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 ucsandman/marketing-studio --skill launch-videogit clone --depth 1 https://github.com/ucsandman/marketing-studioWrote 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/ucsandman/marketing-studio/launch-video)<a href="https://agentmods.dev/skills/ucsandman/marketing-studio/launch-video"><img src="https://agentmods.dev/badge/skills/ucsandman/marketing-studio/launch-video/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/ucsandman/marketing-studio/launch-video"><img src="https://agentmods.dev/badge/skills/ucsandman/marketing-studio/launch-video.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 | $0.00038 | $0.00896 |
| Opus 5 | $0.00019 | $0.00448 |
| Sonnet 5 | $0.00008 | $0.00179 |
| Haiku 4.5 | $0.00004 | $0.00090 |
Grade A, and why
launch-video 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 yesterday.
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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Launch Video
REQUIRED BACKGROUND: marketing-studio skill; also read
${CLAUDE_SKILL_DIR}/../../docs/playbook/remotion.md,
${CLAUDE_SKILL_DIR}/../../docs/playbook/audio.md, and
${CLAUDE_SKILL_DIR}/../../docs/playbook/capture.md. Work in ${CLAUDE_SKILL_DIR}/../...
Produces a scored film and its direction, shot plan, stage approvals, render evidence,
and review record inside <product>/marketing/assets/<brand>/. Read
docs/production-quality.md before production work.
A film is not done without audio, and audio means a voice explaining the product.
Scoring is not optional and node scripts/check-audio.mjs <brand> --project <product>
must exit 0 before the word "done". Two postflop cuts shipped silent on 2026-09-01;
that is the reason this line exists.
Route
Choose the route from the concept and product proof. Use a bespoke composition under
studio/src/films/<brand>/ when the film needs a product-specific visual world or shot
system. Use the directed LaunchVideo composition when its authored shot plan can carry
the idea without reverting to the legacy five-act deck. A shot may use a real capture,
native rebuilt UI, 2D, 3D, or a hybrid. Rebuilding UI is useful for controlled actions;
it is not a universal requirement.
Recipe
- Set
<product>explicitly with--project. Do not create any generated product input or output in engine-localout/. - Explore distinct directions, choose one with a specific reason, and record its visual
metaphor, sound intent, references with provenance, and reviewable style frame in
direction.json. The preset is only a starting grammar. - Write the shot plan before full production. Each shot needs a purpose, duration, scale, camera cadence, transition intent, readable-copy limits, source/reference, and audio beat. Plan narration with the edit; every numeric claim traces to a brief proof point.
- Build an audio-bearing animatic with scratch voice and music. A named non-author reviewer approves both style frame and animatic, bound to their hashes. A weak visual argument stops here, before finish work.
- Build the chosen route. Directed LaunchVideo consumes
directionand authoredshots; a bespoke film owns its shot components and timeline. Match cuts may overlap, hard cut, wipe, dissolve, or continue motion as the relationship demands. Static end frames are one option, not a rule. - Render inexpensive shot proofs and a versioned preview. Inspect the product action at delivery size, the start/middle/end of every shot, and the frames around every cut. Fix the written defect list, then make the full-resolution render once.
- Build product-owned narration, music, and SFX inputs and score the silent lock with
node scripts/score-film.mjs <brand> <film.mp4> --project <product>. It refuses overlapping narration and verifies the delivered master. Music-only requires the explicit recorded exception; never imply narration that is absent. - Generate hash-bound evidence from the exact final render:
node scripts/contact-sheet.mjs <brand> --project <product> --plan <production-plan.json> --render <final.mp4>. - In Mission Control, a named director, operator, or independent reviewer watches the
complete scored cut, records defects and the “would I share this?” verdict. Then run
node scripts/judge-production.mjs <brand> --project <product> --plan <production-plan.json> --render <final.mp4> --strict. - Run the existing audio, palette, studio test/lint, and smoke gates. They prove properties and runtime, not taste. Only the scored, strict-PASS lock proceeds to the production matrix and post kit.
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.
- yesterday Changed · +3 lines 40eb0ab5c4a3
- 3d ago Changed · -1 lines · -15 tokens per session c4a67673be5a
- 4d ago Changed · +22 lines · +4 tokens per session e96b7e7341fe
- 9d ago First seen · 40 lines · 49 tokens per session scan A 2ede82d92579
launch-video is a skill published in the GitHub repository ucsandman/marketing-studio (228 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 896 once invoked, about $0.0002 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
ccvideo
Make product promo videos in the Claude video team style — terracotta canvas, macOS terminal window, animated Claude Code session — with Remotion. Use when the user asks for a product/feature promo, launch video, terminal demo video, or a "Claude-style" video.
saas-product-demo-video
Produce a 20-45s SaaS product demo video in Remotion. Use whenever the user wants to make a product film, marketing reel, explainer, launch video, or LinkedIn/Instagram video of their app - including requests like "make a video of my product", "remotion video", "product demo reel", "launch film", "vertical reel"…
remotion-video-workflow
Build structured short-form videos in Remotion from a brief or source material. Use when the user wants a reusable workflow covering storyboard structure, brand elements, music, ratio adaptation, cover linkage, render, and output verification.
magazine-web-ppt
For marketing and gtm work: bind launches, campaigns, events, and brand plans to growth and pipeline outcomes. Built around the core query "annual-marketing-plan", with GTM strategy lead judgment, buyer-ready proof, and this outcome: approve launch plan, campaign budget, or GTM motion.
html-ppt-zhangzara-coral
OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.
deck-guizang-editorial
OpenDesign's FY26 marketing plan: brand-to-pipeline — audience, offer, channel mix, and the launch calendar that ties creative to growth. Built as a decision-grade marketing & GTM deck for CMO, growth lead, founder.