Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/liang121/video-summarizernpx agentmods add skills/liang121/video-summarizer/video-summarizerWrote 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/liang121/video-summarizer/video-summarizer)<a href="https://agentmods.dev/skills/liang121/video-summarizer/video-summarizer"><img src="https://agentmods.dev/badge/skills/liang121/video-summarizer/video-summarizer/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/liang121/video-summarizer/video-summarizer"><img src="https://agentmods.dev/badge/skills/liang121/video-summarizer/video-summarizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk warn
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 | $0.00132 | $0.01615 |
| Opus 5 | $0.00066 | $0.00807 |
| Sonnet 5 | $0.00026 | $0.00323 |
| Haiku 4.5 | $0.00013 | $0.00161 |
Grade A, and why
video-summarizer 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 9d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Summarizer
Overview
Download videos from any platform and generate a complete resource package including:
- Original video file (mp4)
- Audio file (mp3)
- Subtitle file (with timestamps, vtt/srt format)
- Summary file (summary.md)
Supports all 1800+ websites supported by yt-dlp.
Trigger Conditions
When the user:
- Provides a video link and asks for a summary
- Says "summarize this video", "what's in this video"
- Asks to "extract video content", "transcribe video"
- Says "download this video"
- Provides a link from YouTube/Bilibili/Twitter/Vimeo/TikTok etc.
Supported Platforms
- YouTube (youtube.com, youtu.be)
- Bilibili (bilibili.com, b23.tv)
- Twitter/X (x.com, twitter.com)
- Vimeo (vimeo.com)
- TikTok (tiktok.com)
- Instagram (instagram.com)
- Twitch (twitch.tv)
- And 1800+ other platforms (all sites supported by yt-dlp)
Output Structure
All files are saved to downloads/<video-title>/ in the current working directory:
./downloads/
└── <video-title>/
├── video.mp4 # Original video
├── audio.mp3 # Extracted audio
├── subtitle.vtt # Subtitles with timestamps
├── transcript.txt # Plain text transcript (no timestamps)
└── summary.md # Structured summary
Workflow
Step 1: Install Dependencies
Run the install script to check and install all dependencies:
bash "$SKILL_DIR/scripts/install_deps.sh"
This installs: uv (Python package manager), ffmpeg, yt-dlp, and checks Python version. faster-whisper will be automatically managed by uv.
Step 2: Get Video Info and Create Output Directory
# Get video title (sanitize special characters for folder name)
TITLE=$(yt-dlp --print "%(title)s" "VIDEO_URL" | sed 's/[/:*?"<>|]/_/g' | cut -c1-80)
DURATION=$(yt-dlp --print "%(duration)s" "VIDEO_URL")
# Create output directory
OUTPUT_DIR=./downloads/"$TITLE"
mkdir -p "$OUTPUT_DIR"
Step 3: Download Video and Audio
# Download video (mp4 format, best quality up to 1080p)
yt-dlp -f "bestvideo[height<=1080][ext=mp4]+bestaudio[ext=m4a]/best[height<=1080][ext=mp4]/best" \
--merge-output-format mp4 \
-o "$OUTPUT_DIR/video.%(ext)s" "VIDEO_URL"
# Extract audio (mp3 format)
yt-dlp -x --audio-format mp3 -o "$OUTPUT_DIR/audio.%(ext)s" "VIDEO_URL"
What ships with it
3 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.
- 9d ago First seen · 188 lines · 132 tokens per session scan A bbb70906bda1
video-summarizer is a skill published in the GitHub repository liang121/video-summarizer (53 stars, last pushed 7mo ago), licensed MIT. It adds 132 tokens to every session and 1,615 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.