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 feiskyer/codex-settings --skill youtube-transcribe-skillgit clone --depth 1 https://github.com/feiskyer/codex-settingsWrote 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/feiskyer/codex-settings/youtube-transcribe-skill)<a href="https://agentmods.dev/skills/feiskyer/codex-settings/youtube-transcribe-skill"><img src="https://agentmods.dev/badge/skills/feiskyer/codex-settings/youtube-transcribe-skill/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/feiskyer/codex-settings/youtube-transcribe-skill"><img src="https://agentmods.dev/badge/skills/feiskyer/codex-settings/youtube-transcribe-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 55 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
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 | $0.00058 | $0.00659 |
| Opus 5 | $0.00029 | $0.00329 |
| Sonnet 5 | $0.00012 | $0.00132 |
| Haiku 4.5 | $0.00006 | $0.00066 |
Grade A, and why
youtube-transcribe-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Transcript Extraction
Use the bundled scripts/transcribe_youtube.py wrapper for the primary workflow. It downloads subtitles with yt-dlp, selects the preferred language, converts WebVTT cues into timestamped plain text, and reports the output path and line count.
Requirements
- Install
yt-dlpand confirmyt-dlp --versionsucceeds. - Resolve the absolute directory containing this
SKILL.md; refer to it as<skill-dir>. - Keep the output in the user's current working directory unless they request another location.
The Python wrapper itself uses only the standard library. It can display --help without yt-dlp being installed.
Primary workflow
Run without browser cookies first:
python3 "<skill-dir>/scripts/transcribe_youtube.py" \
"<youtube-url>" \
--output-dir "$PWD"
The default language preference is Simplified Chinese, Traditional Chinese, other Chinese variants, then English. Override it when the user requests another language:
python3 "<skill-dir>/scripts/transcribe_youtube.py" \
"<youtube-url>" \
--languages "ja.*,en.*" \
--output-dir "$PWD"
The wrapper supports normal watch URLs plus youtu.be, Shorts, live, and embed URLs. A successful run writes one .txt file whose non-empty lines use this shape:
00:03 Subtitle text
00:08 Next subtitle text
Cookie retry
Do not read browser cookies by default. If the initial command fails specifically because the video requires sign-in, age verification, membership, or another authenticated session:
- Explain that the retry will let
yt-dlpread YouTube cookies from a local browser profile. - Ask the user which browser profile they approve using.
- Retry only after approval:
python3 "<skill-dir>/scripts/transcribe_youtube.py" \
"<youtube-url>" \
--cookies-from-browser chrome \
--output-dir "$PWD"
Never print, copy, or persist browser cookies in the transcript or logs.
Browser fallback
Use browser automation only when yt-dlp is unavailable or cannot obtain subtitles and an appropriate browser-control capability is available.
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 · 80 lines · 58 tokens per session scan A 1851655e2427
youtube-transcribe-skill is a skill published in the GitHub repository feiskyer/codex-settings (236 stars, last pushed 26d ago), licensed MIT. It adds 58 tokens to every session and 659 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 2026-08-30.
Other skills, from other repositories
gpt-image-skill
A skill for generating or editing images through OpenAI's GPT Image API, a programming interface for requesting image operations. It uses a bundled Python script and supports configuration such as model, size, quality, and output file.
nanobanana-skill
An image-generation and image-editing skill that uses Google Gemini through the Nanobanana tool. It covers prompts, image sizes, output files, models, resolutions, and required setup.
feature-demo-recording
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…
image-authoring
Author images and diagrams as code — SVG, Pillow, Excalidraw, mermaid. Load when asked to draw, illustrate, or make an image, icon, logo, poster, or diagram.
pptx-maker
Generate or restyle a PowerPoint deck. Use when the user wants to create or edit a .pptx presentation, build slides from text or a URL, or design a reusable slide style.
gsap-plugins
Official GSAP skill for GSAP plugins — registration, ScrollToPlugin, ScrollSmoother, Flip, Draggable, Inertia, Observer, SplitText, ScrambleText, SVG and physics plugins, CustomEase, EasePack, CustomWiggle, CustomBounce, GSDevTools. Use when the user asks about a GSAP plugin, scroll-to, flip animations, draggable, SVG…