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 madebyaris/advance-minimax-m3-cursor-rules --skill minimax-multimodal-toolkitgit clone --depth 1 https://github.com/madebyaris/advance-minimax-m3-cursor-rulesWrote 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/madebyaris/advance-minimax-m3-cursor-rules/minimax-multimodal-toolkit)<a href="https://agentmods.dev/skills/madebyaris/advance-minimax-m3-cursor-rules/minimax-multimodal-toolkit"><img src="https://agentmods.dev/badge/skills/madebyaris/advance-minimax-m3-cursor-rules/minimax-multimodal-toolkit/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/madebyaris/advance-minimax-m3-cursor-rules/minimax-multimodal-toolkit"><img src="https://agentmods.dev/badge/skills/madebyaris/advance-minimax-m3-cursor-rules/minimax-multimodal-toolkit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00097 | $0.01385 |
| Opus 5 | $0.00048 | $0.00692 |
| Sonnet 5 | $0.00019 | $0.00277 |
| Haiku 4.5 | $0.00010 | $0.00138 |
Grade A, and why
minimax-multimodal-toolkit 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 12d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MiniMax Multimodal Toolkit
Use MiniMax-native media workflows without bloating the always-on prompt. Route the task to the smallest path that can honestly produce the requested artifact.
When to Use
- The user asks for image, video, voice, speech, music, or multimodal asset generation
- The user explicitly mentions MiniMax media capabilities or wants MiniMax API integration
- The user wants reproducible local media outputs rather than only in-chat prose
- The task involves media conversion, trimming, concatenation, or extraction around generated assets
For deeper routing notes, output conventions, and implementation details, also read reference.md in this skill directory.
Step 0: Determine the Real Goal
Classify the task before acting:
- Direct asset generation: user wants an image, clip, narration, or music artifact
- Product integration: user wants app code that calls MiniMax media APIs
- Media pipeline work: user already has files and needs processing, conversion, or stitching
- Capability research: user wants comparison, planning, or API guidance before building
Do not jump into API integration when a direct generation path is enough.
Step 1: Route to the Right Path
| User need | Primary path | Notes |
|---|---|---|
| One-off image asset | Use the runtime's direct image-generation tool if available | Fastest path for explicit image requests |
| Video, TTS, voice, music, or MiniMax-specific generation | Use current MiniMax docs and the repo/runtime tool surface | Check auth and output path first |
| Existing media needs editing | Use local tooling such as FFmpeg when available | Avoid re-generation unless needed |
| App feature using MiniMax media APIs | Implement integration code and verify with a focused request or fixture | Prefer smallest vertical slice |
| Planning or research only | Gather current docs and synthesize | Do not implement prematurely |
| M3 input path: read an attached image / video frame as ground truth | Feed the file/frame into the model directly via the runtime's multimodal input — no separate "describe the image" step | Use for design parity, error UI triage, screenshot-driven dev. See the minimax-m3-multimodal-input skill for the full workflow. |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 136 lines · 97 tokens per session scan A 231a9d6d56e5
minimax-multimodal-toolkit is a skill published in the GitHub repository madebyaris/advance-minimax-m3-cursor-rules (125 stars, last pushed 2mo ago), licensed MIT. It adds 97 tokens to every session and 1,385 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
codex
Delegate coding tasks to the OpenAI Codex CLI for features, refactoring, PR reviews, and batch fixes. Requires the codex CLI and typically a git repository.
opencode
Delegate coding tasks to the OpenCode CLI for feature work, refactoring, PR review, and autonomous-style runs. Requires opencode installed where the agent can execute shell commands.
code-review
Use when asked to review code. Triggers - "look at this PR", "review this diff", "safe to merge?", change inspection. Input is a diff/branch/PR; output is a severity-ranked list of findings at file:line. If the job is to change code, use development.
debugging
Use when hunting the cause of a bug, error, or failing test — and before proposing any fix. Triggers - "why doesn't this work", stack traces, flaky failures, regressions ("worked yesterday"). Output is reproduce → root cause → minimal fix → regression test. If you already know the cause and just need the fix, use…
quick-tasks
Token-saving mode for everyday lightweight work. Use for one-line fixes, typo/config-value changes, quick questions ("what does this function do?"), throwaway scripts, and anything that ends inside a single file. Output is a minimal diff and a short report. For multi-file, design, or new-feature work, switch to the…
deepnote
DeepNote knowledge base: persistent interlinked markdown wiki with ingest, query, lint, link graph and history.