What is social-youtube?

A command-line tool for managing a YouTube channel through YouTube's official API. It can inspect channel and video data, handle comments, and upload or delete videos.

Use it to check your channel, list uploads, inspect video details or comments, and publish or remove videos from scripts or an agent.

It removes the need to write direct API requests for routine YouTube tasks. A dry-run option lets you inspect a request before it is sent.

social-youtube — Skill for Claude Code by isaacrowntree

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.

Any agent

npx skills add isaacrowntree/claude-social-skills --skill social-youtube

Clone the repo

git clone --depth 1 https://github.com/isaacrowntree/claude-social-skills

Made for: Claude Code.

Or install social, the plugin that ships this one along with the rest of its 10 skills.

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/skills/isaacrowntree/claude-social-skills/social-youtube/github.svg)](https://agentmods.dev/skills/isaacrowntree/claude-social-skills/social-youtube)

Your own site

<a href="https://agentmods.dev/skills/isaacrowntree/claude-social-skills/social-youtube"><img src="https://agentmods.dev/badge/skills/isaacrowntree/claude-social-skills/social-youtube/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/skills/isaacrowntree/claude-social-skills/social-youtube"><img src="https://agentmods.dev/badge/skills/isaacrowntree/claude-social-skills/social-youtube.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 867 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	$0.00066	$0.00867
Opus 5.5	$0.00026	$0.00347
Sonnet 5.5	$0.00013	$0.00173
Haiku 4.5	$0.00007	$0.00087

Measured 1mo ago against content hash ce478764555b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

social-youtube 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.

skills/social-youtube/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

YouTube Data API v3: your channel, uploads, video details, comments, upload and delete videos.

Run: social youtube <command> (installed via bun link in this repo, or bun run /path/to/claude-social-skills/src/cli.ts youtube …). Add --dry-run before any command to print the request instead of sending it.

Credentials

GOOGLE_CLIENT_ID
GOOGLE_CLIENT_SECRET

Create an OAuth client of type "Desktop app" at https://console.cloud.google.com/apis/credentials with the YouTube Data API v3 enabled, then social auth login youtube.

Check what is present with social auth status youtube; store a value with social auth set youtube <KEY> <value> (OS keyring, else ~/.config/social/.env); run the interactive flow with social auth login youtube. Docs: https://developers.google.com/youtube/v3/docs

API description this wrapper is built from

discovery: https://youtube.googleapis.com/$discovery/rest?version=v3. Refresh with bun run gen; CI fails if upstream changes.

Commands

Every command accepts --json (raw JSON) and --jq <expr> (filter the JSON with jq).

`social youtube me`

your channel (channels.list mine=true)

`social youtube videos`

your uploads, newest first (playlistItems.list on the uploads playlist)

  -n, --max <n>              count (1-50) (default "10")
  --page <token>             pageToken from a previous call

`social youtube video <id>`

one video with stats (videos.list)

`social youtube upload <file>`

upload a video (resumable videos.insert); private unless --privacy says otherwise

  --title <t>                 (required)
  --description <text>        (default "")
  --privacy <p>              public | private | unlisted (default "private")
  --tags <tags...>

`social youtube comments <videoId>`

top-level comments on a video (commentThreads.list)

  -n, --max <n>              count (1-100) (default "20")
  --order <o>                time | relevance (default "time")
  --page <token>

Read the full file on GitHub · 92 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.

1mo ago First seen · 92 lines · 0 tokens per session scan A ce478764555b

Subscribe to this mod's changes

social-youtube is a skill published in the GitHub repository isaacrowntree/claude-social-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 867 once invoked, about $0.0003 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 2026-09-19.

Creative and media

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…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 83 tokens