captions-overlay

A set of rules for placing captions, or on-screen subtitles, over talking-head and launch videos. It treats captions as a layer on top of the full image and sorts spoken words into hidden filler, regular subtitle text, or occasional text integrated into the scene.

In plain words
What is it for?
Use it when adding captions or subtitles to spoken video. It helps decide which words to show, where to place them, and when a caption can sit behind or alongside the subject.
Why use it?
It avoids shrinking or shifting the composition just to make room for subtitles. It also gives ordinary speech and emphasis different visual treatments.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/heygen-com/hyperframes/captions-overlay
Any agent
npx skills add heygen-com/hyperframes --skill captions-overlay
Clone the repo
git clone --depth 1 https://github.com/heygen-com/hyperframes

Made for: Claude Code, Codex.

Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,263 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 84cf9826a978, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.agents/skills/captions-overlay/SKILL.md · 82 lines

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-captions skill. 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

Read the full file on GitHub · 82 lines

Changes

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.

  1. 2d ago First seen · 82 lines · 136 tokens per session scan A 84cf9826a978

Subscribe to this mod's changes

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.

Related

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.

AgentEra/Agently · 47 tokens

frame-data-chart-nyt

NYT-newsroom typography, staggered reveal animation, and editorial-grade charts (line, bar, or range band).

nexu-io/html-video · 30 tokens

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…

AbubakrChan/product-launch-motion · 137 tokens

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…

KumarSashank/motiscope · 104 tokens

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.

KumarSashank/motiscope · 75 tokens

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…

KumarSashank/motiscope · 103 tokens