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 hub-ki/video-generation --skill video-plangit clone --depth 1 https://github.com/hub-ki/video-generationWrote 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/hub-ki/video-generation/video-plan)<a href="https://agentmods.dev/skills/hub-ki/video-generation/video-plan"><img src="https://agentmods.dev/badge/skills/hub-ki/video-generation/video-plan/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/hub-ki/video-generation/video-plan"><img src="https://agentmods.dev/badge/skills/hub-ki/video-generation/video-plan.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 | $0.00217 | $0.03914 |
| Opus 5 | $0.00109 | $0.01957 |
| Sonnet 5 | $0.00043 | $0.00783 |
| Haiku 4.5 | $0.00022 | $0.00391 |
Grade A, and why
video-plan 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
video-plan
You are writing the two documents a video gets approved on, and nothing else. No capture,
no cutting, no rendering — that is the demo-video skill, and it refuses to start without
these.
PLAN.md the SHAPE — purpose, audience, beats, targets, spotlights, privacy, out of scope
SCRIPT.md the WORDS — card copy, typed strings, required AI answers, the spoken track
Why they are separate documents: a plan can be right while the copy is wrong, and copy is the thing reviewers actually react to. A stakeholder can approve words; they cannot approve a beat table.
Why they come first: the arc is what changes under review, and every beat captured against an unagreed arc gets re-captured. A sentence that changes after the shoot can cost the whole flow, because patching one beat into an existing cut is usually not available.
Usually, not always — and the condition is worth knowing, because it decides how expensive a late change is:
A single beat can be re-shot only when the scene shares no state with its neighbours, and the source renders stably between runs, and no audio anchor crosses the scene boundary.
On a demo of your own app the first two are typically violated: time-of-day greetings and relative timestamps drift between runs, so a patched beat is visibly discontinuous with the ones around it. On a self-contained section of a third-party website they typically hold. The third condition is the one that comes back later — the moment narration is added, a re-shot beat of a different length moves every following audio anchor, and a pipeline that could re-shoot freely while it was silent can no longer do it.
Reading the app in order to write the plan is fine and expected. Recording it is not. The same holds for a website you do not own — read it, do not film it yet, and do not click anything that writes.
| Need | Read |
|---|---|
| the standard two-part feature-guide format (the default ask — read FIRST if it's a guide) | references/guide-format.md |
| the subject is a WEBSITE, not an app you sign into (the tour arc, and the permission questions that belong in the plan) | references/site-tour-format.md |
| is there a concept of the application? (the reusable half — what the product is for, its flows, the words on screen) | references/application-concept.md |
| the exact shape of both documents, with a fill-in template | references/plan-and-script.md |
| caption card copy — what a headline may and may not do | references/copy-rules.md |
| the spoken track — grammar traps, audience fit, tone | references/spoken-track.md |
What ships with it
6 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.
- 9d ago First seen · 260 lines · 217 tokens per session scan A 4c2062d16b10
video-plan is a skill published in the GitHub repository hub-ki/video-generation (6 stars, last pushed 16d ago), licensed MIT. It adds 217 tokens to every session and 3,914 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
demo-gif
Record, render, optimize, and embed a demo GIF in a repo's README. Use when asked to add a demo gif, record a demo, show the tool in action, or make a README more visual.
demo-gif
Record and optimize reproducible README demo GIFs. Use when asked to record a demo or add a README GIF.
demo-video
A process for automatically recording feature-demo videos of a local web app using Playwright, a browser-automation tool, and ffmpeg, a video-processing tool. It drives the real app, then adds subtitles, labels, a simulated cursor, zooms, and faster playback for waiting periods.
slideops
Use when the user asks for slides, a slide deck, or a presentation about a code repository, one of its subsystems, a feature, an architecture area, or its recent changes. Triggers include "make slides", "build a slide deck", "create a presentation", "HTML slides for this repo", "overview deck", "team update slides"…
ogilvideo
Use this skill when a user asks to analyze, reverse-engineer, plan, prompt, storyboard, direct, animate, improve, or produce a high-quality motion video, agentic AI video, SaaS explainer, product launch film, animated landing-page video, UI motion sequence, screen-recording transformation, or motion-graphics ad. This…
ogilvideo
Use this skill when a user asks to analyze, reverse-engineer, plan, prompt, storyboard, direct, animate, improve, or produce a high-quality motion video, agentic AI video, SaaS explainer, product launch film, animated landing-page video, UI motion sequence, screen-recording transformation, or motion-graphics ad. This…