minimax-h3

minimax-h3 is a skill for Claude Code from SlavaSexton/ComfyUI-Agent-Kit. It costs 102 tokens per session (2,475 once invoked), scanned A, original, Apache-2.0.

Prompting instructions for MiniMax H3, a model that generates video and matching stereo audio from text, images, video, audio, or combinations of them. It can be accessed through a hosted service or run locally in ComfyUI.

In plain words
What is it for?
Writing prompts, debugging generated clips, choosing local model versions for available graphics memory, and building reference-to-video workflows.
Why use it?
They help select the right setup and reduce problems such as unclear speech or the video drifting away from its references.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the comfyui plugin — 4 skills, 1 MCP server shipped together

Good fit Writing prompts, debugging generated clips, choosing local model versions for available graphics memory, and building reference-to-video workflows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/slavasexton/comfyui-agent-kit/minimax-h3
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.

Any agent
npx skills add SlavaSexton/ComfyUI-Agent-Kit --skill minimax-h3
Clone the repo
git clone --depth 1 https://github.com/SlavaSexton/ComfyUI-Agent-Kit

Made for: Claude Code.

Or install comfyui, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

Wrote 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.

agentmods badge for minimax-h3

README.md
[![agentmods](https://agentmods.dev/badge/skills/slavasexton/comfyui-agent-kit/minimax-h3/github.svg)](https://agentmods.dev/skills/slavasexton/comfyui-agent-kit/minimax-h3)
Your own site
<a href="https://agentmods.dev/skills/slavasexton/comfyui-agent-kit/minimax-h3"><img src="https://agentmods.dev/badge/skills/slavasexton/comfyui-agent-kit/minimax-h3/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.

agentmods 80×15 button for minimax-h3

Your own site · 80×15
<a href="https://agentmods.dev/skills/slavasexton/comfyui-agent-kit/minimax-h3"><img src="https://agentmods.dev/badge/skills/slavasexton/comfyui-agent-kit/minimax-h3.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,475 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00102 $0.02475
Opus 5 $0.00051 $0.01238
Sonnet 5 $0.00020 $0.00495
Haiku 4.5 $0.00010 $0.00248

Measured 10d ago against content hash 6f0203b47e89, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

minimax-h3 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 10d 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.

claude-code/skills/minimax-h3/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MiniMax H3 (Hailuo 3)

H3 generates video and synchronised stereo audio jointly, from text, images, reference video, reference audio, or any mix. It is the same model family whether you hit the hosted API or run the open weights, but the two paths are wired completely differently and only one of them is free.

Two paths, do not confuse them.

  • Hosted API, partner nodes MinimaxHailuo03TextToVideoNode / ...FirstLastFrameNode / ...ReferenceNode, category partner/video/MiniMax. 2K output, priced per second, no local weights.
  • Local open weights, core nodes MiniMaxH3ImageToVideo and MiniMaxH3ReferenceToVideo from comfy_extras/nodes_minimax_h3.py. 768p, free, and everything below is about this path.

Who owns what, so you open one file, not three. THIS file owns the prompt format and the operating rules. reference.md next to it owns weights, quant sizes, acceleration packs and their wiring. The MiniMax entry in the kit's MODELS.md owns the node-level graph (every node and socket) and the licence. When they disagree, the node code wins and the discrepancy is a bug worth reporting.

The prompt format is not free-form prose

H3-Base consumes the output of a hosted prompt refiner (H3-Context-IR) that is not in the open release. So locally you write in the refiner's output shape yourself. From MiniMax's own VIDEO_PROMPT_WRITING_GUIDE_base_en.md, that is an optional instruction line, a blank line, then three fields:

integrated_multimodal_description: [Shot 1] ... [Shot 2] At 00:04.500, ...

overall_soundscape: ...

non_diegetic_music: ...
  • integrated_multimodal_description carries visuals, action, shots, speakers, dialogue and diegetic sound along the timeline. overall_soundscape sums ambience and physical-action sound. non_diegetic_music is score the characters cannot hear.
  • Image modes need a fixed first line. I2V: For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced. First-and-last-frame uses the alignment sentence naming both pictures and the second each lands on, to two decimals.

Read the full file on GitHub · 161 lines

Files

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.

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. 10d ago First seen · 161 lines · 102 tokens per session scan A 6f0203b47e89

Subscribe to this mod's changes

minimax-h3 is a skill published in the GitHub repository SlavaSexton/ComfyUI-Agent-Kit (94 stars, last pushed 6d ago), licensed Apache-2.0. It adds 102 tokens to every session and 2,475 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.

Related

Other skills, from other repositories

cinematic-frame-director

Turn a user's idea, scene description, or mood into ONE production-grade cinematic still-image prompt in English for text-to-image models (Seedream, Midjourney, Flux, DALL-E, or any image generator). Use this skill whenever the user asks for an image prompt, a cinematic frame, a "movie still" look, a photorealistic…

artnebo/cinematic-frame-director · 156 tokens

flux-txt2img

Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns.

artokun/comfyui-mcp · 44 tokens

prompt-engineering

ComfyUI prompt engineering knowledge covering CLIP text encoding syntax, weight modifiers, model-specific prompting strategies, and best practices.

artokun/comfyui-mcp · 28 tokens

higgsfield-seedance

Rewrites scene descriptions using professional cinematography language, structures prompts with a six-slot formula (camera + subject + action + setting + style + lighting), and diagnoses content filter rejections via a preflight linter. Use whenever the user asks for a Seedance 2.0 / Seedance Pro prompt, describes a…

OSideMedia/higgsfield-ai-prompt-skill · 100 tokens

higgsfield-prompt

Use when building, writing, refining, or structuring a Higgsfield AI prompt. Covers the MCSLA formula, prompt structure, narrative vs. timestamped formats, and how to write for both text-to-video and image-to-video workflows.

OSideMedia/higgsfield-ai-prompt-skill · 56 tokens

higgsfield-seedance-2-5

Seedance 2.5 prompt director — the omni-reference dialect. Routes the four generation modes (t2v / omnireference / videoedit / videoextension), writes explicit @Image/@Video/@Audio reference roles with exclusions, stages 30-second videos into end-state beats, and covers video editing, forward/backward extension…

OSideMedia/higgsfield-ai-prompt-skill · 191 tokens