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 agentmods add skills/itamarzand88/cli-anything-web/youtube-clinpx skills add ItamarZand88/CLI-Anything-WEB --skill youtube-cligit clone --depth 1 https://github.com/ItamarZand88/CLI-Anything-WEBWrote 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/itamarzand88/cli-anything-web/youtube-cli)<a href="https://agentmods.dev/skills/itamarzand88/cli-anything-web/youtube-cli"><img src="https://agentmods.dev/badge/skills/itamarzand88/cli-anything-web/youtube-cli.svg" alt="Measured on agentmods" 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 | $0.00105 | $0.00799 |
| Opus 5 | $0.00053 | $0.00400 |
| Sonnet 5 | $0.00021 | $0.00160 |
| Haiku 4.5 | $0.00011 | $0.00080 |
Grade A, and why
youtube-cli 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 5d 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.
cli-web-youtube
Search and explore YouTube from the terminal (read-only, no auth, InnerTube API).
Install: pip install cli-web-youtube
Commands
| Command | Purpose | Key options |
|---|---|---|
search videos QUERY |
Search videos | -l/--limit N (default 10) |
video get VIDEO_ID |
Video details (views, duration, description, keywords) | accepts 11-char ID or full URL |
trending list |
Trending/popular videos | -c/--category now|music|gaming|movies, -l/--limit N |
channel get HANDLE |
Channel info + recent videos | accepts @handle, UC... ID, or URL |
transcript get VIDEO |
Timestamped transcript + full text | -l/--lang CODE (repeatable, priority order), -t/--translate CODE, --text-only; accepts ID or URL |
transcript list VIDEO |
Available caption languages | accepts ID or URL |
Examples
# Search (returns id, title, channel, views, duration, published, url per video)
cli-web-youtube search videos "python tutorial" --limit 5 --json
# Video details by ID or URL
cli-web-youtube video get dQw4w9WgXcQ --json
# Trending music videos
cli-web-youtube trending list --category music --limit 10 --json
# Channel info and subscriber count
cli-web-youtube channel get @mkbhd --json | jq '{title, subscriber_count}'
# Plain-text transcript (ideal for feeding to an LLM)
cli-web-youtube transcript get dQw4w9WgXcQ --text-only
# Transcript in a preferred language, or translated, as JSON
cli-web-youtube transcript get dQw4w9WgXcQ --lang en --json
cli-web-youtube transcript get dQw4w9WgXcQ --translate en --json | jq -r '.segments[].text'
# What caption languages exist?
cli-web-youtube transcript list dQw4w9WgXcQ --json
JSON output
Every command accepts --json. Success returns the data object directly, e.g. search: {"query", "estimated_results", "videos": [...]}; video get: {"id", "title", "channel", "views", "duration_seconds", ...}; transcript get: {"video_id", "title", "language_code", "kind", "is_translated", "segment_count", "segments": [{"text", "start", "duration"}], "text"}. Errors return {"error": true, "code": "...", "message": "..."}.
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.
- 5d ago First seen · 60 lines · 105 tokens per session scan A 592078f96c26
youtube-cli is a skill published in the GitHub repository ItamarZand88/CLI-Anything-WEB (215 stars, last pushed 3d ago), licensed MIT. It adds 105 tokens to every session and 799 once invoked, about $0.0005 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
scrapling-official
Scrape web pages using Scrapling with anti-bot bypass (like Cloudflare Turnstile), stealth headless browsing, spiders framework, adaptive scraping, and JavaScript rendering. Use when asked to scrape, crawl, or extract data from websites; webfetch fails; the site has anti-bot protections; write Python code to…
playwright-test-generator
Use when someone wants to add, write, create, or scaffold new Playwright end-to-end tests for a page, flow, form, component, uncovered route, or first-project setup. The skill analyzes coverage gaps, explores live pages only on local/disposable or externally isolated approved non-production targets, proposes scenarios…
playwright-test-generator
Use this skill to generate new Playwright end-to-end tests from scratch — for a page, a user flow, a form, or a component — taking them from zero to reviewed, passing specs. Reach for it whenever someone wants to add, write, create, or scaffold Playwright E2E coverage, fill coverage gaps for uncovered routes, or…
qa-explore
Exploratory end-to-end QA with a team of agents that drive a real browser like human testers — they click through the whole app, create/fill/submit, screenshot and visually judge rendering + data correctness, capture trace/HAR/console/video evidence, adversarially verify each finding, learn from rejected findings, and…
agent-browser
Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Alternative to Playwright MCP - uses Bash commands with ref-based element selection. Triggers on "browse website", "fill form", "click button", "take screenshot", "scrape…
ubrowser
Control a headless browser with 98% token reduction compared to Playwright MCP and Dev Browser. Uses batch execution, minimal responses, and efficient HTML formatting.