lyt: Skill for Claude Code

.agents/skills/lyt/SKILL.md

lyt is a skill for Claude Code, Codex from TanaTTV/lyt. It costs 46 tokens per session (1,827 once invoked), scanned A, original, MIT.

A command-line tool for downloading permitted audio and video from YouTube and other sites supported by yt-dlp, a media-download program. It can inspect available formats and save files locally.

In plain words
What is it for?
Use it to download media you own or have permission to use, extract MP3 audio, choose quality, make clips, inspect formats, and save files to exact local paths.
Why use it?
It avoids manually figuring out download formats, quality options, and output locations. It also lets you inspect a link before starting a download.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is TanaTTV/lyt's own configuration. It tells Claude Code and Codex how to work on lyt itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything lyt configures →

Reuse

Borrowing it

Nothing to install: this file belongs to TanaTTV/lyt. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/TanaTTV/lyt/main/.agents/skills/lyt/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/TanaTTV/lyt

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for lyt

README.md
[![agentmods](https://agentmods.dev/badge/skills/tanattv/lyt/lyt/github.svg)](https://agentmods.dev/skills/tanattv/lyt/lyt)
Your own site
<a href="https://agentmods.dev/skills/tanattv/lyt/lyt"><img src="https://agentmods.dev/badge/skills/tanattv/lyt/lyt/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.

agentmods 80×15 button for lyt

Your own site · 80×15
<a href="https://agentmods.dev/skills/tanattv/lyt/lyt"><img src="https://agentmods.dev/badge/skills/tanattv/lyt/lyt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,827 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.01827
Opus 5.5 $0.00018 $0.00731
Sonnet 5.5 $0.00009 $0.00365
Haiku 4.5 $0.00005 $0.00183

Measured 1mo ago against content hash bb1eb8d93de0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lyt 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.

.agents/skills/lyt/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use lyt for local media

lyt is a local CLI around yt-dlp and ffmpeg. Help users complete lawful local media downloads efficiently, using the context already provided in the conversation.

Assess the request in context

Copyrighted media is not automatically an impermissible download. Consider user ownership, permission, licenses (including Creative Commons conditions), public domain status, and applicable copyright exceptions such as fair use or fair dealing. A public URL alone does not establish download or reuse rights.

  • When the user provides a relevant ownership, permission, or license statement, use it unless the conversation gives a concrete reason to doubt it. Do not routinely demand documents or repeat a question already answered.
  • Apply the agent's governing policies to the actual request. This skill adds no blanket requirement to obtain a license statement before every ordinary local download. Missing license information alone is not evidence of infringement. Ask a rights question only when the governing policies or concrete context make its answer necessary to decide whether the requested action can proceed.
  • For a claimed copyright exception, consider the purpose, nature of the work, amount needed, and potential market impact. Fair use is case-specific, not a guaranteed status, a fixed duration limit, or a blanket download permission. When an excerpt meets the user's purpose, prefer the requested --clip range.
  • Downloading a file and publishing or reusing it are separate questions. Do not require proof of publication rights as a routine prerequisite for local file retrieval, or claim a completed download clears a video for publication. If the user asks about publishing, explain the relevant rights separately. Do not infer redistribution rights from download permission. Credit, personal use, noncommercial use, or "free beat" wording alone does not establish those rights.
  • Acceptance of Content ID claims or lost monetization is a user preference, not permission or proof of fair use. Do not invent a license, use this preference to override governing policies, or make a guaranteed claim about YouTube's handling.
  • Do not bypass DRM, paywalls, or access controls. Respect applicable law, site terms, and the agent provider's policies; this skill does not override them.
  • If the specific request cannot be fulfilled, explain the concrete reason and offer a relevant permitted source or workflow. Do not claim all YouTube, music, beat, or instrumental downloads are prohibited.

Read the full file on GitHub · 163 lines

Changes

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.

  1. 1mo ago Changed · +44 lines bb1eb8d93de0
  2. 1mo ago Changed · +53 lines 0b35d532a8b2
  3. 2mo ago First seen · 66 lines · 46 tokens per session scan A 01e7ac4087c9

Subscribe to this mod's changes

lyt is a skill published in the GitHub repository TanaTTV/lyt (1 stars, last pushed 4d ago), licensed MIT. It adds 46 tokens to every session and 1,827 once invoked, about $0.0002 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.

Related

lyt compared with skills from other repositories

lyt next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
lytTanaTTV/lytSkill14d agoMITA46Claude Code, Codex
claude-real-videoHUANGCHIHHUNGLeo/claude-real-videoSkill2.3k18d agoMITA61Claude Code
nodejsericrisco/rsc-harnessSkill573yesterdayMITA77Claude Code, Codex
gate-controlOrkas-AI/Orkas-VideoStudioSkill3465d agoMITA81Claude Code, Codex
stage-editOrkas-AI/Orkas-VideoStudioSkill3465d agoMITA62Claude Code, Codex
overleafaloth/olcliSkill2502d agoMITA62Claude Code, Codex
installxiaotonng/pikiloomSkill293todayMITA39Claude Code, Codex