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 escapeboy/ai-prompts --skill video-digestgit clone --depth 1 https://github.com/escapeboy/ai-promptsWrote 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/escapeboy/ai-prompts/video-digest)<a href="https://agentmods.dev/skills/escapeboy/ai-prompts/video-digest"><img src="https://agentmods.dev/badge/skills/escapeboy/ai-prompts/video-digest/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/escapeboy/ai-prompts/video-digest"><img src="https://agentmods.dev/badge/skills/escapeboy/ai-prompts/video-digest.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 | $0.00135 | $0.01711 |
| Opus 5.5 | $0.00054 | $0.00684 |
| Sonnet 5.5 | $0.00027 | $0.00342 |
| Haiku 4.5 | $0.00014 | $0.00171 |
Grade A, and why
video-digest 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 13d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
video-digest
Video → text → digest → related notes → fact check → (optionally) knowledge store.
When to Use (and When NOT to)
| Use it | Don't — a simpler path wins |
|---|---|
| A video/podcast link or a local recording, and you want to know what it says | You need a verbatim transcript to publish. Run only scripts/fetch_text.py, skip the digest |
| A lecture or meeting recording that should become a note | The video is behind a login or paywall. Do not work around it |
| You want agents to learn something specific from a video | It is a text article. Read it directly |
Requirements
brew install yt-dlp deno ffmpeg— since late 2025 yt-dlp needs a JavaScript runtime (Deno) for full YouTube support.- Apple Silicon for local transcription:
uv tool install parakeet-mlxanduv tool install mlx-whisper. Models (mlx-community/parakeet-tdt-0.6b-v3~1.2 GB,mlx-community/whisper-large-v3-turbo~1.6 GB) download on first use. - Without Apple Silicon the subtitle path still works; for transcription swap the two
asr_*functions in the script for whisper.cpp or faster-whisper.
Flow
1. Text
python3 ~/.claude/skills/video-digest/scripts/fetch_text.py "<url|path>" --out <scratch-dir>/video-digest/<slug>
- Default order: manual subtitles → auto subtitles (spoken language) → Parakeet (25 European languages) → Whisper (everything else).
--lang <code>when the language is known — helps local files and videos without language metadata.--engine whisperif Parakeet does poorly (heavy noise, music, a lot of language mixing).--engine parakeetforces transcription when auto subtitles are too poor.- The script prints JSON with
title,author,duration,language,description,chapters,transcript_source,words,transcript(path to the text). The transcript has a## [mm:ss] Titleline before each chapter. - Measured on an M4 Pro: subtitles ~5 s; Parakeet transcribed 85 minutes of speech in 72 s (~70× real time). The first run of each model also includes its download.
- Over 3 hours: ask before transcribing.
- "JavaScript runtime" or "Sign in to confirm" errors: check
deno --versionandbrew upgrade yt-dlp. Do not pass browser cookies without explicit consent.
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.
- 13d ago First seen · 105 lines · 135 tokens per session scan A eed6cbd313c3
video-digest is a skill published in the GitHub repository escapeboy/ai-prompts (91 stars, last pushed 9d ago), licensed MIT. It adds 135 tokens to every session and 1,711 once invoked, about $0.0005 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 2026-10-03.
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…