minimax-cli-runtime

An internal instruction guide for a helper process that forwards tasks to the MiniMax runtime from Claude Code.

In plain words
What is it for?
Use it inside the specified rescue subagent for tasks such as diagnosis, planning, research, or requested code changes.
Why use it?
It defines how that helper should pass along requests and prevents it from doing unrelated work or using the wrong commands.

Skill for Claude CodeCodex

Part of the minimax plugin — 2 skills, 7 commands, 1 agent, 3 hooks shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/robbedoo/minimax-plugin-claude-code/minimax-cli-runtime
Any agent
npx skills add robbedoo/minimax-plugin-claude-code --skill minimax-cli-runtime
Clone the repo
git clone --depth 1 https://github.com/robbedoo/minimax-plugin-claude-code

Made for: Claude Code, Codex.

Or install minimax, the plugin that ships this one along with the rest of its 2 skills, 7 commands, 1 agent, 3 hooks.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 656 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.00656
Opus 5 $0.00010 $0.00328
Sonnet 5 $0.00004 $0.00131
Haiku 4.5 $0.00002 $0.00066

Measured 2d ago against content hash 48ee9d68f50a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

minimax-cli-runtime scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/minimax/skills/minimax-cli-runtime/SKILL.md · 42 lines

What it actually says

MiniMax Runtime

Use this skill only inside the minimax:minimax-rescue subagent.

Primary helper:

  • node "${CLAUDE_PLUGIN_ROOT}/scripts/minimax-companion.mjs" task "<raw arguments>"

Execution rules:

  • The rescue subagent is a forwarder, not an orchestrator. Its only job is to invoke task once and return that stdout unchanged.
  • Prefer the helper over hand-rolled git, direct API calls, or any other Bash activity.
  • Do not call setup, review, adversarial-review, status, result, or cancel from minimax:minimax-rescue.
  • Use task for every rescue request, including diagnosis, planning, research, and explicit fix requests.
  • Do not inspect the repo, solve the task yourself, or add independent analysis outside the forwarded prompt text.
  • Leave --effort unset unless the user explicitly requests a specific effort.
  • Leave model unset by default. Add --model only when the user explicitly asks for one.
  • Default to a write-capable MiniMax run by adding --write unless the user explicitly asks for read-only behavior or only wants review, diagnosis, or research without edits.

Command selection:

  • Use exactly one task invocation per rescue handoff.
  • If the forwarded request includes --background or --wait, treat that as Claude-side execution control only. Strip it before calling task, and do not treat it as part of the natural-language task text.
  • If the forwarded request includes --model, pass it through to task.
  • If the forwarded request includes --effort, pass it through to task.
  • If the forwarded request includes --resume, strip that token from the task text and add --resume-last.
  • If the forwarded request includes --fresh, strip that token from the task text and do not add --resume-last.
  • --resume: always use task --resume-last, even if the request text is ambiguous.
  • --fresh: always use a fresh task run, even if the request sounds like a follow-up.
  • --effort: accepted values are none, minimal, low, medium, high, xhigh.
  • task --resume-last: internal helper for "keep going", "resume", "apply the top fix", or "dig deeper" after a previous rescue run.

Safety rules:

  • Default to write-capable MiniMax work in minimax:minimax-rescue unless the user explicitly asks for read-only behavior.
  • Preserve the user's task text as-is apart from stripping routing flags.
  • Do not inspect the repository, read files, grep, monitor progress, poll status, fetch results, cancel jobs, summarize output, or do any follow-up work of your own.
  • Return the stdout of the task command exactly as-is.
  • If the Bash call fails or MiniMax cannot be invoked, return nothing.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 42 lines · 19 tokens per session scan A 48ee9d68f50a

Subscribe to this mod's changes

minimax-cli-runtime is a skill published in the GitHub repository robbedoo/minimax-plugin-claude-code (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 656 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

docs

Use when writing, editing, or organizing documentation, when planning what docs a feature needs, and whenever planning or implementing a new feature or change in a repo (docs ship with the code). Also use when tempted to write docs without showing the discovered readers to the user, without asking for tone, or without…

TanStack/ai · 118 tokens

rulesync

Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.

dyoshikawa/rulesync · 64 tokens

ponytail

Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports…

TanStack/ai · 138 tokens

emoji-storyteller

Retell the answer as a short story told mostly in emoji.

TanStack/ai · 18 tokens

agent-workspace-linux

Use when a task needs an isolated hidden Linux desktop or workspace-owned browser: GUI app QA, web/browser/shopping automation, sandboxed app observation, or stale workspace cleanup. Routes agent-workspace-linux MCP tools on demand. Does NOT apply to host desktop/Chrome control, generic MCP setup, or pure code/file…

ilysenko/codex-desktop-linux · 70 tokens

ss-component

Generate a new UI component following the StyleSeed design conventions.

bitjaru/styleseed · 14 tokens