indexed here, across every type
4mo agoLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied
analyzer
02Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
265 4mo ago A 0 tokens
comparator
03Agent
Compare two outputs WITHOUT knowing which skill produced them.
265 4mo ago A 0 tokens
grader
04Agent
Evaluate expectations against an execution transcript and outputs.
265 4mo ago A 0 tokens