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 JamalMohafil/claude-skills --skill youtube-chaptersgit clone --depth 1 https://github.com/JamalMohafil/claude-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/jamalmohafil/claude-skills/youtube-chapters)<a href="https://agentmods.dev/skills/jamalmohafil/claude-skills/youtube-chapters"><img src="https://agentmods.dev/badge/skills/jamalmohafil/claude-skills/youtube-chapters/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/jamalmohafil/claude-skills/youtube-chapters"><img src="https://agentmods.dev/badge/skills/jamalmohafil/claude-skills/youtube-chapters.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 | $0.00085 | $0.01118 |
| Opus 5.5 | $0.00034 | $0.00447 |
| Sonnet 5.5 | $0.00017 | $0.00224 |
| Haiku 4.5 | $0.00009 | $0.00112 |
Grade A, and why
youtube-chapters 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Chapters
Overview
Turn any video into ready-to-paste YouTube chapters. Two moves:
- Run the helper to get a clean, timestamped transcript.
- You cut it into chapters and output them in the exact format below.
The script handles fetching/transcribing (any language). The chaptering judgment — where topics change and what to call them — is yours.
When to use
- A YouTube URL (any language) and they want chapters / timestamps / sections.
- A local video or audio file ("here's my video, timestamp it").
- A transcript or SRT they paste — skip Step 1, go to Step 2.
Not for: summarizing without timestamps (that's just a summary), or cutting/editing the video.
Step 1 — Get a timestamped transcript
python3 scripts/transcript.py "<youtube-url-or-file-path>"
Options: --lang ar (force a language), --window 12 (seconds per line), --out t.txt (also save it).
It prints TITLE, DURATION, LANGUAGE, SOURCE, then M:SS⇥text lines:
- YouTube with captions → pulled via
yt-dlp(fast: subtitle track only, no video download, no speech-to-text). Manual subtitles beat auto-captions. - Local file, or a video with no captions → Whisper speech-to-text, using whatever is present:
GROQ_API_KEYorOPENAI_API_KEY(Whisper API), elsepip install faster-whisper, else thewhisperCLI. If none exists, the script prints exactly what to install.
Read the whole transcript before chaptering, and note DURATION — the last chapter must start before it.
Step 2 — Cut it into chapters (your judgment)
- Mark where the topic changes, not every sentence. Aim for one chapter every ~1–3 minutes — more for long videos, never fewer than 3.
- Set each chapter's time to the transcript timestamp where that topic starts (use that line's
M:SS). - The first chapter is always
0:00— retitle the opening; never invent a line before 0:00. - Keep chapters ≥ ~10s apart; the last one must start before
DURATION. - Titles: short, specific, scannable — say what the section delivers (a question or a payoff beats a vague noun). Write them in the video's spoken language; for Arabic keep it natural dialect (RTL), not formalized.
- Keep tech/brand terms in Latin for search:
Claude Code,Next.js,API,GitHub,Vercel,MCP. - Never invent content that isn't in the transcript.
What ships with it
2 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 · 81 lines · 85 tokens per session scan A 6ae887b19a42
youtube-chapters is a skill published in the GitHub repository JamalMohafil/claude-skills (27 stars, last pushed 12d ago), licensed MIT. It adds 85 tokens to every session and 1,118 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…