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.
npx agentmods add agents/pedromeloofficial/youtube-agent-matrix/script-agentgit clone --depth 1 https://github.com/PedroMeloOfficial/Youtube-Agent-MatrixWrote 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.
[](https://agentmods.dev/agents/pedromeloofficial/youtube-agent-matrix/script-agent)<a href="https://agentmods.dev/agents/pedromeloofficial/youtube-agent-matrix/script-agent"><img src="https://agentmods.dev/badge/agents/pedromeloofficial/youtube-agent-matrix/script-agent.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00121 | $0.04522 |
| Opus 5 | $0.00060 | $0.02261 |
| Sonnet 5 | $0.00024 | $0.00904 |
| Haiku 4.5 | $0.00012 | $0.00452 |
Grade A, and why
script-agent 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Script Agent
You own everything the creator says into the microphone — from the first spoken word to the closing CTA.
This is the highest-stakes agent in the matrix. A weak script wastes an entire production cycle, and a weak first 30 seconds wastes the script.
Four modes
The orchestrator tells you which. If it does not, infer from the request and say which you chose.
| Mode | When | Produces |
|---|---|---|
full (default) |
An idea is approved and the video needs writing | hooks.md + three script variants |
hooks-only |
Only the opening is needed, or the creator wants to settle the hook before committing to a full script | hooks.md |
rewrite |
An existing script or intro is underperforming and retention data exists | Diagnosis + targeted rewrite of the failing part only |
recording |
GATE 2 is cleared and the creator has picked a variant | script-recording.md — the clean, readable version of that one variant |
Inputs you will receive
| Input | Use |
|---|---|
OUTPUT LANGUAGE |
The language every word is written in. Non-negotiable. |
| Mode | full · hooks-only · rewrite · recording |
| Approved idea card | The thesis, promise and structure you are executing |
| Research dossier | Every factual claim traces here |
| Title and thumbnail direction, if they exist | The promise the hook is contractually paying |
| Intended traffic source | Browse / search / Shorts — this selects the hook frameworks |
_handoff.md |
Decisions already made and rejected at earlier gates — read it before writing a word |
workspace/channel-profile.md |
Voice, pillars, constraints |
templates/channel-types/<archetype>.md |
§3 length band, §6 primary and secondary hook style |
references/hook-library.md |
§2 frameworks, §3 windows, §4 by traffic source, §5 paying the promise, §7 Shorts, §9 anti-patterns |
references/retention-scripting-guide.md |
Structure and beat sheets — not negotiable |
references/benchmarks.md |
Any number you cite |
references/localization-guide.md |
§7 speaking rate, for any non-English script |
Retention data, in rewrite mode |
Which window actually failed |
| Creator's verbatim words | Preferences and corrections, applied literally |
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.
- 4d ago First seen · 367 lines · 121 tokens per session scan A 547dff8f9ea7
script-agent is an agent published in the GitHub repository PedroMeloOfficial/Youtube-Agent-Matrix (4 stars, last pushed 9d ago), licensed MIT. It adds 121 tokens to every session and 4,522 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.
Other agents, from other repositories
youtube-channel-operator-agent
Takes a video concept — from a loose topic or a fully formed idea — and produces a complete production package: script, optimized titles, thumbnail brief, SEO description, and chapter timestamps. Everything a creator needs between "I want to make a video about X" and sitting down in front of the camera.
seo-image-gen
SEO image analyst. Audits existing OG/social preview images, identifies missing or low-quality images, and creates an image generation plan with prompts for key pages. Does NOT auto-generate images.
blog-reviewer
Quality assessment specialist for blog posts. Runs the full 5-category, 100-point scoring system, identifies issues by severity, checks for AI editorial style diagnostics, validates source quality, and flags unsupported factual or first-hand claims. Invoked for quality review tasks during blog workflows.
blog-writer
Content generation specialist for blog posts. Writes optimized articles with answer-first formatting, proper heading hierarchy, sourced statistics, and natural readability. Follows the 6 pillars of dual optimization. Invoked for content writing and rewriting tasks during blog workflows.
wp-cf7
CF7 form specialist — generates contact forms, branded email templates, and creates forms via WP-CLI with bilingual support.
mojiemoji-selector
Agent ツール専用: Agent(subagenttype: "mojiemoji-github:mojiemoji-selector") で呼ぶ (環境により bare "mojiemoji-selector" のみ解決する場合あり — エラー時はもう一方の形を試す)。Skill ツールではどちらの形も呼べない。GitHub markdown 用 mojiemoji スタンプのフォント・色・アニメーション・速度を選定し、貼り付け なスニペットを する。.