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 agentmods add skills/varnan-tech/opendirectory/hyperframes-product-launch-videonpx skills add Varnan-Tech/opendirectory --skill hyperframes-product-launch-videogit clone --depth 1 https://github.com/Varnan-Tech/opendirectoryWrote 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/varnan-tech/opendirectory/hyperframes-product-launch-video)<a href="https://agentmods.dev/skills/varnan-tech/opendirectory/hyperframes-product-launch-video"><img src="https://agentmods.dev/badge/skills/varnan-tech/opendirectory/hyperframes-product-launch-video.svg" alt="Measured on agentmods" 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 | $0.00074 | $0.00884 |
| Opus 5 | $0.00037 | $0.00442 |
| Sonnet 5 | $0.00015 | $0.00177 |
| Haiku 4.5 | $0.00007 | $0.00088 |
Grade A, and why
hyperframes-product-launch-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 5d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Launch Video Skill
This skill guides you through the creation of high-end, premium product launch videos using Hyperframes. It emphasizes a structured workflow from brand discovery to final verification.
Leveraging Official Hyperframes Skills
This skill acts as the Director and Architect for your video project. To ensure technical accuracy and access to the latest framework patterns, you must use it in conjunction with the official Hyperframes skills.
Before writing any code, you should:
- Invoke the official /hyperframes skill to review composition rules, data-attribute semantics, and framework constraints.
- Invoke the official /gsap skill for detailed timeline references, easing functions, and complex animation patterns.
By combining the strategic guidance of this skill with the technical documentation of the official skills, you will produce production-grade video compositions.
Stateless Project Generation (CRITICAL)
This directory (hyperframes-product-launch-video) is a read-only template and skill folder. You must never write project-specific files here.
Whenever you create a new video project:
- Target Directory: All project files must be created in the user's target video project folder (e.g.,
my-new-video/ormy-new-video/assets/). - Project DNA: Generate the
brand_dna.jsoninside the target project'sassets/or root folder. - Art Direction: Save the final
ART_DIRECTION.mdinside the target project folder. - No Side Effects: Do not modify any files within this skill folder during a project run.
Workflow
1. The Interrogation Phase (Brand DNA)
Before starting, you must understand the brand.
- Website Analysis: Use Playwright to visit the user's website. Extract brand colors, typography (fonts), and core value propositions.
- Asset Request: Ask the user for logos and icons. Specify the need for clean, transparent, tightly-cropped PNGs or SVGs.
- Video Type Selection: Ask if this is a 100% motion graphics video or a hybrid (e.g., Founder talking head + Hyperframes motion graphics).
What ships with it
10 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.
- ART_DIRECTION.md 1.2 KB
- README.md 6.7 KB
- references/camera-and-easing-math.md 2.5 KB
- references/gotchas.md 2.4 KB
- references/motion-design-patterns.md 4.8 KB
- scripts/assets/favicon.png 14 KB
- scripts/assets/logo.png 130 KB
- scripts/extract_site_dna.js 5.8 KB runs code
- scripts/package.json 308 B
- scripts/scaffold_project.js 2.2 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.
- 5d ago First seen · 63 lines · 74 tokens per session scan A 56dcf0889562
hyperframes-product-launch-video is a skill published in the GitHub repository Varnan-Tech/opendirectory (635 stars, last pushed 19d ago), licensed MIT. It adds 74 tokens to every session and 884 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 2026-08-30.
Other skills, from other repositories
marketing-collateral-design
Use this skill to create professional static promotional graphics whose typography, claims, and contact details must remain exact. The core production rule is hybrid, not one-shot: generate or source imagery separately, then compose real text and vector elements deterministically in HTML/CSS/SVG. Image models are art…
blog-cover-image
Generate and revise raster cover images for blog posts and articles from a title, brief, draft, local file, URL content supplied by the user, or reference images. Use when Codex needs to create a blog cover, article hero/header image, editorial thumbnail, Open Graph/social preview visual, or a channel-specific cover…
chanjing-one-click-video-creation
用户输入选题或工作流，自动生成完整短视频成片（文案、分镜、数字人口播与 AI 画面混剪）；调用 Chanjing Open API 与同仓库子技能脚本。.
chanjing-tts-voice-clone
Use Chanjing TTS API to synthesize speech from text with a user-provided cloned voice (reference audio via public URL).
chanjing-avatar
Use Chanjing Avatar API for lip-syncing video generation (upload audio/video, create tasks, poll results).
chanjing-tts
Use Chanjing TTS API to convert text to speech (list voices, create tasks, poll, download from returned URLs).