Harness Experiment

Run a harness change as a controlled experiment, with a small end-to-end eval, one change at a time, repeated runs, and looking at flipped tasks, request count, tokens and cache hits, not just the average score. Use before and after changing prompts, tools, skills, subagent layout, compaction or other agent scaffolding, or when asked whether a change helped.

MiniMax AI Updated 13.8k repo stars
MCode Stack: the workflows and skills the MiniMax Code team uses to build MiniMax Code

File contents

MiniMax-AI/mcode-stack commit 22a333314a

Frequently asked questions

npx get-skill add minimax-ai/harness-experiment