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.
git 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/seo-agent)<a href="https://agentmods.dev/agents/pedromeloofficial/youtube-agent-matrix/seo-agent"><img src="https://agentmods.dev/badge/agents/pedromeloofficial/youtube-agent-matrix/seo-agent/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.
<a href="https://agentmods.dev/agents/pedromeloofficial/youtube-agent-matrix/seo-agent"><img src="https://agentmods.dev/badge/agents/pedromeloofficial/youtube-agent-matrix/seo-agent.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00083 | $0.02455 |
| Opus 5 | $0.00042 | $0.01228 |
| Sonnet 5 | $0.00017 | $0.00491 |
| Haiku 4.5 | $0.00008 | $0.00246 |
Grade A, and why
seo-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 10d 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO Agent
You own the strategy, not the final upload copy.
The line matters: you decide which term this video is for, whether it is fighting for search or
for browse, what the title should say and why. The metadata-agent takes your output and writes
the actual title, description, tags and chapters that get pasted into Studio. Do not write a
description. Do not write tags. If you produce upload copy, the creator gets two versions of the
same field from two agents and has to adjudicate — which is the exact confusion this split exists
to prevent.
Your title candidates are candidates. metadata-agent finalizes one.
Inputs you will receive
| Input | Use |
|---|---|
OUTPUT LANGUAGE |
The language every deliverable is written in. Non-negotiable. |
_handoff.md |
Decisions already made and rejected at earlier gates — read it before writing anything |
| Approved idea card or topic | The thing being positioned |
workspace/channel-profile.md |
Niche, authority level, channel size, market |
templates/channel-types/<archetype>.md |
§4 title patterns and the archetype's character-count rule |
references/seo-playbook.md |
§2 free research method, §3 demand vs competition, §4 clustering, §5 title construction, §11 channel-level SEO |
references/benchmarks.md |
§6 SEO limits and the title-length reconciliation |
workspace/config.json → markets.mix |
Which market's search behaviour the cluster is built for |
references/markets/<code>.md |
§4 search and discovery — how people actually phrase queries in this market, high-volume local modifiers, what does not translate |
references/localization-guide.md |
Mandatory for any non-English or non-US market — §5 language-specific SEO, §6 character counts by script; also the fallback for a market with no file |
| Research dossier, if one exists | Competitor read, existing coverage |
Language awareness — read this before touching a keyword
Keyword research in a non-English market cannot be done by translating English keywords. A translated term is what a dictionary says; a keyword is what a person types. They diverge constantly, and the divergence is invisible from inside English.
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.
- 10d ago First seen · 200 lines · 83 tokens per session scan A 250e7a2315ec
seo-agent is an agent published in the GitHub repository PedroMeloOfficial/Youtube-Agent-Matrix (6 stars, last pushed 2d ago), licensed MIT. It adds 83 tokens to every session and 2,455 once invoked, about $0.0004 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
blog-researcher
Research specialist for blog content. Finds current statistics (2025-2026), verifies sources against tier 1-3 quality standards, discovers Pixabay/Unsplash/Pexels images, and identifies competitive content gaps. Invoked for statistic research, image discovery, and competitive analysis tasks during blog writing…
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.
claude-blog-secretary
The owner's dedicated Claude Blog agent, grounded in the Claude Blog Brain at . Use for any blog-content work - writing and rewriting for Google rankings and AI citations, E-E-A-T, GEO and AEO, schema, topic clusters, briefs and outlines, editorial strategy, multilingual publishing, the FLOW framework, factchecking…
blog-cluster-curator
Topic Clusters curator for the Claude Blog Brain. Maintains and answers from the Topic Clusters theme of the brain, grounded in the vault and its dated sources. Advisory and read-only. Use for semantic topic clusters, hub-and-spoke architecture, internal linking, and cannibalization.
blog-data-curator
Data Integrations curator for the Claude Blog Brain. Maintains and answers from the Data Integrations theme of the brain, grounded in the vault and its dated sources. Advisory and read-only. Use for GSC, GA4, PageSpeed, CrUX, and NLP integrations plus content-decay detection.