whereismyai
Mcode Stack
Mcode Stack is an open source repository of workflows and skills that power MiniMax Code development.
Mcode Stack contains workflows, skills, and checklists that the MiniMax Code team uses daily to build MiniMax Code. It provides practical methods to manage AI-written code quality, decide on subagent tasks, handle long commands, and control context usage. Each piece installs directly into MiniMax Code as a skill or plugin using the common SKILL.md format. The catalog works in MiniMax Code and Claude Code, and is also compatible with other agents that support skills. It is designed for developers who want to improve their engineering habits around coding agents.
Mcode Stack at a glance
Key features
- Installs skills and checklists via SKILL.md format
- Provides subagent split checks for task management
- Audits tool costs and prompt cache context tax
- Offers long session and command audits
- Includes independent and code review skills
- Supports plugin installation and marketplaces
Use it for
- Decide whether work goes to a subagent or the main loop
- Split large features and refactors into small reviewable PRs
- Measure and trim tool costs in agent context
- Audit long shell commands and background tasks
- Review diffs and code health from a clean context
Companions
Tools that articles about Mcode Stack recommend using with it, each with its job.
- Context7 — Provides up-to-date documentation for AI agents and code editors.
- Ollama — Run local models at zero marginal cost, with code kept on your machine.
- OpenRouter — Access over 500 models and 80 providers through one unified API.
- Daytona — Runs sessions in isolated sandboxes synced to git branches.
- Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
- Oh My OpenCode Slim — Lightweight multi-agent orchestration and background tasks.
Alternatives to Mcode Stack
- codemax — Combines multiple paid AI coding plans into a single terminal to bypass usage limits.
- SmallCode — Runs fully local with budget-managed context and a forgiving parser for small models.
- pstack — Improves AI coding agent outcomes with rigorous workflows.
- OpenCode — Works with 75+ model providers, local models, and existing subscriptions
- jcode — Optimized for massive parallelism with low memory usage per session.
- P3 Stack — Native T3 orchestration with worktree threads and delegated subagents.
- mini-SWE-agent — It offers high performance with a simplified, minimal codebase.
- Supermaven — It uses a 1 million token context window for professional codebases.
- AGENTS.md — It separates agent-specific instructions from human-focused README files.
- Codebase Memory MCP — High-speed indexing and persistent knowledge graphs for AI coding agents.
- ZCode — Integrates GLM-5.3 with multi-agent workflows and remote chat control.
- Context Mode — Saves up to 98 percent of context per session by keeping raw data out of the LLM.
All Mcode Stack alternatives