A media downloader and transcription tool for video and audio websites. It can download media, extract audio, fetch subtitles, transcribe speech into text, and search YouTube.

Use it to download videos or MP3s, get video information, fetch subtitles, transcribe local or online files, and search YouTube.

It removes the need to use separate tools for downloading media, obtaining subtitles, and turning speech into text.

media-fetch — Skill for Claude Code and Codex by JansenAnalytics: A media downloader and transcription tool for video and…

Install

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.

agentmods

npx agentmods add skills/jansenanalytics/claudex/media-fetch

Any agent

npx skills add JansenAnalytics/claudex --skill media-fetch

Clone the repo

git clone --depth 1 https://github.com/JansenAnalytics/claudex

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jansenanalytics/claudex/media-fetch.svg)](https://agentmods.dev/skills/jansenanalytics/claudex/media-fetch)

Your own site

<a href="https://agentmods.dev/skills/jansenanalytics/claudex/media-fetch"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/media-fetch.svg" alt="Measured on agentmods" height="20"></a>

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,064 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00067	$0.02064
Opus 5	$0.00034	$0.01032
Sonnet 5	$0.00013	$0.00413
Haiku 4.5	$0.00007	$0.00206

Measured yesterday against content hash fd815a084c20, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

media-fetch 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 yesterday.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/batch.py, scripts/fetch.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/media-fetch/SKILL.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Media Fetch

Download, extract, and transcribe media from 1000+ sites. Built on yt-dlp + ffmpeg + Whisper.

Scripts: ${CLAUDE_SKILLS_DIR:-$HOME/.claude-agent/.claude/skills}/media-fetch/scripts/ Downloads: ~/.media-fetch/downloads/ Transcripts: ~/.media-fetch/transcripts/ Metadata: ~/.media-fetch/metadata/

Quick Reference

S=${CLAUDE_SKILLS_DIR:-$HOME/.claude-agent/.claude/skills}/media-fetch/scripts

# Download video (best quality)
python3 $S/fetch.py URL

# Audio only (MP3)
python3 $S/fetch.py URL --audio

# Download + transcribe (the "summarize this video" workflow)
python3 $S/fetch.py URL --transcript

# Subtitles only (fastest — no download needed)
python3 $S/fetch.py URL --subs

# Video info (no download)
python3 $S/fetch.py URL --info

# Search YouTube
python3 $S/fetch.py --search "prop trading strategies"

# Extract audio from local file
python3 $S/batch.py --file video.mp4 --extract-audio

# Transcribe local audio/video
python3 $S/batch.py --file audio.mp3 --transcribe

Commands — fetch.py

Video Info (No Download)

python3 fetch.py URL --info
python3 fetch.py URL --info --json    # Machine-readable

Shows: title, channel, duration, views, likes, description, chapters, available formats, subtitle languages, best video/audio quality.

Download Video

python3 fetch.py URL                       # Best quality MP4
python3 fetch.py URL --quality 720         # Max 720p
python3 fetch.py URL --quality 480         # Max 480p
python3 fetch.py URL -o /tmp/videos        # Custom output dir
python3 fetch.py URL --format "bestvideo[height<=1080]+bestaudio"  # Custom format

Download Audio Only

python3 fetch.py URL --audio               # MP3, best quality
python3 fetch.py URL --audio --clip 5:00-10:00   # Extract clip

Download Subtitles Only

The fastest way to get video content — no media download needed:

python3 fetch.py URL --subs                    # English subtitles
python3 fetch.py URL --subs --sub-lang en,no   # English + Norwegian
python3 fetch.py URL --subs --sub-lang auto    # Auto-generated captions

Read the full file on GitHub · 268 lines

Files

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.

Changes

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.

yesterday First seen · 268 lines · 67 tokens per session scan A fd815a084c20

Subscribe to this mod's changes

media-fetch is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 2,064 once invoked, about $0.0003 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 2026-09-03.

Creative and media ffmpeg media transcription whisper youtube yt-dlp

youtube-transcribe

YouTube 视频 → 下载 → 转录 → 翻译 → 存为 Markdown。支持中英文，英文内容自动翻译成中文，输出中英对照。.

chubbyguan/chubbyskills · 41 tokens

remotion-video

Use when you need to render an actual video file with Remotion — React compositions, the Composition/Sequence/TransitionSeries graph, transitions, burned-in word-by-word captions from a transcript, automatic silence removal, b-roll overlays, headless CI renders, and a final MP4 or MOV. NOT writing the script, hook…

ericrisco/rsc-harness · 116 tokens

media-transcription

Run, monitor, cancel, and resume the durable media transcription pipeline (media-transcription-pipeline-v2) for raw meeting media on /Volumes/badass-media. Use when the user asks to transcribe a meeting or media file from the NAS, check transcription progress, cancel a transcription, resume a failed/partial run, or…

joelhooks/joelclaw · 86 tokens

media-fetch