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 unknowlei/minimax-h3-opencode-skills --skill minimax-h3-prompt-reviewergit clone --depth 1 https://github.com/unknowlei/minimax-h3-opencode-skillsWrote 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/unknowlei/minimax-h3-opencode-skills/minimax-h3-prompt-reviewer)<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.
<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>- 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 | $0.00101 | $0.01641 |
| Opus 5 | $0.00051 | $0.00821 |
| Sonnet 5 | $0.00020 | $0.00328 |
| Haiku 4.5 | $0.00010 | $0.00164 |
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.
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.
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.
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.
- 13d ago First seen · 114 lines · 101 tokens per session scan A fd9ab502f3e1
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.
Other skills, from other repositories
seedance-prompt
This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.0 video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt.
multimodal-llm
Vision, audio, video generation, and multimodal LLM integration patterns. Use when processing images, transcribing audio, generating speech, generating AI video (Kling v3, Sora 2, Veo 3.1 std/lite/fast, Runway Gen-4.5 via gen4turbo), or building multimodal AI pipelines.
bootstrap
Bootstrap a greenfield project with parent-owned interviews and bounded plan, revision, and apply actions.
deep-research
Autonomous deep research on codebases and technical topics with structured report output via map-reduce explorer architecture.
mermaid
Create, validate, and repair Mermaid.js diagrams. Use when generating flowcharts, sequence, class, ER, state, or Gantt diagrams, or any visualization.
teach-me
Turn a 'teach me X' request into a single interactive HTML lesson, rendered Arcade-first, by emitting a lesson data model and assembling it with rp1 tooling.