A first-run setup command for the yt-mem-ai YouTube tool. It checks prerequisites and guides configuration for browser cookies, optional proxy access, and the video-embedding model.

It helps inspect current settings, choose a logged-in browser, configure Webshare when needed, and select an embedding model for non-English videos.

It helps resolve common access problems, such as YouTube asking users to sign in or rate-limiting requests, before video processing begins.

yt-setup — Command for Claude Code by dasein108

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.

Clone the repo

git clone --depth 1 https://github.com/dasein108/yt-mem-ai

Made for: Claude Code.

Or install yt-mem-ai, the plugin that ships this one along with the rest of its 9 commands.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/dasein108/yt-mem-ai/yt-setup/github.svg)](https://agentmods.dev/commands/dasein108/yt-mem-ai/yt-setup)

Your own site

<a href="https://agentmods.dev/commands/dasein108/yt-mem-ai/yt-setup"><img src="https://agentmods.dev/badge/commands/dasein108/yt-mem-ai/yt-setup/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/dasein108/yt-mem-ai/yt-setup"><img src="https://agentmods.dev/badge/commands/dasein108/yt-mem-ai/yt-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 519 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.

Model	Per session	Once invoked
Fable 5.1	$0.00021	$0.00519
Opus 5	$0.00010	$0.00260
Sonnet 5	$0.00004	$0.00104
Haiku 4.5	$0.00002	$0.00052

Measured 8d ago against content hash 321fa15251b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

yt-setup 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 8d 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.

integrations/claude-code/commands/yt-setup.md · 32 lines

What it actually says

Run the yt-mem-ai first-run setup as a short interactive wizard, using the yt skill's "Configure & maintain" flow. Ask one thing at a time; skip a step if the user says it's already fine. Persist every choice with uvx yt-mem-ai config set KEY VALUE (global config ~/.yt-mem-ai/config.env).

Prereqs — confirm uv/uvx is on PATH (uvx --version). If missing, point to https://docs.astral.sh/uv/ and stop.
Show current state — run uvx yt-mem-ai config list and summarize what's already set vs default.
Cookies browser — the fix for YouTube's "Sign in to confirm you're not a bot" check. Ask which browser they're logged into YouTube on and set YT_COOKIES_BROWSER (chrome/brave/firefox/edge, or blank for none).
Webshare proxy (optional) — only if they hit IP rate-limits. If yes, set WEBSHARE_PROXY_USERNAME + WEBSHARE_PROXY_PASSWORD, then either YT_USE_WEBSHARE true (proxy everything) or YT_CAPTIONS_USE_WEBSHARE true (proxy only the transcript API — recommended, yt-dlp stays direct).
Embedding model (optional) — default is English all-MiniLM-L6-v2. If they watch non-English videos, set YT_EMBEDDING_MODEL paraphrase-multilingual-MiniLM-L12-v2. Note: if they already have a library, run uvx yt-mem-ai reembed afterwards to migrate it.
Caption languages (optional) — set YT_CAPTION_LANGS (e.g. en,es) if they want a non-default priority order.
Verify — run uvx yt-mem-ai config list to show the final state, then offer a smoke test: /yt-summarize <a short YouTube URL>.

Keep it conversational and skippable; don't set anything the user didn't confirm.

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.

8d ago First seen · 32 lines · 21 tokens per session scan A 321fa15251b6

Subscribe to this mod's changes

yt-setup is a command published in the GitHub repository dasein108/yt-mem-ai (7 stars, last pushed 16d ago), licensed MIT. It adds 21 tokens to every session and 519 once invoked, about $0.0001 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.

Claude Code agent-skills ai-agents codex cursor lancedb

yt-setup

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

deps-audit

init

migrate

handoff

lians-recall

t800-onboard