Multi Agent Eval Harness

Role-level metrics, coordination-failure tests, and transcript grading for multi-agent systems. Use when single-agent eval misses bugs that only appear when agents collaborate — handoff drops, role drift, blame loops, deadlocks.

akillness Updated 57 repo stars
Neon sea-creature AI companion squad inspired by the jeo-code mascot

File contents

akillness/oh-my-gods commit 5de667561f

Frequently asked questions

npx get-skill add akillness/multi-agent-eval-harness