# Run bounded metric-improvement experiments with MiMoCode

> Run MiMoCode’s opt-in experiment workflow against a fixed evaluation budget, then review kept changes, measured deltas and an independent audit.

- Skill: `agentskillexchange/run-bounded-metric-improvement-experiments-with-mimocode` (Agent Skill)
- Install (CLI): `npx get-skill add agentskillexchange/run-bounded-metric-improvement-experiments-with-mimocode`
- Raw SKILL.md: https://api.skillmd.com/api/skills/agentskillexchange/run-bounded-metric-improvement-experiments-with-mimocode/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Security
- Author: agentskillexchange (https://skillmd.com/u/agentskillexchange)
- Updated: 2026-11-15
- Page: https://skillmd.com/skills/agentskillexchange/run-bounded-metric-improvement-experiments-with-mimocode

---


# Run bounded metric-improvement experiments with MiMoCode

Run MiMoCode’s opt-in experiment workflow against a fixed evaluation budget, then review kept changes, measured deltas and an independent audit.

## Prerequisites

MiMoCode workflow runtime; configured provider; Git; disposable repository checkout; fixed-budget evaluator and explicit editable scope

## Installation

Install or set up from the source-backed instructions:

Use a reviewed build containing commit 676c654d7cd6fe83e064365b1461d567ab3c0102. For source setup inspect upstream requirements, check out that commit, use the repository-declared Bun 1.3.14 toolchain, install dependencies and launch the documented bun run dev entry with MIMOCODE_EXPERIMENTAL_WORKFLOW_TOOL=true. Configure an authorized provider and confirm workflow is offered. Supply the documented research-experiment args and use a disposable checkout. Installation and execution were not tested.

- Source: https://github.com/XiaomiMiMo/MiMo-Code

## Documentation

- https://github.com/XiaomiMiMo/MiMo-Code/blob/676c654d7cd6fe83e064365b1461d567ab3c0102/packages/cli/src/workflow/builtin/research-experiment.js

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/run-bounded-metric-improvement-experiments-mimocode/)

