agentmods.dev

lyt AGENTS.md

A repository instruction file describing how to work on TanaTTV/lyt, a Node.js command-line tool that wraps yt-dlp and ffmpeg for downloading or processing media.

In plain words
What is it for?
Use it to find the project’s entry points, run its tests and website checks, understand the experimental desktop app’s status, and verify packaged builds.
Why use it?
It explains the repository’s non-obvious setup, supported areas, and standard checks so an agent does not assume ordinary dependency or release practices.

Instructions file for CodexOpenCode

1 20d ago A scan 562 tokens original MIT
View the source file TanaTTV/lyt
Install

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.

agentmods
npx agentmods add instructions/tanattv/lyt/agents-md
Clone the repo
git clone --depth 1 https://github.com/TanaTTV/lyt

Made for: Codex, OpenCode.

Per session 562 This file is loaded in full into every session.
When invoked 562 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00562 $0.00562
Opus 5 $0.00281 $0.00281
Sonnet 5 $0.00112 $0.00112
Haiku 4.5 $0.00056 $0.00056

Measured 2d ago against content hash bfb314fd1cdd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lyt AGENTS.md 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 2d 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.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Cursor Cloud specific instructions

lyt is a zero-runtime-dependency Node.js CLI (Node 20+) that wraps yt-dlp and ffmpeg. The npm package and the website/ static site have no npm dependencies and no lockfiles, so npm install is a no-op. Do not expect a node_modules directory.

Services / surfaces

  • CLI (production product): entry points bin/lyt.js, bin/yt3.js, bin/yt4.js. Run directly, e.g. node bin/lyt.js --help.
  • Website (website/): dependency-free static site. Standard commands live in website/package.json (build, check, serve). npm run serve listens on 127.0.0.1:4173.
  • Desktop app (app/): experimental Tauri prototype, explicitly NOT part of the release (see app/README.md). Requires Rust/Tauri toolchain; out of scope for normal development.

Lint / test / build / run

  • There is no separate lint step in this repo. Standard commands are in package.json and README.md (npm test, npm run check:pack, npm run check:website, npm run check, npm run smoke:linux).
  • npm run check runs the Node test suite + npm-pack payload verification + website build/SEO checks.
  • npm run smoke:linux packs the CLI, installs it globally to a temp prefix, and performs a real permitted download from Wikimedia Commons (needs network
    • a provisioned yt-dlp).

yt-dlp provisioning (non-obvious)

  • ffmpeg is preinstalled system-wide, but yt-dlp is NOT on PATH.
  • lyt manages its own checksum-verified yt-dlp binary under ~/.local/share/lyt/bin/. The startup update script runs node bin/lyt.js doctor --fix to provision it ahead of time; the CLI also auto-downloads it on first real use. The unit tests do NOT need yt-dlp (they mock it), so tests pass even before provisioning.
  • Provisioning and real downloads need outbound network (GitHub releases for the binary, and the media host). Use lyt doctor to confirm readiness.
  • Clipboard integration is unavailable on this headless Linux VM (no xclip/xsel/wl-clipboard); --paste/--watch will not work here.

Read the full file on GitHub · 41 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. 2d ago First seen · 41 lines · 562 tokens per session scan A bfb314fd1cdd

Subscribe to this mod's changes

lyt AGENTS.md is an instructions file published in the GitHub repository TanaTTV/lyt (1 stars, last pushed 20d ago), licensed MIT. It adds 562 tokens to every session, about $0.0028 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 2026-08-31.

audio-downloaderclicommand-line-tooldownloaderffmpegnodejs
Related

Other instructions, from other repositories

leclap AGENTS.md

Instructions for heristop/leclap, covering agents.md, project overview, repository layout, setup and commands.

heristop/leclap · 2,378 tokens

leclap CLAUDE.md

Instructions for heristop/leclap: This repository's agent guidance lives in AGENTS.md — read it first; it is the single source of truth for structure, commands, and conventions.

heristop/leclap · 83 tokens

hyperframes AGENTS.md

AGENTS.md instructions for heygen-com/hyperframes, covering hyperframes, skills, build & test, linting & formatting and composition validation.

heygen-com/hyperframes · 1,468 tokens

mediago AGENTS.md

Instructions for mediago-dev/mediago, covering repository guidelines, project structure & module organization, tooling and script placement, documentation site safety and build, test, and development commands.

mediago-dev/mediago · 1,037 tokens

pueue AGENTS.md

Instructions for Nukesor/pueue: This project does not approve of large-scale work done by LLMs.

Nukesor/pueue · 522 tokens

openscreen AGENTS.md

Instructions for getopenscreen/openscreen, covering agents.md, setup commands, development principles, project layout and code style.

getopenscreen/openscreen · 5,627 tokens