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 heygen-com/hyperframes-community-skills --skill camera-3d-captionsgit clone --depth 1 https://github.com/heygen-com/hyperframes-community-skillsWrote 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/heygen-com/hyperframes-community-skills/camera-3d-captions)<a href="https://agentmods.dev/skills/heygen-com/hyperframes-community-skills/camera-3d-captions"><img src="https://agentmods.dev/badge/skills/heygen-com/hyperframes-community-skills/camera-3d-captions/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/heygen-com/hyperframes-community-skills/camera-3d-captions"><img src="https://agentmods.dev/badge/skills/heygen-com/hyperframes-community-skills/camera-3d-captions.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 | $0.00189 | $0.02467 |
| Opus 5.5 | $0.00076 | $0.00987 |
| Sonnet 5.5 | $0.00038 | $0.00493 |
| Haiku 4.5 | $0.00019 | $0.00247 |
Grade A, and why
camera-3d-captions 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 23d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
3D camera captions
The After Effects move (3D camera, depth of field, text on a path, Posterize Time 15, motion blur) rebuilt as a deterministic per-frame painter for HyperFrames. One clock paints plate, matte and every glyph. Nothing is a CSS animation.
When to use / when not
- Use on a static-camera talking-head take (avatar or real), landscape, medium shot or wider, 5–20 s per piece. The words must perform in depth around the speaker.
- Do not use for plain subtitles, a moving or handheld camera (the matte and the plate transform assume a locked shot), extreme close-ups (no room behind or around the head), or a subject a person-matting model can't separate.
Requirements and side effects (complete list)
- Tools:
- Node 22+ and the HyperFrames CLI pinned to the tested version,
npx [email protected](downloads fromregistry.npmjs.org). Use that exact version for every command below. ffmpegon PATH.- Python 3 with
fonttools,brotli,numpy,pillow.
- Node 22+ and the HyperFrames CLI pinned to the tested version,
- Matte:
npx [email protected] remove-backgroundruns locally. On first run it downloads its person-segmentation model (~170 MB) to~/.cache/hyperframes/. - Render time: compositions load GSAP 3.14.2 from
cdn.jsdelivr.netat preview/render time. - Word clock: any word-level transcriber the user already runs locally. Onset accuracy matters; plain Whisper starts run late.
- Fonts: user-supplied files. Confirm the licence allows embedding.
- Hand-drawn style (optional): needs the
p5-paint-animationskill installed and set up (its setup downloads pinned puppeteer, Chrome for Testing, p5 and p5.brush).build-sprites.pyruns it headlessly; frames are written to that skill'sout/and removed afterwards. - Nothing else: no credentials, no paid calls, nothing uploaded. Files are written only into the project
(
assets/,renders/).
Prep (once per take)
- Portion and plate.
bash scripts/prep-take.sh <take.mp4> <start_s> <dur_s> <project>/assetsproduces:portion.mp4: the audio source.plate-tall.mp4: reflect-padded 240 px each side, 480 px top, 240 px bottom, so whips, trucks and pull-backs never show an edge.person.webm: the alpha matte, same frames.- The script then checks the plate and matte against the portion (size, frame rate, frame count) and fails on any mismatch.
- Word clock. Word timings for the portion, in seconds from its start.
- Fonts. Pick 2–3 roles (caption / hero / ring), then
python3 scripts/font-metrics.py assets/metrics.js key=font.woff2[@wght=…,opsz=…] ….- A variable font must get its axes passed here AND pinned in CSS (
font-variation-settings,font-optical-sizing: none). Otherwise the browser's opsz follows the size and words overlap.
- A variable font must get its axes passed here AND pinned in CSS (
- Silhouette. Read the head box and shoulder line off the
person.webmalpha before placing anything.
What ships with it
11 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.
- assets/kit/cam3d.js 23 KB runs code
- assets/kit/finish.js 2.0 KB runs code
- assets/kit/tables.js 3.6 KB runs code
- references/recipes.md 7.3 KB
- references/worked-film.html 25 KB
- scripts/font-metrics.py 2.3 KB runs code
- scripts/frame-bounds.js 3.2 KB runs code
- scripts/glyph-gaps.js 3.7 KB runs code
- scripts/hand/build-sprites.py 5.2 KB runs code
- scripts/hand/hand-word.anim.js 3.0 KB runs code
- scripts/prep-take.sh 2.7 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.
- 23d ago First seen · 145 lines · 189 tokens per session scan A 2f5507777cea
camera-3d-captions is a skill published in the GitHub repository heygen-com/hyperframes-community-skills (208 stars, last pushed 2d ago), licensed Apache-2.0. It adds 189 tokens to every session and 2,467 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-09-23.
Other skills, from other repositories
paperclip-capsules
Generate, implement, or review Paperclip capsule visuals. Use for capsule art, agent capsules, heartbeat status capsules, identicons, capsule banks, or brand-usage validation.
video-hyperframes
Hyperframes / Remotion-compatible continuous frame animation with autoplay support.
brag
Turn the current project website into a short, polished, shareable launch video using Hyperframes. Use when someone says "/brag", "let's brag about this", "make a launch video", "turn this into a video", or wants to share what they built. Reads the project code directly — no live URL or screenshots needed.
brag-slim
Turn a project directory or a website URL into a short, shareable launch video with music, motion, and share copy. One file, no bundled assets — built entirely by the model with the tools already on the machine. Use when someone says "/brag-slim", "let's /brag about this", "brag about a website", "make a launch…
video-hyperframes
A web-based sequence of video frames designed for Hyperframes or Remotion, with each frame presenting one visual idea.
broll-director
Turn a complete original SRT and design into immutable shot truth, revisable creative proposals, semantic chapters, a shared visual world, a compact motion map, and three representative-scene choices.