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.
npx skills add CHENyiru3/AI-Skills-Collections --skill minimax-cligit clone --depth 1 https://github.com/CHENyiru3/AI-Skills-CollectionsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chenyiru3/ai-skills-collections/minimax-cli)<a href="https://agentmods.dev/skills/chenyiru3/ai-skills-collections/minimax-cli"><img src="https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/minimax-cli/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chenyiru3/ai-skills-collections/minimax-cli"><img src="https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/minimax-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00081 | $0.02240 |
| Opus 5.5 | $0.00032 | $0.00896 |
| Sonnet 5.5 | $0.00016 | $0.00448 |
| Haiku 4.5 | $0.00008 | $0.00224 |
Grade A, and why
minimax-cli 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MiniMax CLI
Use mmx for MiniMax's multimodal command-line workflows: text, image, video, speech, music, vision, search, quota, and configuration. Prefer this skill when the user wants a direct MiniMax result from the terminal or wants MiniMax wired into an agent workflow.
Prerequisites
- Node.js 18+.
- CLI installed:
npm install -g mmx-cli
mmx --version
- Authentication configured with a MiniMax token plan:
mmx auth login --method api-key --api-key sk-xxxxx
mmx auth status
mmx quota
MiniMax keys are region-specific. If mmx quota reports invalid api key, check whether the account belongs to the CN platform:
mmx config set --key region --value cn
mmx quota
Global defaults use https://api.minimax.io; CN defaults use https://api.minimaxi.com.
Safety And Secret Handling
- Do not print or paste full API keys in final answers, logs, docs, commits, or examples.
- Prefer persistent config (
~/.mmx/config.json) or environment variables over putting keys in shell history. - Use
mmx config showandmmx auth statusfor masked verification. - Use
--dry-runwhen constructing expensive media commands before execution. - For long-running or costly video/music work, confirm prompt, model, output path, and whether the user wants synchronous waiting or async task IDs.
Command Selection
| User intent | Command family | Good default |
|---|---|---|
| Chat, coding text, structured text | mmx text chat |
--message, optional --system, --output json for parsing |
| Text-to-image | mmx image generate |
--prompt, --aspect-ratio, --out or --out-dir |
| Text/image-to-video | mmx video generate |
--prompt, optional --first-frame, --download, --async |
| Video task status/download | mmx video task get, mmx video download |
Use task IDs and file IDs from earlier output |
| Text-to-speech | mmx speech synthesize |
--text or --text-file, --voice, --out |
| Voice list | mmx speech voices |
Filter with --language |
| Music generation | mmx music generate |
Require lyrics, --lyrics-file, --lyrics-optimizer, or --instrumental |
| Music cover | mmx music cover |
--audio or --audio-file, --prompt, optional lyrics |
| Image understanding | mmx vision describe |
--image, optional question via --prompt |
| Web search | mmx search query |
--q, use --output json for downstream parsing |
| Usage/budget | mmx quota or mmx quota show |
Use before expensive media generation |
| Tool schema export | mmx config export-schema |
Use for agent/tool integration |
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.
- 6d ago First seen · 229 lines · 81 tokens per session scan A 80f6572e690f
minimax-cli is a skill published in the GitHub repository CHENyiru3/AI-Skills-Collections (1 stars, last pushed 7d ago), licensed MIT. It adds 81 tokens to every session and 2,240 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-02.
Other skills, from other repositories
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
duckduckgo-search
Free keyless web, news, and image search via ddgs.
mcporter
List, auth, and call MCP servers/tools from the terminal.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
safe-refactor
Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.