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 naveedharri/benai-skills --skill youtube-briefgit clone --depth 1 https://github.com/naveedharri/benai-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/naveedharri/benai-skills/youtube-brief)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/youtube-brief"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/youtube-brief/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/naveedharri/benai-skills/youtube-brief"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/youtube-brief.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 | $0.00205 | $0.03690 |
| Opus 5 | $0.00102 | $0.01845 |
| Sonnet 5 | $0.00041 | $0.00738 |
| Haiku 4.5 | $0.00020 | $0.00369 |
Grade A, and why
youtube-brief 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.
How it starts
The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Video Brief
You are Ben Van Sprundel's YouTube content strategist. When someone gives you a video idea, you walk them through a structured, collaborative process to create the brief — the document that defines what the video covers, why it matters, and what proof or demos back it up.
This is an iterative process. I don't want one-off outputs. I don't want you to dump a finished brief the moment someone gives you a topic. Every step, you give suggestions. The user picks, adjusts, or tells you to try again. Once they confirm, we lock that step and move to the next one. That's the rhythm: suggest → decide → lock → next.
The reason this process exists: great YouTube videos aren't just topics recorded on camera. They're strategically planned. A clear outcome for the viewer. A reason this video deserves to exist on the channel. Defined talking points. Concrete proof or demos. Rushing to scripting or filming without a brief produces shallow, unfocused videos that waste production time. The brief is the thinking that makes the video good.
Non-negotiable rules:
- Never skip a step. Never combine steps. Never output a finished brief before Step 6.
- Every step: you suggest multiple options. The user chooses. We lock it. We move on.
- If something doesn't align with the ICP or YouTube strategy, say so. Be honest, not a yes-machine.
- The more clearly defined each decision is, the better. Vague decisions = vague video.
Reference Documents
You have access to these knowledge sources in the references/ folder (relative to this SKILL.md). Read them when specified in each step.
| Document | What it contains | When to read |
|---|---|---|
icp-ideal-customer-profile.md |
Who Ben's audience is — their pain points, desires, segments | Steps 1, 2, 3, 4, 5 |
youtube-strategy.md |
Ben's YouTube channel strategy, content pillars, what performs well | Steps 1, 2, 3 |
what-we-do-offer.md |
Ben's business, products, positioning, unique approach | Steps 2, 3, 5 |
voice-personality.md |
Tone attributes, core message, content philosophy | Steps 2, 4 |
ben-profile-background.md |
Ben's personal story, milestones, beliefs, what sets him apart | Steps 2, 5 (when personal angles matter) |
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.
- 7d ago First seen · 289 lines · 205 tokens per session scan A 5e7a18b7f1a8
youtube-brief is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed yesterday), licensed MIT. It adds 205 tokens to every session and 3,690 once invoked, about $0.0010 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 2026-09-05.
Other skills, from other repositories
project
A single starting point for setting up an AI-assisted project in Claude Cowork. It asks questions about the work, reviews available add-ons, and creates project instructions, custom agents, and connected workflows.
design-sync-upload
An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.
doc-html-slide
A renderer that turns presentation content into a single HTML slide deck that opens directly in a browser. It creates a 16:9 slide sequence with navigation, fullscreen viewing, printing to PDF, and speaker-note controls.
cs-channel-message
A channel-message writing tool for search ads, advertising, customer relationship messages, and app notifications. It uses the NCM sequence—Need, Channel, Moment, Message, and CTA—to adapt wording to where and when customers see it.
design-tokens-transformer
A converter for design tokens, which are named values for colors, fonts, spacing, borders, shadows, and motion. It translates one shared token source into CSS variables and Tailwind or shadcn-style theme files, and can convert them back for checking.
media-higgsfield-explainer
A Higgsfield workflow for making non-photorealistic narrated explainer videos. It pairs each narration line with a 10-second animated clip and joins the clips into one finished video.