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 2233admin/design-pipeline --skill video-delivery-specsgit clone --depth 1 https://github.com/2233admin/design-pipelineWrote 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/2233admin/design-pipeline/video-delivery-specs)<a href="https://agentmods.dev/skills/2233admin/design-pipeline/video-delivery-specs"><img src="https://agentmods.dev/badge/skills/2233admin/design-pipeline/video-delivery-specs/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/2233admin/design-pipeline/video-delivery-specs"><img src="https://agentmods.dev/badge/skills/2233admin/design-pipeline/video-delivery-specs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00111 | $0.03057 |
| Opus 5 | $0.00056 | $0.01528 |
| Sonnet 5 | $0.00022 | $0.00611 |
| Haiku 4.5 | $0.00011 | $0.00306 |
Grade A, and why
video-delivery-specs 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 6d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Delivery Specs
Deliver motion content correctly across platforms: produce per-platform spec sheets, repurpose one master into every aspect ratio safely, handle captions and accessibility, and run a pre-delivery QC and collect-files pass before handover.
When to use
Use when exporting or delivering finished motion, when targeting multiple platforms from one master, when checking safe areas for UI-overlay platforms, when deciding caption strategy, or when packaging a project for handover/archive.
Decision tree — master strategy and spec path
Two judgments: what to build as the master so it survives every crop, and which delivery path each platform needs. Decide the master before animating — re-cropping after the fact is where deliveries break.
How many ratios does the brief's distribution need?
├─ One ratio only → animate native to that ratio; no spine needed.
└─ Multiple ratios → build a 16:9 master with a centre 1:1 "title-safe
spine"; expect to RE-LAYOUT (not just crop) for 9:16.
Per target, which path?
├─ Social (Reels/TikTok/Shorts/Story) → 9:16 1080×1920, H.264 8-12 Mbps,
│ burn in captions, keep action out of top/bottom/right UI zones.
├─ Feed → 4:5 (1080×1350) for most screen real estate.
├─ YouTube long-form → 16:9, upload high-bitrate / ProRes, .srt sidecar.
├─ Broadcast → follow the broadcaster's spec PDF EXACTLY: ProRes 422 HQ,
│ region frame rate, R128/A85 loudness, title-safe 90%, textless + slate.
├─ OOH/signage → pixel-exact to the screen, silent, oversize type.
└─ Web hero → MP4+WebM, muted autoplay loop, compress hard, poster frame.
Rule of thumb: if a platform overlays UI (all vertical social), the safe-area map governs layout before the spec governs export. Get the layout wrong and no bitrate fixes it.
Workflow
- List target platforms from the brief's distribution line (Reels, Feed, Story, TikTok, YouTube, Shorts, broadcast, OOH, web).
- Pull each platform's spec (table below; full detail in references/platform-specs.md).
- Plan the master + cutdowns using the repurposing matrix so the 16:9 master survives the crop to 9:16 and 1:1.
- Decide captions/accessibility — burned-in vs uploaded, styling, safe placement.
- Run QC against the checklist, then collect files for handover/archive.
What ships with it
5 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.
- 6d ago First seen · 168 lines · 111 tokens per session scan A de26746cc0cc
video-delivery-specs is a skill published in the GitHub repository 2233admin/design-pipeline (9 stars, last pushed 7d ago), licensed MIT. It adds 111 tokens to every session and 3,057 once invoked, about $0.0006 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 2026-09-04.
Other skills, from other repositories
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
omd-apply
A skill that applies a project's DESIGN.md file as visual and brand guidance for interface work. It covers components, colors, fonts, layout, copy, motion, and visual assets.
ss-review
Review UI code for design system compliance, accessibility, and best practices.
ss-pattern
Generate a composed UI pattern from the active StyleSeed grammar and brand recipe using existing primitives.
ss-reference
Compile screenshots, URLs, Figma exports, or an existing UI into a project-local StyleSeed output grammar with evidence, tokens, confidence, anti-patterns, and a validation screen. Use when the user supplies a design reference that StyleSeed does not already model.
cicd-integration
Generate CI/CD pipeline configurations that automate design system quality checks — token validation, component linting, visual regression, accessibility scanning, and release gating. Produces ready-to-use pipeline files for GitHub Actions, GitLab CI, CircleCI, or Bitbucket Pipelines, configured to enforce the…