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 JuanMarchetto/agent-skills --skill youtube-devrelgit clone --depth 1 https://github.com/JuanMarchetto/agent-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/juanmarchetto/agent-skills/youtube-devrel)<a href="https://agentmods.dev/skills/juanmarchetto/agent-skills/youtube-devrel"><img src="https://agentmods.dev/badge/skills/juanmarchetto/agent-skills/youtube-devrel/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/juanmarchetto/agent-skills/youtube-devrel"><img src="https://agentmods.dev/badge/skills/juanmarchetto/agent-skills/youtube-devrel.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 | $0.00075 | $0.01457 |
| Opus 5.5 | $0.00030 | $0.00583 |
| Sonnet 5.5 | $0.00015 | $0.00291 |
| Haiku 4.5 | $0.00007 | $0.00146 |
Grade A, and why
youtube-devrel 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 2mo 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube DevRel
Generate developer YouTube content — from idea to publish-ready assets.
Workflow
Given a video idea, produce:
-
Title — SEO-optimized using proven formulas:
[Tech] Tutorial: [What you'll build]— "React Tutorial: Build a Todo App from Scratch"How to [Task] with [Tech]— "How to Deploy to AWS with Docker"[Tech A] vs [Tech B]: Which is Better?— "Next.js vs Remix: Which Should You Learn?"[Number] [Topic] Tips in [Time]— "10 VS Code Tips in 10 Minutes"Why I [Action] [Tech]— "Why I Switched from React to Svelte"
-
Description — first 150 chars keyword-rich, timestamps placeholder, resource links, hashtags:
[First 150 chars: Compelling summary with main keyword] In this video, I'll show you [what they'll learn]. Timestamps: 0:00 - Introduction 2:00 - [Section 1] [...] Resources mentioned: - [Link 1] - [Link 2] Links: - My website: [URL] - GitHub repo: [URL] - Discord: [URL] #[keyword1] #[keyword2] #[keyword3] -
Outline — timed segments with hook (first 30s shows end result), chapters, CTA placement:
0:00 - Hook (show the finished result) 0:30 - Prerequisites & setup 2:00 - Concept explanation (why this matters) 4:00 - Step 1: [First major step] 8:00 - Step 2: [Second major step] ... XX:00 - Final result demo XX:30 - Recap & next steps XX:45 - CTA (subscribe, comment) -
Script Notes — key points per segment (not verbatim script — bullet points to talk from)
-
Thumbnail Brief — text (3-5 words), composition (face + logo + emotion), colors:
- Patterns that work: Face + tech logo + emotion, Before/after, Big text + icon, Comparison, Result preview
- High contrast, brand consistent colors
- Rule of thirds composition
-
Tags — 10-15 relevant tags mixing broad and specific
For Shorts:
- Hook in first 2 seconds
- One concept, 30-45 seconds
- Big on-screen captions
- Vertical format (9:16)
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.
- 2mo ago First seen · 149 lines · 75 tokens per session scan A d9d53a4593ca
youtube-devrel is a skill published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 7mo ago), licensed MIT. It adds 75 tokens to every session and 1,457 once invoked, about $0.0003 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 2026-09-03.
youtube-devrel compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| youtube-devrelJuanMarchetto/agent-skills | Skill | 5 | 7mo ago | MIT | A | 75 | Claude Code |
| x402browser-use/browser-use | Skill | 121k | yesterday | MIT | A | 166 | Claude Code |
| browser-usebrowser-use/browser-use | Skill | 121k | yesterday | MIT | A | 54 | Claude Code, Codex |
| open-sourcebrowser-use/browser-use | Skill | 121k | yesterday | MIT | A | 101 | Claude Code |
| remote-browserbrowser-use/browser-use | Skill | 121k | yesterday | MIT | A | 22 | Claude Code |
| cloudbrowser-use/browser-use | Skill | 121k | yesterday | MIT | A | 177 | Claude Code |
| opencli-autofixjackwener/OpenCLI | Skill | 31k | 4d ago | Apache-2.0 | A | 61 | Claude Code |