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/heygen-com/hyperframes/captions-overlaynpx skills add heygen-com/hyperframes --skill captions-overlaygit clone --depth 1 https://github.com/heygen-com/hyperframesWhat 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 | $0.00136 | $0.01263 |
| Opus 5 | $0.00068 | $0.00632 |
| Sonnet 5 | $0.00027 | $0.00253 |
| Haiku 4.5 | $0.00014 | $0.00126 |
Grade A, and why
captions-overlay 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 2d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Captions Overlay Doctrine
Overlay doctrine — supplements the upstream
embedded-captionsskill. Applies ON TOP of it; do not expect it folded into the upstream skill.
Two ideas combine here. First, the caption model — every spoken phrase is drop,
rail, or embed, and embed is the scarce earned peak, not the default. Second, the
overlay law — a caption line is composited ON TOP of the film as an overlay; it is
NOT a reserved zone, so you never shift content up or leave a dead band to "make room"
for it. The two reinforce each other: because captions ride as an overlay (the verbatim
rail in front, the occasional embed behind the subject), the composition keeps its full
frame and centers on the true vertical center.
The caption model — drop / rail / embed
Every spoken phrase is one of three things (verbatim from embedded-captions):
| What | How it's shown | |
|---|---|---|
| drop | filler — um/uh, stutters, self-corrections | not shown |
| rail | the default — ordinary spoken content (verbatim) | clean lower-third subtitle, in front, readable. A punch word can get an inline emphasis highlight (accent colour / active-word pop) — it stays on the rail. |
| embed | a promoted peak — the headline beat | one big word composited behind the subject (matte occlusion), designed entrance + exit |
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.
- 2d ago First seen · 82 lines · 136 tokens per session scan A 84cf9826a978
captions-overlay is a skill published in the GitHub repository heygen-com/hyperframes (43,593 stars, last pushed today), licensed Apache-2.0. It adds 136 tokens to every session and 1,263 once invoked, about $0.0007 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
architecture-diagram
Create a professional, dark-themed software/system architecture diagram as a single self-contained HTML file with inline SVG. Use when asked to visualize system components, layers, services, or how parts of a codebase fit together.
frame-data-chart-nyt
NYT-newsroom typography, staggered reveal animation, and editorial-grade charts (line, bar, or range band).
product-launch-motion
Use when making, directing or rescuing a product launch video, promo, teaser, demo reel, sizzle, feature-announcement film or animated product explainer built from code — and when an existing one looks basic, reads as a slideshow, has reveals that miss the voiceover, an invisible cursor, an inaudible sound effect, a…
rebuild-site
Rebuild a whole landing page / multi-section website from a screen recording that scrolls or walks through it. Use when the user has a recording of an ENTIRE page (not a single animation) and wants the full page recreated — layout, sections, copy, design system, and scroll animations. Orchestrates analyze (measured…
recreate
Recreate an analyzed animation as working web code — GSAP (JavaScript), CSS/Web Animations, Framer Motion (React), or Lottie/SVG. Use after /motiscope:analyze, or when the user asks to "build/recreate this animation in ". Reads the motiscope animation spec and emits a runnable component.
motiscope-analyze
Analyze a screen recording of an animation to characterize its motion — timing, easing, transforms, and sequencing — so it can be recreated as web code. Use when the user drops or points at a video of an animation (.mp4/.mov/.webm/.mkv/.m4v/.avi/.gif) and says things like "I want this animation on my site", "recreate…