[Agent]: Add support for MiniMax Code (mcode)

PR #4645 already contains the proposed integration, tests, and documentation. Review that pull request first, then use mcode --help and mcode exec --help to verify the documented entry points and inspect the .minimax/skills/<skill-name>/SKILL.md structure. Done means specify init --integration mcode supports the documented MiniMax Code workflow.

Agent Name

MiniMax Code

Official Website

https://github.com/MiniMax-AI/minimax-code

Agent Type

CLI tool (command-line interface)

CLI Command (if applicable)

mcode

Installation Method

Official installer, or npm:

npm install -g @minimax-ai/code@latest --registry=https://registry.npmjs.org/ --ignore-scripts=false --include=optional --allow-scripts=@minimax-ai/code,better-sqlite3

Command/Workflow Structure

• Agent Skills format (SKILL.md in skill subdirectories)
• Directory location: .minimax/skills/<skill-name>/SKILL.md
• Invocation: /speckit-<command> (via slash shortcut)

Argument Passing Pattern

MiniMax Code accepts free-form instructions after the skill slash command:

/<skill-name> [instructions]

Spec Kit's SkillsIntegration renders the existing $ARGUMENTS placeholder into generated SKILL.md content.

Popularity/Usage

Growing adoption (hundreds of users)

Documentation Links

• Repository: https://github.com/MiniMax-AI/minimax-code
• CLI Reference: mcode --help, mcode exec --help

Use Case

MiniMax Code is a terminal coding agent built with native support for Agent Skills in .minimax/skills. Adding first-class support in Spec Kit enables users of MiniMax Code to adopt Spec-Driven Development workflows seamlessly via specify init --integration mcode.

Example Command File

---
name: speckit-plan
description: Execute the implementation plan workflow
---

# Plan Skill
Execute the planning workflow with $ARGUMENTS.

Contribution

• I can help test the integration
• I can provide example command files
• I can help with documentation
• I can submit a pull request for the integration

Additional Context

PR #4645 with full integration, tests, and documentation has been submitted.

AI Disclosure

Prepared with AI assistance. ChatGPT (GPT-5.6 Sol) was used to review the integration design, validate the Spec Kit and MiniMax Code architecture, and identify the relevant integration surfaces. Antigravity (Gemini 3.8 Flash, High, autonomous) was used during implementation and test/documentation authoring.