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 teskor-hub/minimax-h3-skill --skill minimax-h3-reel-makergit clone --depth 1 https://github.com/teskor-hub/minimax-h3-skillWrote 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/teskor-hub/minimax-h3-skill/minimax-h3-reel-maker)<a href="https://agentmods.dev/skills/teskor-hub/minimax-h3-skill/minimax-h3-reel-maker"><img src="https://agentmods.dev/badge/skills/teskor-hub/minimax-h3-skill/minimax-h3-reel-maker/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/teskor-hub/minimax-h3-skill/minimax-h3-reel-maker"><img src="https://agentmods.dev/badge/skills/teskor-hub/minimax-h3-skill/minimax-h3-reel-maker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00065 | $0.01411 |
| Opus 5.5 | $0.00026 | $0.00564 |
| Sonnet 5.5 | $0.00013 | $0.00282 |
| Haiku 4.5 | $0.00006 | $0.00141 |
Grade A, and why
minimax-h3-reel-maker 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 1mo 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MiniMax H3: two reference workflows
Use the bundled graphs and preserve the user's intended scene, clothing, props, actions and audio requirements. This skill prepares a generative reconstruction, not a pixel-preserving face-swap. It does not authorize paid compute, uploads, installation, queue changes or messages to other people by itself.
Select the workflow without requesting unnecessary assets
- A source video is supplied and its motion/cuts should be reproduced: Ref + ControlNet, recorded as
control. Useassets/01_REF_CONTROLNET_TS.json. Keep depth, DWPose and TS Pose Keypoint Smoother. - No source video is supplied: Ref Only, recorded as
refs. Useassets/02_REF_ONLY.json. Work from available photos and the requested action. Do not ask for or require a source reel, pose video, depth maps, ControlNet, TS smoother or source audio. These nodes and source dependencies are absent from this graph. - An explicit mode choice overrides automatic selection. If the user supplies a clip but wants only its aesthetic, the clip need not become motion control. Do not turn a photos-only request into a reconstruction task.
Both workflows use H3 ref2va weights. They are preparation workflows, not separate checkpoints. Motion Strip and Hybrid are not defaults in this handoff.
Read workflows.md for models, dependencies, controls, alignment, installation and packaging. Read prompting.md before writing the full prompt. Recorded versions and test limits are in provenance.json.
Prepare the inputs
With a source clip: read its matching description, inspect dense frames across the full selected interval and inspect the audio. Use the description for intent and footage for evidence. Identify people, garments, props, room layout, opening/ending states, cuts, camera motion, facial acting and critical action beats. Resolve contradictions instead of silently simplifying the scene. If a meaningful description is missing, ask only for the missing intent; an explicit request to proceed from footage alone is sufficient.
What ships with it
12 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.
- .gitignore 23 B
- assets/01_REF_CONTROLNET_TS.json 52 KB
- assets/02_REF_ONLY.json 25 KB
- assets/prompt_structure.txt 603 B
- LICENSE 1.0 KB
- references/prompting.md 4.4 KB
- references/provenance.json 1.2 KB
- references/workflows.md 10 KB
- scripts/check_prompt_dialogue.py 4.1 KB runs code
- scripts/configure_workflow.py 10 KB runs code
- scripts/pose_smoother.py 8.3 KB runs code
- scripts/workflow_api.py 17 KB runs code
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.
- 1mo ago First seen · 48 lines · 65 tokens per session scan A b37256e83752
minimax-h3-reel-maker is a skill published in the GitHub repository teskor-hub/minimax-h3-skill (16 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 1,411 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-20.
Other skills, from other repositories
seedance-shotlist-director
Generate a director's shotlist as an editable HTML production board for Seedance 2.0. Use whenever the user provides a script, scene breakdown, story idea, or treatment to turn into a numbered shotlist with English Seedance prompts — trigger on "make a shotlist", "director’s shotlist", "break this script into…
seedance-storyboard
A storyboard-writing guide that turns a story, script, or scene description into prompts for Seedance and similar AI video tools. It sets the overall visual style and breaks the action into timed shots with camera movement.
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
higgsfield-cinema
Guides users through professional filmmaking workflows in Higgsfield Cinema Studio, including creating multi-shot sequences, configuring optical stacks, applying color grading, managing Soul Cast AI actors, and structuring per-scene prompts with Director Panel camera movements. Use when the user mentions Cinema…
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…
higgsfield-audio
Use when the user asks about audio in Higgsfield videos, needs to add dialogue or lip-sync, wants sound effects or ambient sound in generated video, asks about music or BGM in output, or is using any audio-capable model (Kling 3.0, Seedance 1.5 Pro, Seedance 2.0, Veo 3/3.1, Grok Video / Grok Imagine). Also use when…