MiniMax-AI/mcode-stack

MiniMax-AI/mcode-stack

Description: The workflows and skills the MiniMax Code team uses to build MiniMax Code. Open source, install and use.

Language: JavaScript

License: MIT

Stars: 1

Forks: 1

Open issues: 2

Created: 2026-10-28T02:17:41Z

Pushed: 2026-10-28T02:52:19Z

Default branch: main

Fork: no

Archived: no

README:

English · 中文

The workflows and skills the MiniMax Code team uses to build MiniMax Code. Open source, install and use.

This is not a prompt collection or a list of "best practices". It is what people on the team actually use every day: how to keep AI-written code at a high bar, how to decide whether a task should go to a subagent, how long to wait on a long command, how to keep long sessions from going dull, and what goes into context on every turn. Each piece is a SKILL.md skill or checklist that installs straight into MiniMax Code.

• [Quick start](#quick-start)
• [What's inside](#whats-inside)
• [How it works](#how-it-works)
• [Articles](#articles)
• [Stacks](#stacks)
• [Contribute your own stack](#contribute-your-own-stack)

Quick start

One skill, for all your projects:

git clone https://github.com/MiniMax-AI/mcode-stack.git ~/mcode-stack
mkdir -p ~/.agents/skills
cp -R ~/mcode-stack/stacks/ronny/skills/long-command-check ~/.agents/skills/

Open a new session and type /skills in MiniMax Code to see it. Run it with /long-command-check, or let the agent load it from its description.

The whole stack, as a plugin:

mcode plugin marketplace list # shows your local plugin directory

Copy the whole stacks/ronny directory into that directory, then open /plugins in MiniMax Code and press Ctrl+R to refresh. A local plugin is installed as soon as it is in that directory; press Space in the panel to enable or disable it.

More install options

MiniMax Code discovers skills in these directories (one subdirectory per skill, containing SKILL.md):

• For the current project only: .minimax/skills/, .claude/skills/ or

.agents/skills/ in the project

• For all projects: ~/.agents/skills/ (~/.claude/skills/ and

~/.codex/skills/ are read too)

mcode plugin add installs from the official catalog only; it does not take a GitHub URL or a local path.

The skills use the common SKILL.md format, so most of them also work in other agents that support skills.

What's inside

| When | Skill | What it does | | --- | --- | --- | | Plan & split | [subagent-split-check](stacks/ronny/skills/subagent-split-check/SKILL.md) | Decide whether work goes to a subagent or stays in the main loop | | | [engineering-small-prs](stacks/ronny/skills/engineering-small-prs/SKILL.md) | Split large features, refactors and migrations into small reviewable PRs | | | [engineering-change-descriptions](stacks/ronny/skills/engineering-change-descriptions/SKILL.md) | Write PR and commit descriptions that say what changed and why | | Context & tools | [tool-budget-audit](stacks/ronny/skills/tool-budget-audit/SKILL.md) | Measure what tools cost in context; trim, tool search or programmatic tool calling | | | [context-tax-audit](stacks/ronny/skills/context-tax-audit/SKILL.md) | What gets injected into every request, and what it does to the prompt cache | | Long sessions & commands | [long-session-check](stacks/ronny/skills/long-session-check/SKILL.md) | Drop, summarize or write to file; compact or start fresh; memory scoping | | | [handoff-doc](stacks/ronny/skills/handoff-doc/SKILL.md) | A hand-off doc so a new session can pick up the work | | | [long-command-check](stacks/ronny/skills/long-command-check/SKILL.md) | Ten-point audit of long shell commands and background tasks | | Review | [independent-review](stacks/ronny/skills/independent-review/SKILL.md) | Review a diff from a clean context: only diff, requirement and test results | | | [engineering-code-review](stacks/ronny/skills/engineering-code-review/SKILL.md) | Review a change for code health: design, functionality, complexity, tests, approval risk | | | [engineering-review-comments](stacks/ronny/skills/engineering-review-comments/SKILL.md) | Write clear, severity-labeled review comments that explain the reasoning | | | [engineering-review-feedback](stacks/ronny/skills/engineering-review-feedback/SKILL.md) | Handle reviewer comments as the author: fix, clarify, resolve disagreements | | Experiments & hotfixes | [harness-experiment](stacks/ronny/skills/harness-experiment/SKILL.md) | Small eval, one change at a time, repeated runs, look at flipped tasks | | | [trajectory-review](stacks/ronny/skills/trajectory-review/SKILL.md) | Look at how the agent got its result, not only whether it passed | | | [engineering-emergency-changes](stacks/ronny/skills/engineering-emergency-changes/SKILL.md) | Decide whether a hotfix is a real emergency and run expedited review safely |

A stack usually has three kinds of things:

| Kind | What it is | How to use it | | --- | --- | --- | | Skill | A directory with a SKILL.md | Invoke it in MiniMax Code with /, or let the agent load it from its description | | Checklist | Also a skill: the agent walks your project item by item. A plain-text copy lives in checklists/ | Same as above, or just read it | | Workflow | A WORKFLOW.md describing how this person works with MiniMax Code every day | Read it |

How it works

AI writes code faster every month. What separates results now is the layer of engineering habits around the agent: when to make it stop and check its own work, who reviews, where state lives, what counts as a real experiment. Those habits are hard to follow from an article, so we turned them into skills and checklists. They pair with our *MCode Engineering Notes* column: the article explains the idea, this repository makes it runnable.

We also believe harness engineering is a craft that moves forward by experiment. Everything here will keep changing as we learn. Take it, change it, and send your version back.

Articles

| # | MCode Engineering Notes | Companion skills | | --- | --- | --- | | 01 | [More subagents isn't better: manage context first, then parallelize](notes/01-subagent.md) | independent-review, subagent-split-check, harness-experiment | | 02 | [Too many tools will eat your context: from tool search to PTC](notes/02-tool-context.md) | tool-budget-audit | | 03 | [Keeping long sessions sharp: compaction vs....