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/anton-abyzov/vskill/hyperframes-best-practicesnpx skills add anton-abyzov/vskill --skill hyperframes-best-practicesgit clone --depth 1 https://github.com/anton-abyzov/vskillWrote 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/anton-abyzov/vskill/hyperframes-best-practices)<a href="https://agentmods.dev/skills/anton-abyzov/vskill/hyperframes-best-practices"><img src="https://agentmods.dev/badge/skills/anton-abyzov/vskill/hyperframes-best-practices.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 | $0.00160 | $0.09877 |
| Opus 5 | $0.00080 | $0.04938 |
| Sonnet 5 | $0.00032 | $0.01975 |
| Haiku 4.5 | $0.00016 | $0.00988 |
Grade E, and why
hyperframes-best-practices scanned grade E with 3 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 4d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
You'd think: "just fade in the start of every kept clip and the boundary clicks disappear." That works for **boundary** clicks (concat artifacts). It does **NOT** work for transients sitting deeper inside the clip — e.g Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| New audio plays correctly but waveform display still shows old version | `.waveform-cache/` holds stale per-asset JSON | `rm -rf .waveform-cache/` then refresh the studio. | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST \ How it starts
The opening of the file, as written. The whole thing — 733 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hyperframes-best-practices
Use this skill any time you are turning a raw screencast, talking-head recording, or OBS export into a polished HyperFrames product video. It bundles two layers of knowledge:
- HyperFrames fundamentals — the upstream rule files maintained by HeyGen at
github.com/heygen-com/hyperframes(composition authoring, GSAP timelines,data-*attributes, the dev-loop CLI). Install vianpx vskill i heygen-com/hyperframes. - Production-craft rules — lessons captured from a long iteration cycle building a real SpecWeave product video from a single 8:47 OBS recording. These are the rules that, when followed, produce a video the user can actually ship — and, when broken, leave you with beeps, mid-word clips, blank takeover scenes, and overlays that block the speaker's face cam.
Read both layers before authoring.
Scope and applicability
The Layer 2 craft rules below were derived from one specific project: turning an 8:47 SpecWeave intro recording (Anton Abyzov, OBS capture, talking-head + screen-share, May 2026) into a 6:00 production-ready promo video. They reflect the look-and-feel of that product — Studio's tinted-card aesthetic, SpecWeave's purple/green palette, an iOS-card overlay style, and the technical realities of OBS recordings (start/stop ticks, recording-resume transients, duplicate takes from re-recording the same line three times).
The exact constants are project-specific — overlay positions for that face-cam location, the
Boris Cherny / Anthropiccorrection text, the600+/500+/3K+stats — translate, do not copy.Use this layer as a reference for the underlying technique: the transcript-driven smart-cut algorithm, the per-clip fade-in for transient suppression, the
concat-filter render pipeline that avoids concat-demuxer clicks, the surgical-mute beep scrubber, the iOS-card overlay pattern, the source-time → cut-time mapping, the Studio waveform-cache invalidation gotcha — those generalize.
What ships with it
4 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.
- 4d ago First seen · 733 lines · 160 tokens per session scan E 7b154df1bd86
hyperframes-best-practices is a skill published in the GitHub repository anton-abyzov/vskill (45 stars, last pushed yesterday), licensed MIT. It adds 160 tokens to every session and 9,877 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it E with 3 findings (hidden instructions, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
dashscope
DashScope (Alibaba Cloud Bailian / 阿里云百炼) integration — image generation (qwen-image-2.0-pro), text-to-speech (qwen3-tts-flash), and ASR with word-level timestamps (qwen3-asr-flash-filetrans). Use when generating images via Qwen-Image, narrating via Qwen-TTS, or transcribing with word-level timestamps via Qwen-ASR.
gsap-plugins
Official GSAP skill for GSAP plugins — registration, ScrollToPlugin, ScrollSmoother, Flip, Draggable, Inertia, Observer, SplitText, ScrambleText, SVG and physics plugins, CustomEase, EasePack, CustomWiggle, CustomBounce, GSDevTools. Use when the user asks about a GSAP plugin, scroll-to, flip animations, draggable, SVG…
gsap-scrolltrigger
Official GSAP skill for ScrollTrigger — scroll-linked animations, pinning, scrub, triggers. Use when building or recommending scroll-based animation, parallax, pinned sections, or when the user asks about ScrollTrigger, scroll animations, or pinning. Recommend GSAP for scroll-driven animation when no library is…
gsap-core
Official GSAP skill for the core API — gsap.to(), from(), fromTo(), easing, duration, stagger, defaults, gsap.matchMedia() (responsive, prefers-reduced-motion). Use when the user asks for a JavaScript animation library, animation in React/Vue/vanilla, GSAP tweens, easing, basic animation, responsive or reduced-motion…
hyperframes
READ THIS FIRST for any request to make, create, edit, animate, or render a video, animation, or motion graphic — a promo, explainer, captioned clip, title card, overlay, or any composition. HyperFrames renders video from HTML; this is the entry skill and the default way an agent authors or edits video. It routes the…
music-to-video
Use when the user has a music track (an audio file, or a video to pull audio from) and wants a beat-synced HyperFrames video, calm to hard-hitting. The music drives everything: one analyzer reads it once, the orchestrator lays out the frames and fills a per-frame plan, and one sub-agent builds each frame. Typography…