minimax-h3-prompt-reviewer

minimax-h3-prompt-reviewer is a skill for Codex from unknowlei/minimax-h3-opencode-skills. It costs 101 tokens per session (1,641 once invoked), scanned A, original, MIT.

A reviewer and repair tool for MiniMax H3 video-generation prompts. It checks prompts against the required format for text-to-video, image-to-video, and reference-based modes, then rewrites them when needed.

In plain words
What is it for?
Audit and repair prompts involving video generation, image-to-video conversion, first- or last-frame workflows, and full-reference video generation.
Why use it?
Free-form prompts can miss required structure or use the wrong mode. The reviewer identifies those problems and returns a corrected prompt in the official format.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex; mentions OpenCode.

Good fit Audit and repair prompts involving video generation, image-to-video conversion, first- or last-frame workflows, and full-reference video generation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/unknowlei/minimax-h3-opencode-skills/minimax-h3-prompt-reviewer
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 unknowlei/minimax-h3-opencode-skills --skill minimax-h3-prompt-reviewer
Clone the repo
git clone --depth 1 https://github.com/unknowlei/minimax-h3-opencode-skills

Made for: Codex.

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-prompt-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/unknowlei/minimax-h3-opencode-skills/minimax-h3-prompt-reviewer/github.svg)](https://agentmods.dev/skills/unknowlei/minimax-h3-opencode-skills/minimax-h3-prompt-reviewer)
Your own site
<a href="https://agentmods.dev/skills/unknowlei/minimax-h3-opencode-skills/minimax-h3-prompt-reviewer"><img src="https://agentmods.dev/badge/skills/unknowlei/minimax-h3-opencode-skills/minimax-h3-prompt-reviewer/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-prompt-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/skills/unknowlei/minimax-h3-opencode-skills/minimax-h3-prompt-reviewer"><img src="https://agentmods.dev/badge/skills/unknowlei/minimax-h3-opencode-skills/minimax-h3-prompt-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,641 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 $0.00101 $0.01641
Opus 5 $0.00051 $0.00821
Sonnet 5 $0.00020 $0.00328
Haiku 4.5 $0.00010 $0.00164

Measured 13d ago against content hash fd9ab502f3e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

minimax-h3-prompt-reviewer 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 13d 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.

skills/minimax-h3-prompt-reviewer/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MiniMax H3 Prompt Reviewer

Review the supplied prompt against MiniMax H3's base or full-reference format, then repair it. Do not stop at critique when a corrected prompt can be produced.

Routing Contract

New MiniMax H3 requests should enter through minimax-h3-creative-director. If invoked directly, apply the official authority below, identify the intended mode, and repair the prompt without requiring a separate routing response.

Official Format Authority

Before reviewing, read ../h3-prompt-writing/SKILL.md, then read ../h3-prompt-writing/references/base-en.txt for T2VA/I2VA/FL2VA/L2VA or ../h3-prompt-writing/references/ref-en.txt for Ref2VA. Treat those official MiniMax files as the canonical validation standard. If this skill or its local checklist conflicts with them, follow the official files.

Read references/validation-checklist.md before reviewing.

Mandatory Format

Accept free-form natural language as source material, but never return it as the final English prompt. Convert every task into exactly one official format:

  • Base T2VA/I2VA/FL2VA/L2VA -> mode alignment instruction when applicable plus the three core fields
  • Full-reference generation/editing/continuation -> the six required sections in order

Interactive Direction Check

Before repairing, use the host's structured-choice tool when the prompt is sparse, two or more major creative axes are missing, the intended preservation/result cannot be determined reliably, or the user asks the AI to decide or improvise the direction. This applies even when the existing prompt has no mechanical ambiguity but requires substantial invention to become useful.

In OpenCode, call the built-in question tool instead of printing Markdown options. In Codex, use the available structured user-input tool; if unavailable, ask one concise plain-text question.

Ask as many related questions as the current review stage requires; normally 1-5, but three is not a per-call, per-turn, or per-session ceiling. A strict yes/no question may contain exactly two options; every other choice question must contain at least five materially different, feasible options. Put the context-specific recommendation first with (Recommended), explain each choice in one sentence, omit Other, and use multiple selection only for combinable decisions. Before every question tool call, count the options in the actual payload. If any non-binary choice has fewer than five, do not submit it; expand it with meaningful alternatives or make it open-ended. Do not create near-duplicates merely to reach five.

Read the full file on GitHub · 114 lines

Files

What ships with it

2 files 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. 13d ago First seen · 114 lines · 101 tokens per session scan A fd9ab502f3e1

Subscribe to this mod's changes

minimax-h3-prompt-reviewer is a skill published in the GitHub repository unknowlei/minimax-h3-opencode-skills (112 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 1,641 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.