orchestrator

orchestrator is a skill for Claude Code from PedroMeloOfficial/Youtube-Agent-Matrix. It costs 111 tokens per session (6,334 once invoked), scanned A, original, MIT.

An orchestrator for running a YouTube channel through specialized agents, from research and video ideas to scripts, thumbnails, publishing details, Shorts, repurposing, and monetization. It keeps channel-specific state and requires the creator to approve key decisions.

In plain words
What is it for?
Use it to audit a channel, study competitors, plan content, create hooks and scripts, design thumbnail concepts, prepare SEO and upload metadata, repurpose videos, and plan monetization.
Why use it?
It gives different parts of channel work to focused helpers while keeping decisions and cited benchmarks under review. A benchmark is a reference number used to compare performance, and this system does not invent one when its references lack it.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the youtube-agent-matrix plugin — 1 skill, 1 command, 14 agents shipped together

Good fit Use it to audit a channel, study competitors, plan content, create hooks and scripts, design thumbnail concepts, prepare SEO and upload metadata, repurpose videos, and plan monetization.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add PedroMeloOfficial/Youtube-Agent-Matrix
Claude Code
/plugin install youtube-agent-matrix

Made for: Claude Code.

Or install youtube-agent-matrix, the plugin that ships this one along with the rest of its 1 skill, 1 command, 14 agents.

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 orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/pedromeloofficial/youtube-agent-matrix/orchestrator/github.svg)](https://agentmods.dev/skills/pedromeloofficial/youtube-agent-matrix/orchestrator)
Your own site
<a href="https://agentmods.dev/skills/pedromeloofficial/youtube-agent-matrix/orchestrator"><img src="https://agentmods.dev/badge/skills/pedromeloofficial/youtube-agent-matrix/orchestrator/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 orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/skills/pedromeloofficial/youtube-agent-matrix/orchestrator"><img src="https://agentmods.dev/badge/skills/pedromeloofficial/youtube-agent-matrix/orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,334 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 $0.00111 $0.06334
Opus 5 $0.00056 $0.03167
Sonnet 5 $0.00022 $0.01267
Haiku 4.5 $0.00011 $0.00633

Measured 3d ago against content hash 17284e7b762f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

orchestrator 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 3d 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/orchestrator/SKILL.md · 573 lines

How it starts

The opening of the file, as written. The whole thing — 573 lines — stays where its author put it; the contents beside it link to each section on GitHub.

YouTube Agent Matrix — Orchestrator

You are the engine of a complete YouTube channel operating system. You route work to specialized subagents, hold state, and enforce approval gates. You do not write scripts, research topics, or design thumbnails yourself.

Two rules govern everything below:

  1. Never cross an approval gate without the creator. Present options, recommend one, wait.
  2. Never invent a benchmark. Every number you or a subagent cites comes from references/benchmarks.md. If it isn't there, say the benchmark is unavailable.

Startup sequence — run this before anything else

Step 1 — Load or create the workspace config

Read workspace/config.json, relative to the current working directory — the project folder the creator launched from, never ${CLAUDE_PLUGIN_ROOT} (that points at the plugin's read-only installed files, shared across every channel). This is what gives each channel its own workspace.

If it does not exist, this is a first run. Do the language setup before any other work, then continue with whatever the creator originally asked for.

Ask exactly this, and nothing else, as your first message:

Before we start — what language should I work in?

All deliverables (ideas, scripts, titles, descriptions, calendars, reports) will be
written in the language you pick. I'll save it so you're only asked once.

  1. English
  2. Português (Brasil)
  3. Español
  4. Français
  5. Deutsch
  6. Italiano
  7. 日本語
  8. Other — just tell me which

Reply with a number or the language name.

Then write workspace/config.json:

{
  "output_language": "pt-BR",
  "output_language_name": "Português (Brasil)",
  "channel_profile": "workspace/channel-profile.md",
  "channel_type_primary": null,
  "channel_type_secondary": null,
  "markets": {
    "mix": [ { "code": "BR", "share": 100 } ],
    "source": "declared"
  },
  "created_at": "YYYY-MM-DD"
}

Then ask the second and last setup question, in the language they just chose:

Read the full file on GitHub · 573 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. 3d ago Changed · +7 lines 17284e7b762f
  2. 11d ago First seen · 566 lines · 111 tokens per session scan A 2826774e6d1d

Subscribe to this mod's changes

orchestrator is a skill published in the GitHub repository PedroMeloOfficial/Youtube-Agent-Matrix (6 stars, last pushed 3d ago), licensed MIT. It adds 111 tokens to every session and 6,334 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

blog-chart

Generate dark-mode-compatible inline SVG data visualization charts for blog posts. Supports horizontal bar, grouped bar, donut, line, lollipop, area, and radar charts with automatic platform detection (HTML vs JSX/MDX). Enforces chart type diversity, accessible markup (role=img, aria-labelledby), source attribution…

AgriciDaniel/claude-blog · 164 tokens

blog-image

AI image generation and editing for blog content powered by Gemini via MCP. Claude acts as Creative Director - interpreting intent, selecting domain expertise, constructing optimized 6-component prompts (Subject + Action + Context + Composition + Lighting + Style), and orchestrating Gemini for blog-quality results.…

AgriciDaniel/claude-blog · 176 tokens

blog-audio

Generate audio narration of blog posts using Google Gemini TTS. Supports summary narration, full article read-aloud, and two-speaker podcast/dialogue mode with 30 voice options. Outputs MP3 with HTML5 audio embed code. Works standalone via /blog audio or internally from blog-write. Falls back gracefully when API key…

AgriciDaniel/claude-blog · 123 tokens

cyxj-video-cover

A generator for making 16:9 video-cover background scenes without text, letters, numbers, logos, or watermarks.

chenyuxiaojin/xiaochen-skills · 131 tokens

Video SEO Optimization Agent

Craft a keyword-optimized title, description, tags, and thumbnail for a video, then publish it to a connected YouTube account.

SamurAIGPT/open-ai-youtube-agent · 32 tokens

citedy-video-shorts

Stateful MCP-first producer for branded AI UGC shorts. Generates scripts, reuses brand/avatar memory, renders vertical talking-head videos, and optionally publishes to Instagram Reels and YouTube Shorts.

citedy/citedy-seo-agent · 46 tokens