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 yaxeen/storytelling-skills --skill long-form-youtubegit clone --depth 1 https://github.com/yaxeen/storytelling-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/yaxeen/storytelling-skills/long-form-youtube)<a href="https://agentmods.dev/skills/yaxeen/storytelling-skills/long-form-youtube"><img src="https://agentmods.dev/badge/skills/yaxeen/storytelling-skills/long-form-youtube/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/yaxeen/storytelling-skills/long-form-youtube"><img src="https://agentmods.dev/badge/skills/yaxeen/storytelling-skills/long-form-youtube.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 | $0.00048 | $0.01664 |
| Opus 5 | $0.00024 | $0.00832 |
| Sonnet 5 | $0.00010 | $0.00333 |
| Haiku 4.5 | $0.00005 | $0.00166 |
Grade A, and why
long-form-youtube 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 12d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Long-Form YouTube Scripts
- Short-form wins the first 2 seconds; long-form must win the next 20 minutes.
- Retention is a chain of open loops: every section opens the next before it closes itself.
- Built on the six levers — see storytelling-hooks for the full psychology. One-line recap:
- Curiosity gap · 2. Emotional mirror · 3. Conflict engine · 4. Relatability · 5. Pattern + surprise · 6. Three-act structure.
When to Use
- Writing a YouTube video script, tutorial, essay, story, review, or explainer.
- Planning structure/outline before scripting, or diagnosing a video that "loses people in the middle".
- Any niche: education, tech, finance, vlog, documentary, business, faith.
Packaging First (Before Any Scripting)
- Lock the title + thumbnail pair before outlining. The video is written to deliver on the pack, not the other way around — a great script under a weak pack never gets watched. Use titles-and-thumbnails for the pair.
- Define the target viewer in one sentence: who exactly should click and stay (stage, situation, private worry) — not "everyone interested in X". Every relatability and stakes choice flows from this. The right viewer retained beats the most viewers clicked.
- Intake before outlining: confirm topic + the user's points, target runtime, audience avatar, goal (subs / sales / session time), and the next video to tease. Always ask for the user's own points if they say they have them — never substitute assumed points for real ones. Everything else may be assumed explicitly if the user can't respond.
Video Skeleton (Quick Reference)
| Section | Time | Job | Lever focus |
|---|---|---|---|
| Hook | 0:00–0:30 | Stop the click-away, make a promise | 1, 4, 2 |
| Setup | 0:30–1:30 | Frame the stakes, preview the payoff | 3, 6 |
| Body (chapters) | bulk | Deliver value as a loop chain | all |
| Sag point | ~40–60% | Re-hook before attention drops | 1, 5 |
| Payoff | near end | Resolve the opening promise | 6 |
| Outro/CTA | last 15s | One next action | 1 |
What ships with it
1 file 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.
- 12d ago First seen · 121 lines · 48 tokens per session scan A 7263c517a545
long-form-youtube is a skill published in the GitHub repository yaxeen/storytelling-skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 1,664 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 2026-08-31.
Other skills, from other repositories
self-media-content-brief
A short planning document for deciding what content to make, for whom, on which platform, and with what evidence.
self-media-content-workflow
A general workflow for planning, creating, adapting, reviewing, and archiving social-media content.
self-media-platform-copywriting
A writing workflow for turning an approved topic, evidence, and brief into posts for platforms such as X, Xiaohongshu, WeChat, and short-video apps.
self-media-short-video
A planning and production guide for vertical short videos on platforms such as TikTok, Xiaohongshu, and WeChat Channels.
self-media-wechat-publisher
A publishing workflow that turns approved Markdown into formatted WeChat articles or image posts and saves them as drafts.
self-media-content-analytics
A review process for measuring and learning from social-media content using screenshots, exported files, tables, links, or other supplied data.