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-multishot-plannergit 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-multishot-planner)<a href="https://agentmods.dev/skills/unknowlei/minimax-h3-opencode-skills/minimax-h3-multishot-planner"><img src="https://agentmods.dev/badge/skills/unknowlei/minimax-h3-opencode-skills/minimax-h3-multishot-planner/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-multishot-planner"><img src="https://agentmods.dev/badge/skills/unknowlei/minimax-h3-opencode-skills/minimax-h3-multishot-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 68 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00120 | $0.01861 |
| Opus 5 | $0.00060 | $0.00931 |
| Sonnet 5 | $0.00024 | $0.00372 |
| Haiku 4.5 | $0.00012 | $0.00186 |
Grade A, and why
minimax-h3-multishot-planner 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MiniMax H3 Multishot Planner
Plan a confirmed multishot video before the text, keyframe, or full-reference specialist writes the executable H3 prompt. Produce a structured shot plan, not the final H3 prompt.
Execution Is Mandatory After Loading
The skill tool only loads these instructions. Loading this Skill is not execution and is never a successful handoff by itself.
After this Skill is loaded:
- Do not load any final H3 specialist.
- Do not draft an H3 prompt.
- Ask or confirm shot count.
- Question the user about Shot 1, confirm it, then repeat for Shot 2 and every remaining shot.
- Build and confirm the complete
multishot_plan. - Return control to the director only after final confirmation.
No final specialist may run while any planned shot remains unasked or unconfirmed.
Invocation Contract
Enter only through minimax-h3-creative-director:
- Enter immediately when the user explicitly requests multiple shots, scenes, cuts, a montage, a sequence, or shot-by-shot planning.
- When effective duration is at least 10 seconds and the user has not chosen single-shot or multishot, let the director ask a binary multishot question. Enter only after the user accepts.
- Do not enter when the user explicitly requests one continuous shot, one take, no cuts, or an equivalent single-shot treatment.
- Do not enter merely because a prompt contains several actions. A continuous action arc can remain one shot.
- Do not choose T2VA, I2VA, FL2VA, L2VA, or Ref2VA here.
If duration is unknown, return control to the director to resolve duration before applying the 10-second gate.
Choice Source
Consult references/shot-choice-library.md for shot vocabulary and option design. Do not treat it as an official closed vocabulary or insert every available term.
Question Payload Rules
OpenCode does not impose a three-question workflow limit. Use the number of questions required by each state below.
- 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 strongest context-specific recommendation first and append
(Recommended)to its label. - Explain the creative consequence of every option in one concise sentence.
- Keep every option label within five words; place detail in its description.
- Do not add
Other; OpenCode supplies custom input automatically. - Do not pad a list with near-duplicates. If five meaningful choices cannot be produced, ask an open-ended question instead of a choice question.
- Generate content and performance choices from the user's actual subject, assets, genre, duration, and desired outcome. Never present generic placeholders.
- Use multiple selection only when choices can genuinely coexist.
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.
- 12d ago First seen · 166 lines · 120 tokens per session scan A 80cdb60f3c02
minimax-h3-multishot-planner is a skill published in the GitHub repository unknowlei/minimax-h3-opencode-skills (112 stars, last pushed 1mo ago), licensed MIT. It adds 120 tokens to every session and 1,861 once invoked, about $0.0006 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.
open-video
Generate, edit, or direct videos via open-source models (MiniMax H3 baseline; Wan2.2 / LTX future). Use when the user wants to turn a concept, script, or reference image into a finished video or multi-shot film — single shots, image-to-video, first-last-frame interpolation, reference-video/audio styling, or stitched…
minimax-h3
Write, debug and structure prompts for MiniMax H3 video generation (T2VA, I2VA, FL2VA, L2VA, Ref2VA) and configure its ComfyUI workflow. Use when the user mentions MiniMax H3, minimaxh3, fl2va, ref2va, MiniMaxH3ReferenceToVideo, reference-to-video, asks to animate a photo, write a video prompt, pick a model quant, or…
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.
processon-diagram-generator
A skill for creating PowerPoint presentations by planning slides, generating an image for each slide, and assembling those images into a PPTX file. It supports several predefined visual styles.