minimax-h3-skill: Instructions file for Claude Code

CLAUDE.md

minimax-h3-skill CLAUDE.md is an instructions file for Claude Code from teskor-hub/minimax-h3-skill. It costs 2,497 tokens per session, scanned A, original, MIT.

A Claude Code skill and portable prompts for writing prompts and setting up ComfyUI for MiniMax H3, an open-weight video model that also generates stereo audio.

In plain words
What is it for?
Creating MiniMax H3 video prompts, configuring its ComfyUI workflow, and using the guidance in other chat tools.
Why use it?
It collects model-specific guidance and documents known failure cases, so users do not have to reconstruct the setup and prompting approach themselves.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is teskor-hub/minimax-h3-skill's own configuration. It tells Claude Code how to work on minimax-h3-skill itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything minimax-h3-skill configures →

Reuse

Borrowing it

Nothing to install: this file belongs to teskor-hub/minimax-h3-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/teskor-hub/minimax-h3-skill/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/teskor-hub/minimax-h3-skill

Made for: Claude Code.

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-skill CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/teskor-hub/minimax-h3-skill/claude-md/github.svg)](https://agentmods.dev/instructions/teskor-hub/minimax-h3-skill/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/teskor-hub/minimax-h3-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/teskor-hub/minimax-h3-skill/claude-md/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-skill CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/teskor-hub/minimax-h3-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/teskor-hub/minimax-h3-skill/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,497 This file is loaded in full into every session.
When invoked 2,497 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.02497 $0.02497
Opus 5 $0.01248 $0.01248
Sonnet 5 $0.00499 $0.00499
Haiku 4.5 $0.00250 $0.00250

Measured 10d ago against content hash 0e00b688ad0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

minimax-h3-skill CLAUDE.md 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.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MiniMax H3 skill — working notes

What this is

A Claude Code skill (plus two portable chat prompts) that teaches prompt-writing and ComfyUI setup for MiniMax H3 — an open-weight, omni-modal video model that generates video and native stereo audio in one forward pass, at 24 fps, over a trained clip length of ~124–362 frames. It ships as two separate checkpoints, fl2va (frame-conditioned) and ref2va (reference-conditioned). The skill is built on MiniMax's own prompt-writing guides, plus the failure modes those guides don't cover.

This repo is documentation. There is nothing to build, run, or test — the "product" is the prose in SKILL.md, references/, portable-prompt.md and reels-portable-prompt.md, and the one script in tools/.

After every edit: hand over the push commands

The git repo with origin (teskor-hub/minimax-h3-skill) lives on the PC, at D:\claude\minimax-h3-skill. The VPS copy has no remote — nothing can be pushed from there. So the last thing every editing session does is:

  1. Copy the changed files to the PC over the tunnel (scp -O -T -i ~/.ssh/vps_to_pc -P 2222 <file> [email protected]:'D:\claude\minimax-h3-skill\<file>').

  2. End the reply with a ready-to-paste command block the user runs on the PC — cd, git add naming exactly the files that changed, git commit -m, git push. One block, nothing to edit by hand, no commentary inside it.

    The shell is Windows PowerShell 5.1, not git-bash. No &&, no trailing \ line continuations — they are parse errors there. Write one command per line, backslash paths, and let PowerShell run the lines in order. Always include the cd, or git runs in C:\Users\win10 and fails with not a git repository.

Don't commit or push on the user's behalf; hand over the commands.

Where things live

  • Source of truth: this repo, /workspaces/usual/minimax-h3-skill — git, remote teskor-hub/minimax-h3-skill, branch main.
  • Installed copy: /root/.claude/skills/minimax-h3 — what Claude Code actually loads. Currently byte-identical to this repo. After editing SKILL.md, references/, or tools/, re-sync the installed copy (git pull / re-clone / copy) or the running skill is stale.
  • This session's cwd /workspaces/h3 minimax is an empty scratch dir, not the project.

Read the full file on GitHub · 163 lines

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 · 163 lines · 2,497 tokens per session scan A 0e00b688ad0f

Subscribe to this mod's changes

minimax-h3-skill CLAUDE.md is an instructions file published in the GitHub repository teskor-hub/minimax-h3-skill (8 stars, last pushed 2d ago), licensed MIT. It adds 2,497 tokens to every session, about $0.0125 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 instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens