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 calesthio/generative-media-skills --skill midjourney-videogit clone --depth 1 https://github.com/calesthio/generative-media-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/calesthio/generative-media-skills/midjourney-video)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/midjourney-video"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/midjourney-video/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/calesthio/generative-media-skills/midjourney-video"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/midjourney-video.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 | $0.00082 | $0.05162 |
| Opus 5 | $0.00041 | $0.02581 |
| Sonnet 5 | $0.00016 | $0.01032 |
| Haiku 4.5 | $0.00008 | $0.00516 |
Grade A, and why
midjourney-video 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 9d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Midjourney Video
Treat Midjourney Video as a human-operated creative service, not a developer API. Prepare inputs, motion direction, settings, budget, and acceptance criteria; then hand the approved plan to the subscribed account owner for manual execution on midjourney.com or in Discord.
Keep the interface boundary absolute
As of 2026-07-10, Midjourney's official Community Guidelines say it does not provide an API except for rare explicitly granted exceptions and prohibits automated tools, third-party scripts, and automated interaction. The current Terms also prohibit automated access and one account may be used by only one person.
Therefore:
- Do not write or run browser automation, Discord self-bots, reverse-engineered HTTP calls, cookie/token replay, scraping, queued submission scripts, or unofficial “Midjourney API†clients.
- Do not ask for account credentials, session cookies, Discord tokens, or remote control of the user's session.
- Do not call a third-party gateway an official Midjourney API. Do not send content to one without separate user approval and a terms/privacy review.
- Do not promise unattended backend integration, webhooks, deterministic job submission, programmatic seeds, or an SLA.
- Route requirements for supported programmatic generation to a provider with a documented public API. Use this skill only for planning and a manual operator handoff unless the customer can show an explicit written Midjourney automation exception.
Never perform the manual UI steps yourself. A human operator must inspect the account state, approve the visible GPU-time impact, submit the job, choose candidates, extend, and download.
Treat that manual execution as a revision-bound authorization, not delegated autonomy. Freeze the exact handoff text, input hashes, settings, prompt, submission count, and Fast-minute cap before approval. Approval covers only that revision and those listed submissions. Any operator edit, changed account state, extra variation or extension, visibility mismatch, or undocumented UI behavior voids the approval and requires a new handoff.
What ships with it
1 file 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.
- 9d ago First seen · 276 lines · 82 tokens per session scan A 733527204ceb
midjourney-video is a skill published in the GitHub repository calesthio/generative-media-skills (171 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 5,162 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
cliptalk-cover-director
Produces evidence-backed cover candidates and reviewable cover variants for a ClipTalk video. Use when the user asks for a cover, poster frame, thumbnail, or multiple cover directions; do not use for timeline editing or social-video reframing.
cliptalk-smart-reframe
Creates a subject-aware, time-varying crop track and a review-only social-format preview from an accepted ClipTalk cut. Use for automatic vertical, square, or portrait reframing; do not use for a fixed manual crop or before content editing is accepted.
cliptalk-content-extractor
Locates and assembles source passages matching a semantic request. Use for extracting explanations, topics, quotes, demonstrations, or other specifically described content.
cliptalk-interview-editor
Produces a coherent interview edit by combining speaker discovery, topic selection, dialogue context, cleanup, subtitles, and preview. Use for interviews, podcasts, testimonials, or question-and-answer recordings.
cliptalk-shortform-hook-director
Finds and assembles a reviewable short-form cut with a strong opening hook. Use for Shorts, Reels, social clips, talking-head cutdowns, or requests for a punchier opening.
cliptalk-social-reframe-exporter
Creates a review-only 9:16, 4:5, 1:1, or 16:9 version from an existing accepted ClipTalk cut, then checks the rendered preview. Use only when a cut already exists and the user asks to adapt it for Shorts, Reels, Douyin, Xiaohongshu, WeChat Channels, or square feeds; do not use when the user still needs content found…