MiniMax plugin for Claude Code
Use MiniMax from inside Claude Code for code reviews or to delegate tasks to MiniMax.
This plugin is for Claude Code users who want an easy way to start using MiniMax from the workflow
they already have.
What You Get
/minimax:review for a normal read-only MiniMax review/minimax:adversarial-review for a steerable challenge review/minimax:rescue, /minimax:status, /minimax:result, and /minimax:cancel to delegate work and manage background jobs
Requirements
- MiniMax API key.
- Set the
MINIMAX_API_KEY environment variable.
- Node.js 18.18 or later
Install
Add the marketplace in Claude Code:
/plugin marketplace add robbedoo/minimax-plugin-claude-code
Install the plugin:
/plugin install minimax@robbedoo-minimax
Reload plugins:
/reload-plugins
Then run:
/minimax:setup
/minimax:setup will tell you whether MiniMax is ready. It checks that MINIMAX_API_KEY is set and the API is reachable.
If MiniMax is not configured yet, export your API key:
export MINIMAX_API_KEY="your-api-key-here"
After install, you should see:
- the slash commands listed below
- the
minimax:minimax-rescue subagent in /agents
One simple first run is:
/minimax:review --background
/minimax:status
/minimax:result
Usage
/minimax:setup
Checks whether MiniMax is configured and the API is reachable.
You can also use /minimax:setup to manage the optional review gate.
Enabling review gate
/minimax:setup --enable-review-gate
/minimax:setup --disable-review-gate
When the review gate is enabled, the plugin uses a Stop hook to run a targeted MiniMax review based on Claude's response. If that review finds issues, the stop is blocked so Claude can address them first.
[!WARNING]
The review gate can create a long-running Claude/MiniMax loop and may drain usage limits quickly. Only enable it when you plan to actively monitor the session.
/minimax:review
Runs a normal MiniMax review on your current work. It gives you the same quality of code review as running a review inside MiniMax directly.
[!NOTE]
Code review especially for multi-file changes might take a while. It's generally recommended to run it in the background.
Use it when you want:
- a review of your current uncommitted changes
- a review of your branch compared to a base branch like
main
Use --base <ref> for branch review. It also supports --wait and --background. It is not steerable and does not take custom focus text. Use /minimax:adversarial-review when you want to challenge a specific decision or risk area.
Examples:
/minimax:review
/minimax:review --base main
/minimax:review --background
This command is read-only and will not perform any changes. When run in the background you can use /minimax:status to check on the progress and /minimax:cancel to cancel the ongoing task.
/minimax:adversarial-review
Runs a steerable review that questions the chosen implementation and design.
It can be used to pressure-test assumptions, tradeoffs, failure modes, and whether a different approach would have been safer or simpler.
It uses the same review target selection as /minimax:review, including --base <ref> for branch review.
It also supports --wait and --background. Unlike /minimax:review, it can take extra focus text after the flags.
Use it when you want:
- a review before shipping that challenges the direction, not just the code details
- review focused on design choices, tradeoffs, hidden assumptions, and alternative approaches
- pressure-testing around specific risk areas like auth, data loss, rollback, race conditions, or reliability
Examples:
/minimax:adversarial-review
/minimax:adversarial-review --base main challenge whether this was the right caching and retry design
/minimax:adversarial-review --background look for race conditions and question the chosen approach
This command is read-only. It does not fix code.
/minimax:rescue
Hands a task to MiniMax through the minimax:minimax-rescue subagent.
Use it when you want MiniMax to:
- investigate a bug
- try a fix
- continue a previous MiniMax task
- take a faster or cheaper pass with a smaller model
[!NOTE]
Depending on the task and the model you choose these tasks might take a long time and it's generally recommended to force the task to be in the background or move the agent to the background.
