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 davidtoby/agent-skills --skill x-video-download-normalizationgit clone --depth 1 https://github.com/davidtoby/agent-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/davidtoby/agent-skills/x-video-download-normalization)<a href="https://agentmods.dev/skills/davidtoby/agent-skills/x-video-download-normalization"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/x-video-download-normalization/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/davidtoby/agent-skills/x-video-download-normalization"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/x-video-download-normalization.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 | $0.00072 | $0.01007 |
| Opus 5 | $0.00036 | $0.00504 |
| Sonnet 5 | $0.00014 | $0.00201 |
| Haiku 4.5 | $0.00007 | $0.00101 |
Grade C, and why
x-video-download-normalization scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$TMP" How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
X Video Download Normalization
Use this for X/Twitter video downloads when consistency matters more than preserving source filenames.
Workflow
- Save all X video downloads under one shared directory:
~/.Hermes/workspace/output/x_videos/
- Derive a generic filename from the account handle and tweet/status ID:
x_video_<handle>_<statusid>.mp4
- Download with
yt-dlpinto a temp subfolder first. - If the downloaded container is already
.mp4, move it into place. - If it is not
.mp4, convert it to mp4 with ffmpeg:- video:
libx264 - audio:
aac
- video:
- Remove the temp folder.
- Verify the result with:
ls -lhffprobe -show_entries format=duration,size:stream=codec_name,width,height -of json
Commands
Single X status URL
BASE="$HOME/.Hermes/workspace/output/x_videos"
TMP="$BASE/.tmp_<handle>_<statusid>"
mkdir -p "$TMP"
yt-dlp --no-playlist -o "$TMP/%(uploader)s_%(id)s.%(ext)s" "<x-url>"
RAW=$(find "$TMP" -maxdepth 1 -type f | head -1)
DEST="$BASE/x_video_<handle>_<statusid>.mp4"
EXT="${RAW##*.}"
if [ "$EXT" = "mp4" ]; then
mv -f "$RAW" "$DEST"
else
ffmpeg -y -i "$RAW" -c:v libx264 -c:a aac "$DEST"
fi
rm -rf "$TMP"
Verification
ls -lh "$DEST"
ffprobe -v error -show_entries format=duration,size:stream=codec_name,width,height -of json "$DEST"
Important notes
- Prefer
--no-playlistfor X URLs that include/video/1or when yt-dlp tries to treat the post as a playlist. - X status URLs may resolve internally to a different media item ID during download; preserve the user-facing status ID in the output filename anyway.
- Always report back the final saved path, duration, size, resolution, and codecs when available.
- Keep filenames generic and stable; do not reuse the long source title as the final local filename.
Pitfall: Slow HLS fragment downloads for large X videos
Some X/Twitter videos — especially long ones (30min+, 200MB+) — use HLS streaming with thousands of small fragments (e.g., 3386 fragments for a 450MB file). The default yt-dlp behavior downloads all fragments sequentially, which can take 20+ minutes on typical connections and is prone to timeout.
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.
- 6d ago First seen · 97 lines · 72 tokens per session scan C 2e9f5fb5c45c
x-video-download-normalization is a skill published in the GitHub repository davidtoby/agent-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 1,007 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
officecli-pitch-deck
Use this skill when the user is building a fundraising / investor pitch deck — seed, Series A / B / C, convertible note, SAFE round, strategic raise. Trigger on: 'pitch deck', 'investor deck', 'Series A deck', 'Series B deck', 'Series C deck', 'fundraising deck', 'seed pitch', 'VC deck', 'raising capital', 'term sheet…
morph-ppt
Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style continuous motion, shapes that grow / move / rotate as the slide advances. Trigger on: 'morph', 'morph transition', 'smooth transition', 'continuous animation across slides', 'Keynote-style…
morph-ppt-3d
3D Morph PPT — extends morph-ppt with GLB model insertion, cinematographic camera, model-content layout, and enriched visual design system.
draw
Draw - command-line tool for everyday use.
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
blockrun
Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun", "use grok", "use gpt", "dall-e", "deepseek").