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 indranilbanerjee/digital-marketing-pro --skill video-scriptgit clone --depth 1 https://github.com/indranilbanerjee/digital-marketing-proWrote 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/indranilbanerjee/digital-marketing-pro/video-script)<a href="https://agentmods.dev/skills/indranilbanerjee/digital-marketing-pro/video-script"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/digital-marketing-pro/video-script/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/indranilbanerjee/digital-marketing-pro/video-script"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/digital-marketing-pro/video-script.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 | $0.00034 | $0.02435 |
| Opus 5.5 | $0.00014 | $0.00974 |
| Sonnet 5.5 | $0.00007 | $0.00487 |
| Haiku 4.5 | $0.00003 | $0.00244 |
Grade A, and why
video-script 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 18d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/digital-marketing-pro:video-script
Purpose
Write a production-ready video marketing script with hook variants, timestamps, visual direction notes, CTA placement, and platform-specific formatting. Produces a complete script package ready for production with visual and audio columns, accessibility notes, and thumbnail concepts.
Input Required
The user must provide (or will be prompted for):
- Video type: The format of the video — ad spot, explainer, testimonial, product demo, social short, educational tutorial, brand story, or event recap
- Target platform: Where the video will be published — YouTube, TikTok, Instagram Reels, LinkedIn, YouTube Shorts, Facebook, or multi-platform
- Target length: Desired duration — 15s, 30s, 60s, 90s, 2-3 min, 5-10 min, or long-form 10+ min
- Key message or topic: The core idea, value proposition, or subject matter the video must communicate
- Call to action: What the viewer should do after watching — visit URL, subscribe, purchase, sign up, download, follow, etc.
- Target audience: Who the video is for — demographics, psychographics, awareness level, and platform behavior
- Brand tone: Desired tone and energy level — professional, casual, humorous, inspirational, educational, urgent, or conversational
- Available assets: What production resources are available — on-camera talent, b-roll footage, product samples, graphics/animation capability, studio vs. location, screen recordings
- Competitor video references: Optional — links or descriptions of competitor or aspirational videos to benchmark against
- Performance goals: What success looks like — views, watch-through rate, click-through rate, conversions, engagement, or brand lift
Process
- Load brand context: Read
~/.claude-marketing/brands/_active-brand.jsonfor the active slug, then load~/.claude-marketing/brands/{slug}/profile.json. Apply brand voice, compliance rules for target markets (skills/context-engine/compliance-rules.md), and industry context. Also check for guidelines at~/.claude-marketing/brands/{slug}/guidelines/_manifest.json— if present, load restrictions and relevant category files. Check for custom templates at~/.claude-marketing/brands/{slug}/templates/. Check for agency SOPs at~/.claude-marketing/sops/. If no brand exists, ask: "Set up a brand first (/digital-marketing-pro:brand-setup)?" — or proceed with defaults. - Determine platform specs and format constraints: Reference platform-specific requirements — aspect ratio (16:9, 9:16, 1:1), max duration, safe zones for text overlays, caption placement areas, and native content conventions. Apply platform algorithm preferences (e.g., TikTok favors native-feeling content, LinkedIn rewards professional storytelling, YouTube prioritizes watch time).
2.4. Identify the script class — organic or ad — and load campaign context: These are different disciplines with different physics. Organic content earns its audience (discovery intent, step 2.5). Ads buy theirs, so the craft is about what happens inside a paid, often skippable slot. If this script belongs to a campaign, read the campaign context first —
~/.claude-marketing/brands/{slug}/campaigns/and any campaign-plan output — so the script inherits the campaign's objective, funnel stage, audience, and offer instead of inventing parallel ones. A mid-funnel retargeting ad and a cold-audience awareness ad are different scripts for the same product; the campaign brief decides which one this is.
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.
- 18d ago Changed · -132 tokens per session 5cee6bb1d2e3
- 23d ago First seen · 71 lines · 166 tokens per session scan A 4223b295e32d
video-script is a skill published in the GitHub repository indranilbanerjee/digital-marketing-pro (912 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 2,435 once invoked, about $0.0001 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 2026-10-05.
Other skills, from other repositories
cf-brief
Write a research-backed content brief from a keyword or topic: intent, competitors, outline. "brief me on this topic".
cf-publish
Publish a reviewed piece to Webflow or WordPress as draft, scheduled or live. "push this live to WordPress".
cf-template
Create a custom content-type template: sections, word counts, citation minimums. "make a template for our case studies".
cf-variants
Generate scored A/B variants of a headline, opening line, hook or CTA, with a test plan. "give me headline options to test".
cf-translate
Translate a finished piece into 15 languages, keeping brand voice and citations; literal, adapted or transcreated. "translate this into Spanish".
cf-video-script
Write a timestamped video script with B-roll and on-screen text for YouTube, Shorts or Reels. "turn this into a video script".