Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/J-StaR-Films-Studios/VibeCode-Protocol-Suitenpx agentmods add skills/j-star-films-studios/vibecode-protocol-suite/embedded-captionsWrote 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/j-star-films-studios/vibecode-protocol-suite/embedded-captions)<a href="https://agentmods.dev/skills/j-star-films-studios/vibecode-protocol-suite/embedded-captions"><img src="https://agentmods.dev/badge/skills/j-star-films-studios/vibecode-protocol-suite/embedded-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/j-star-films-studios/vibecode-protocol-suite/embedded-captions"><img src="https://agentmods.dev/badge/skills/j-star-films-studios/vibecode-protocol-suite/embedded-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 | $0.00268 | $0.07224 |
| Opus 5 | $0.00134 | $0.03612 |
| Sonnet 5 | $0.00054 | $0.01445 |
| Haiku 4.5 | $0.00027 | $0.00722 |
Grade A, and why
embedded-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 7d 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.
This is a copy
94% identical to embedded-captions — 96 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Embedded Captions
One catalog, picked up front (CATALOG.md — 17 identities; the three engines behind it are backend detail). Standard (default) builds a clean verbatim rail (lower-third subtitle carrying most text) + an embed climax composited into the scene behind the subject at the peak. Cinematic is pure embed — no rail, every caption composited behind the subject (hero typography, accumulation, occlusion as the effect). Theme is a complete themed constitution — body paradigm × hero setpiece × front fx × plate reaction, composed from registries (themes/README.md): ordnance terminal neonsign stardust stomp. Most explainer / voiceover is Standard; embed is the scarce, earned peak — embedding every word is the common mistake; Theme is for VFX-grade asks ("炸", "特效", "像 AE 做的").
Operational flow (TL;DR)
The craft prose below is long; the pipeline itself is short — and everything deterministic is computed or compiled, never hand-written:
- Decision gate (refuse bad clips) → pick ONE identity from CATALOG.md (17 identities; engine/compiler derived by lookup — never surface a mode/category question)
hyperframes init(skip it if the project dir already exists with the video inside —matte.cjs/transcribe.cjsadopt any video in the dir as source.mp4) →bash scripts/prepare.sh <project>(matte ∥ transcribe ∥ audio-envelope in parallel, then safe-zones v2 with scene palette/optics/lighting — one command, nothing forgotten)- author a small JSON of creative choices (read
safe-zones.jsonfirst): Cinematic →plan.json→fill-timings.cjs→fit-fonts.cjs→make-composition.cjs; Theme →theme.json→make-theme.cjs(rail/panel/poem/takeover paradigms;anchoris the quiet rail default) - Visual QA:
node scripts/preview-frames.cjs <project>→ faithful composite previews in ~2s/frame (no render). Check § Visual QA before paying for a render. render-and-composite.sh→ gates (timing / occlusion+hero / overflow / hand-off) →final.mp4
What ships with it
60 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.
- .gitignore 676 B
- assets/brand/CDPR-fankit-terms.txt 2.5 KB
- assets/brand/cyberpunk-widths.json 3.0 KB
- assets/fonts/char-widths.json 39 KB
- assets/strokefonts/HersheyScript1.svg 59 KB
- assets/strokefonts/HersheyScriptMed.svg 69 KB
- CATALOG.md 55 KB
- dna/chrome.json 1.7 KB
- dna/cream.json 1.5 KB
- dna/documentary.json 1.4 KB
- dna/editorial.json 1.6 KB
- dna/glitch.json 1.8 KB
- dna/ink.json 1.5 KB
- dna/keynote.json 1.4 KB
- dna/loud.json 1.9 KB
- dna/neon.json 1.5 KB
- dna/README.md 12 KB
- dna/velocity.json 1.9 KB
- modes/cinematic/_archive/champion/spec.md 4.6 KB
- modes/cinematic/_archive/champion/template.html 5.6 KB
- modes/cinematic/_archive/memory-wall/spec.md 5.7 KB
- modes/cinematic/_archive/memory-wall/template.html 5.5 KB
- modes/cinematic/_archive/portrait-header/spec.md 3.5 KB
- modes/cinematic/_archive/portrait-header/template.html 5.2 KB
- modes/cinematic/cinematic-cream/spec.md 1.1 KB
- modes/cinematic/cinematic-cream/template.html 10 KB
- modes/cinematic/engine.html 17 KB
- modes/cinematic/README.md 2.6 KB
- modes/standard/_anatomy.md 11 KB
- modes/standard/_motion.md 18 KB
- modes/standard/fonts/build-fonts-css.cjs 3.5 KB runs code
- references/aesthetic-principles.md 7.6 KB
- references/anti-patterns.md 12 KB
- references/bespoke-vs-presets.md 9.0 KB
- references/caption-grouping.md 4.2 KB
- references/composition-craft.md 55 KB
- references/direction-catalog.md 7.7 KB
- references/example-renders/champion.html 11 KB
- references/example-renders/memory-wall.html 10 KB
- references/failure-modes.md 11 KB
- references/layout-heuristics.md 13 KB
- references/motion-vocabulary.md 5.5 KB
- references/rail.md 4.4 KB
- references/reference-bar.md 2.6 KB
- references/scene-types.md 6.1 KB
- references/test-set.md 3.9 KB
- references/typographic-moves.md 8.5 KB
- references/typography-presets.md 4.6 KB
- scripts/audio-envelope.cjs 3.0 KB runs code
- scripts/check-occlusion.cjs 10 KB runs code
- scripts/check-overflow.cjs 6.6 KB runs code
- scripts/check-rail-climax.cjs 8.2 KB runs code
- scripts/check-timing.cjs 6.2 KB runs code
- scripts/fill-timings.cjs 4.5 KB runs code
- scripts/fit-fonts.cjs 6.2 KB runs code
- scripts/gen-stroke-path.py 1.7 KB runs code
- scripts/inject-fonts.cjs 5.8 KB runs code
- scripts/lib-dna.cjs 7.2 KB runs code
- scripts/make-cinematic.cjs 56 KB runs code
- scripts/make-composition.cjs 16 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.
- 7d ago First seen · 287 lines · 268 tokens per session scan A f259486ad695
embedded-captions is a skill published in the GitHub repository J-StaR-Films-Studios/VibeCode-Protocol-Suite (24 stars, last pushed today), licensed ISC. It adds 268 tokens to every session and 7,224 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to embedded-captions, differing in 96 lines, and is treated as a copy.
Other skills, from other repositories
gpt-image-2-style-library
Choose GPT-Image2 / gpt-image-2 visual styles and industrial prompt templates from the awesome-gpt-image-2 style library. Use when an agent needs to create, rewrite, classify, or improve image-generation prompts with repository-backed templates, categories, style tags, scene tags, pitfalls, and example cases.
seedance-prompt
This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.0 video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt.
short-drama-storyboard
A workflow for turning a Chinese short-drama script and its visual facts into a shot-by-shot storyboard with frozen starting-frame prompts.
short-drama-video-prompts
A writing guide for turning approved short-drama storyboards and starting images into copy-ready prompts for generating video scenes. It covers both image-to-video prompts, which use a reference image, and text-to-video prompts, which describe the scene in words.
short-drama-develop
A Chinese-language writing workflow for turning novel, short-drama, or comic-drama ideas and source material into an adaptation plan, story direction, creative brief, story engine, and episode map.
short-drama-write
A writing workflow for creating or revising a shootable Chinese short-drama or animated-drama episode in Markdown.