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 wyattowalsh/agents --skill yt-dlpgit clone --depth 1 https://github.com/wyattowalsh/agentsWrote 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/wyattowalsh/agents/yt-dlp)<a href="https://agentmods.dev/skills/wyattowalsh/agents/yt-dlp"><img src="https://agentmods.dev/badge/skills/wyattowalsh/agents/yt-dlp/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/wyattowalsh/agents/yt-dlp"><img src="https://agentmods.dev/badge/skills/wyattowalsh/agents/yt-dlp.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 | $0.00057 | $0.02714 |
| Opus 5.5 | $0.00023 | $0.01086 |
| Sonnet 5.5 | $0.00011 | $0.00543 |
| Haiku 4.5 | $0.00006 | $0.00271 |
Grade A, and why
yt-dlp scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Scope:** Supported video/audio hosts via `yt-dlp`, user-owned cookie files, playlist metadata, and local output under an explicit directory. **NOT for:** static page fetch (use Fetch MCP or `curl`), broad multi-source How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
yt-dlp
CLI skill for yt-dlp: read-only URL probes, caption/transcript extraction, and optional media download. Follow the transcript-first protocol before any download.
Scope: Supported video/audio hosts via yt-dlp, user-owned cookie files, playlist metadata, and local output under an explicit directory. NOT for: static page fetch (use Fetch MCP or curl), broad multi-source research (research), ffmpeg transform recipes (ffmpeg), or bypassing platform Terms of Service.
Canonical Vocabulary
| Term | Meaning | NOT |
|---|---|---|
| probe | Read-only metadata via --dump-json; no media write |
download |
| transcript | Captions/subtitles to text files; prefer over full download | audio rip by default |
| download | Persist media bytes after probe + user approval | silent bulk grab |
| playlist | Multi-entry URL; enumerate before selective download | blind full-playlist download |
| cookies | User-owned Netscape cookie file passed with --cookies |
committed or skill-bundled secrets |
| doctor | Preflight JSON report for binary, version, ffmpeg | live URL smoke |
| format id | yt-dlp format_id from probe (e.g. 251, 137+140) |
guessed extension |
| manual sub | Creator-uploaded captions | auto-generated only |
| auto sub | Platform-generated captions | guaranteed accuracy |
Dispatch
$ARGUMENTS |
Mode | Action |
|---|---|---|
probe <url> / metadata <url> / info <url> |
Probe | Run bundled probe_url.py; summarize title, id, duration, subs |
transcript <url> / subs <url> / captions <url> |
Transcript | Probe first; extract best available subtitles without video download |
download <url> / fetch <url> / save <url> |
Download | Probe first; confirm rights + format; download to explicit output dir |
playlist <url> |
Playlist | Probe with playlist allowed; list entries; selective download only with approval |
cookies <path> / cookies check <path> |
Cookies | Validate user-owned cookie file path; never copy into repo |
doctor / preflight |
Doctor | Run scripts/doctor.py --format json |
| Natural language: "what is this video", "get subtitles", "download this" | Auto | Map to probe → transcript → download per protocol below |
| (empty) | Help | Show modes, protocol, ethics pointer, and examples |
What ships with it
8 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.
- evals/evals.json 6.1 KB
- references/ethics-and-tos.md 3.8 KB
- references/formats-and-quality.md 1.6 KB
- references/troubleshooting.md 1.9 KB
- scripts/asset_toolkit/validate_hooks.py 13 KB runs code
- scripts/check.py 2.6 KB runs code
- scripts/doctor.py 4.0 KB runs code
- scripts/probe_url.py 5.4 KB runs code
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 · 259 lines · 57 tokens per session scan A cde79880e43b
yt-dlp is a skill published in the GitHub repository wyattowalsh/agents (5 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 2,714 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…