Home / cherryhq / cherry-studio · resources/code-cli-skills/code-mate-minimax-code/SKILL.md · GitHub

code-mate-minimax-code skillA

code-mate-minimax-code is agent-read markdown (skill) from cherryhq/cherry-studio: Runs MiniMax Code headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to MiniMax Code or obtain a MiniMax-based coding-agent result..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# MiniMax Code

## Run

1. Set the Bash working directory to the exact project the user named and set a finite timeout, normally 10 minutes.
2. Check availability with `command -v mcode`. If it is missing, stop and ask the user to install MiniMax Code in Code Mate.
3. Run one task and exit:

```bash
mcode exec "<prompt>"
```

Pass the prompt as one quoted argument. For analysis-only tasks pass `--permission smart` explicitly; never pass `--permission full`. Treat a nonzero exit as failure, and treat the final answer text as the result. Never start the interactive TUI or login flow from the agent task.

## Authentication And Permissions

If MiniMax Code reports missing login, API key, model, or provider configuration, stop and ask the user to configure MiniMax Code in Code Mate. Never request, read, print, or copy credentials.

Only allow modification tools when the user explicitly requests workspace changes, and prefer read-only instructions in the prompt otherwise. Never pass a flag or setting that relaxes the permission mode.
…

Read the whole file at its exact version.

How to install

Latest version
mdr add cherryhq/cherry-studio/code-mate-minimax-code@git:20260921.c3eda0c
Exact content
mdr add cherryhq/cherry-studio/code-mate-minimax-code@sha256:dafe696e2cffbb60

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_y2qv5kbgs4256frk.svg)](https://markdownregistry.com/a/art_y2qv5kbgs4256frk)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260921.c3eda0c latest2026-09-21 c3eda0c 1,428 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (1428 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

cherryhq/cherry-studio · 52,106 stars · license AGPL-3.0 · pushed 2026-09-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_y2qv5kbgs4256frk
GET https://markdownregistry.com/api/v1/resolve?ref=cherryhq/cherry-studio/code-mate-minimax-code
GET https://markdownregistry.com/api/v1/blob/dafe696e2cffbb60aa05e5e79cbbc16b24ee20d7ac09c8b5d8fd01739a280acc

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from cherryhq/cherry-studio

cherry-electron-dev skill
cherryhq/cherry-studio · .agents/skills/cherry-electron-dev/SKILL.md · Develop, fix, and profile Cherry Studio in a tracked Electron instance. Use for everyday implementation, UI and…
git:20260726.fcf8648 · audit A · 52,106 stars
cherry-pr-test skill
cherryhq/cherry-studio · .agents/skills/cherry-pr-test/SKILL.md · Test Cherry Studio PRs by resolving and checking out a PR, statically inspecting its changes, running interactive UI…
git:20260726.fcf8648 · audit A · 52,106 stars
cherry-regression-test skill
cherryhq/cherry-studio · .agents/skills/cherry-regression-test/SKILL.md · Run Cherry Studio critical-path system regression tasks through the repository-owned Playwright E2E workflow. Use for…
git:20260922.bdd4113 · audit A · 52,106 stars
create-skill skill
cherryhq/cherry-studio · .agents/skills/create-skill/SKILL.md · Create a new skill in the current repository. Use when the user wants to create/add a new skill, or mentions creating a…
git:20260316.fe0678a · audit A · 52,106 stars
gh-create-issue skill
cherryhq/cherry-studio · .agents/skills/gh-create-issue/SKILL.md · Use when user wants to create a GitHub issue for the current repository. Must read and follow the repository's issue…
git:20260822.5f660de · audit A · 52,106 stars
gh-create-pr skill
cherryhq/cherry-studio · .agents/skills/gh-create-pr/SKILL.md · Create or update GitHub pull requests using the repository-required workflow and template compliance. Use when asked to…
git:20260827.4a5f580 · audit A · 52,106 stars
gh-pr-review skill
cherryhq/cherry-studio · .agents/skills/gh-pr-review/SKILL.md · Automated Cherry Studio review for local branches, PRs, commits, files, architecture docs, and repository skills. Use…
git:20260903.2c65c71 · audit A · 52,106 stars
prepare-release skill
cherryhq/cherry-studio · .agents/skills/prepare-release/SKILL.md · Prepare a new release by collecting commits, generating bilingual release notes, updating version files, and creating a…
git:20260921.38beb60 · audit A · 52,106 stars
AGENTS.md@.agents/skills/vercel-react-best-practices agents
cherryhq/cherry-studio · .agents/skills/vercel-react-best-practices/AGENTS.md
git:20260316.6eb461d · audit B · 52,106 stars
vercel-react-best-practices skill
cherryhq/cherry-studio · .agents/skills/vercel-react-best-practices/SKILL.md · React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing…
v1.0.0 · audit A · 52,106 stars
AGENTS.md agents
cherryhq/cherry-studio · AGENTS.md
git:20250914.3fc92e0 · audit B · 52,106 stars
CLAUDE.md claude
cherryhq/cherry-studio · CLAUDE.md
git:20260916.da37142 · audit A · 52,106 stars

Every file in cherryhq/cherry-studio

Browse by kind, by grade A, or by owner.