# MCode Stack — AI Coding Tool Review & Pricing

> MCode Stack is MiniMax's open-source repository of the workflows, skills and checklists the MiniMax Code team actually uses to build MiniMax Code. Each team member's stack is a plugin package of SKILL.md skills that encode engineering habits for agentic coding, from context budgeting and subagent splitting to independent review, and pairs with the MCode Engineering Notes article series.

Source: https://ai.dosa.dev/tools/mcode-stack · Updated Oct 29, 2026 · Category: Developer Productivity & Workflow · Published by dosa.dev

## At a glance

- **Tool**: MCode Stack
- **Company**: MiniMax
- **Category**: [Developer Productivity & Workflow](https://ai.dosa.dev/category/productivity)
- **Pricing model**: Open Source
- **Official website**: https://github.com/MiniMax-AI/mcode-stack

## Key features

- Per-engineer stacks (ronny, jiachen) shipped as installable plugin packages
- Skills for planning and splitting work: subagent-split-check, engineering-small-prs, engineering-change-descriptions
- Context and long-session skills: tool-budget-audit, context-tax-audit, long-session-check, handoff-doc, long-command-check
- Review and experiment skills: independent-review, engineering-code-review, harness-experiment, trajectory-review
- Installs as a plugin marketplace in MiniMax Code, Claude Code and Codex, or by copying skills into ~/.agents/skills/

## Pricing

**Model**: Open Source

Free and open source under the MIT license; the skills run inside MiniMax Code, Claude Code, Codex or other skill-aware agents, which bring their own model costs.

## Who it is for

- **Best for**: Developers using MiniMax Code, Claude Code or Codex who want battle-tested, team-authored skills for keeping AI-written code reviewable and agent context lean.
- **Not ideal for**: Anyone looking for a standalone coding agent or IDE, since this is a skills and workflow collection rather than an agent itself.

## Verdict

A rare look at how an AI coding-agent team works with its own agent, packaged as reusable skills that are useful well beyond MiniMax Code.

## Recent updates

Published on October 28, 2026 with 390+ stars in its first days; October 29, 2026 updates made each stack a one-command Claude Code and Codex install and renumbered the Engineering Notes companions.

## Frequently asked questions

### Is MCode Stack free?

Yes - MCode Stack is Open Source. Free and open source under the MIT license; the skills run inside MiniMax Code, Claude Code, Codex or other skill-aware agents, which bring their own model costs.

### Is MCode Stack open source?

Yes - MCode Stack is open source. Free and open source under the MIT license; the skills run inside MiniMax Code, Claude Code, Codex or other skill-aware agents, which bring their own model costs.

### Who is MCode Stack best for?

Developers using MiniMax Code, Claude Code or Codex who want battle-tested, team-authored skills for keeping AI-written code reviewable and agent context lean.

### Who is MCode Stack not ideal for?

Anyone looking for a standalone coding agent or IDE, since this is a skills and workflow collection rather than an agent itself.

### What are the best MCode Stack alternatives?

The closest MCode Stack alternatives on ai.dosa.dev are Pieces for Developers, agenttrace, Vibe Kanban - all listed under Developer Productivity & Workflow.

### Who makes MCode Stack?

MCode Stack is developed by MiniMax. It is listed in the Developer Productivity & Workflow category on ai.dosa.dev.

## Top alternatives

- [Pieces for Developers](https://ai.dosa.dev/tools/pieces-for-developers) (Freemium) — Developers and teams who need to manage disparate workflow context, revisit past coding decisions, and maintain consistent documentation across multiple tools and projects.
- [agenttrace](https://ai.dosa.dev/tools/agenttrace) (Open Source) — Developers who need a privacy-conscious way to audit, monitor, and diagnose the behavior, costs, and performance of various AI coding agents locally.
- [Vibe Kanban](https://ai.dosa.dev/tools/vibe-kanban) (Free) — Solo developers and individual power users who need to run multiple AI coding agents in parallel while managing separate git worktrees and tasks locally.
- [ai-memory](https://ai.dosa.dev/tools/ai-memory) (Open Source) — Developers who frequently switch between multiple AI coding agents or machines and want a unified, persistent knowledge base that survives session ends and tool switches.
- [smolvm](https://ai.dosa.dev/tools/smolvm) (Open Source) — Running untrusted code, powering coding agents with persistent/resettable workspaces, and deploying portable VM-based workloads that require a real Linux kernel.
- [coop](https://ai.dosa.dev/tools/coop) (Open Source) — Security-conscious developers who want to run autonomous coding agents on real projects without risking host machine compromise.
- Full alternatives guide: https://ai.dosa.dev/tools/mcode-stack/alternatives