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 jaansokk/cursor_tools --skill yt-transcriptgit clone --depth 1 https://github.com/jaansokk/cursor_toolsWrote 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/jaansokk/cursor_tools/yt-transcript)<a href="https://agentmods.dev/skills/jaansokk/cursor_tools/yt-transcript"><img src="https://agentmods.dev/badge/skills/jaansokk/cursor_tools/yt-transcript/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/jaansokk/cursor_tools/yt-transcript"><img src="https://agentmods.dev/badge/skills/jaansokk/cursor_tools/yt-transcript.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 | $0.00104 | $0.00615 |
| Opus 5.5 | $0.00042 | $0.00246 |
| Sonnet 5.5 | $0.00021 | $0.00123 |
| Haiku 4.5 | $0.00010 | $0.00061 |
Grade A, and why
yt-transcript 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 1mo 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Transcript Fetcher
Fetches the transcript of a YouTube video and loads the full text into your context so you can work with it immediately.
How it works
There's a Python script bundled with this skill that uses youtube-transcript-api to pull subtitles directly from YouTube — no browser or API key needed. It prints plain text to stdout. You capture that output and you're ready to go.
Prerequisites
The youtube-transcript-api package must be installed:
pip install youtube-transcript-api
Check first with pip show youtube-transcript-api to avoid reinstalling.
Usage
python /path/to/yt-transcript/scripts/yt_transcript.py "<youtube_url_or_video_id>" [lang]
- First argument: any YouTube URL format (watch, shorts, embed, youtu.be) or a raw 11-character video ID
- Second argument (optional): language code. Defaults to
en. Useetfor Estonian.
The script prints the full transcript as plain text to stdout. Capture it and work with it directly — no files are created.
Workflow
- User shares a YouTube link (or video ID)
- Ensure
youtube-transcript-apiis installed - Run the script, capturing stdout
- The transcript is now in your context — proceed with whatever the user needs (summarize, answer questions, extract key points, feed into another skill, etc.)
Language handling
- Default: English (
en) - If the user asks for Estonian or the video is in Estonian, use
et - The script prefers manual subtitles over auto-generated ones when available
Error handling
If the script fails (e.g., no transcript available, video is private, invalid URL), relay the error to the user clearly. Common issues:
- "Could not extract a valid YouTube video ID" — the URL format wasn't recognized
- Transcript not available — the video may not have subtitles, or they may be disabled
- Network errors — check connectivity
Important notes
- This skill is designed for Claude Code where the script runs on the user's machine with direct network access. It will not work in sandboxed environments that block youtube.com.
- The transcript text can be long for lengthy videos. That's fine — just work with it in context.
- Don't save transcript files unless the user explicitly asks for it.
What ships with it
1 file 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.
- 1mo ago First seen · 60 lines · 104 tokens per session scan A f5ca5394ae93
yt-transcript is a skill published in the GitHub repository jaansokk/cursor_tools (1 stars, last pushed 7mo ago), licensed MIT. It adds 104 tokens to every session and 615 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
ab-testing-framework
Design, run, and analyze A/B tests (controlled experiments) using Ronny Kohavi's methodology and Gibson Biddle's DHM trade-off analysis. Use when the user needs to plan an experiment, choose metrics (OEC), evaluate statistical significance, assess sample size requirements, avoid common experimentation pitfalls, or…
continuous-discovery
Guide teams through building sustainable customer interview habits and discovery practices. Use when setting up weekly customer interviews, preparing interview guides, coaching story-based interviewing technique, synthesizing user research findings, planning assumption tests, or helping teams that say they don't have…
prd-writer
Guide users through writing Product Requirements Documents (PRDs) and decomposing them into executable technical tasks. Use when creating a PRD, product spec, product one-pager, feature brief, PRP, or when breaking requirements into tasks with estimates, sprint planning, or technical decomposition.
product-led-growth-playbook
Evaluate growth strategy, growth team structure, and go-to-market motions using Elena Verna's PLG frameworks. Use when the user asks about product-led growth, PLG, growth team hiring, self-serve vs sales-led motions, product-led sales, PQA/PQL models, growth loops, when to hire a head of growth, earned vs rented…
ai-evals-builder
Build AI evals using the Husain-Shankar framework (error analysis, open/axial coding, LLM-as-judge). Use when a user needs to create, improve, or debug evals for an AI product — including defining failure modes, building LLM judges, or setting up production monitoring for an LLM application.
dhm-strategy-framework
Evaluate and strengthen product strategy using Gibson Biddle's DHM framework (Delight, Hard-to-copy, Margin-enhancing). Use when the user asks about product strategy, competitive advantage, feature prioritization trade-offs, or wants to stress-test whether a product idea is strategically sound.