- name
SKILL.md
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add MiniMax-AI/mcode-stack --skill harness-experiment -a cursor -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add MiniMax-AI/mcode-stack --skill harness-experiment -a claude-code -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add MiniMax-AI/mcode-stack --skill harness-experiment -a codex -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add MiniMax-AI/mcode-stack --skill harness-experiment -a grok -ySend the copied message in a Grok Bot chat. The Bot fetches this SKILL.md from GitHub and adds it to the skills all your Bots share.
Install this skill: https://github.com/MiniMax-AI/mcode-stack/tree/HEAD/stacks/ronny/skills/harness-experimentFrom the publisher
Harness engineering moves forward by experiment. The principle: measure first, change one thing at a time, keep what survives testing.
Companion to MCode Engineering Notes 01, 02 and 05.
One prompt edit, one tool moved, one subagent merged, one threshold changed. If you need several, run several experiments.
For baseline and candidate, record:
Only report numbers you actually measured, with run counts.
trajectory-review). Find out why it flipped.Scaffolding built around a model's weak spots ages fastest. After each model upgrade, rerun the eval and ask which parts of the harness still earn their keep.
A short experiment record: hypothesis, the single change, eval set and run count, the metric table for baseline and candidate, flipped tasks with causes, and the decision (keep / revert / iterate).
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 ave
---name: harness-experimentdescription: Run a harness change as a controlled experiment, with a small end-to-end eval, one change at a time, repeated…---# stacks/ronny/skills/harness-experiment/SKILL.mdOverview
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.
FAQ
Download stacks/ronny/skills/harness-experiment/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
The publisher keeps it at https://github.com/MiniMax-AI/mcode-stack.
Claude, Cursor, Codex, and Grok Build can read a SKILL.md you add from the publisher's repository. Grok Bot installs it when you send the skill's GitHub folder link in a chat.