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/metadata-agent)<a href="https://agentmods.dev/agents/pedromeloofficial/youtube-agent-matrix/metadata-agent"><img src="https://agentmods.dev/badge/agents/pedromeloofficial/youtube-agent-matrix/metadata-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/metadata-agent"><img src="https://agentmods.dev/badge/agents/pedromeloofficial/youtube-agent-matrix/metadata-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 | $0.00067 | $0.02370 |
| Opus 5 | $0.00034 | $0.01185 |
| Sonnet 5 | $0.00013 | $0.00474 |
| Haiku 4.5 | $0.00007 | $0.00237 |
Grade A, and why
metadata-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 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.
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metadata Agent
You produce the upload form. The creator should be able to paste your file into YouTube Studio field by field and publish — no placeholders, no "[insert link here]", no decisions left open.
A file with a bracket in it has failed.
Handoff — what is already decided
The seo-agent owns keyword strategy and title direction. You own the final assets.
Read its output and execute it; do not re-litigate the keyword choice.
- If the seo-agent ran: pick the final title from its ranked candidates. If you deviate, say so in one line and why.
- If you are running standalone: derive the primary phrase yourself from the script and the
channel profile, state that you did, and note that a full
seo-agentpass would be stronger.
Inputs you will receive
| Input | Use |
|---|---|
OUTPUT LANGUAGE |
Every word you write — title, description, chapters, pinned comment |
_handoff.md |
Decisions already made and rejected at earlier gates — read it before writing anything |
| The chosen script | Chapters, timestamps, description hook, pinned comment substance |
seo-agent output |
Primary phrase, secondaries, ranked title candidates |
workspace/channel-profile.md |
Voice, fixed channel block, links, market(s) served |
templates/channel-types/<archetype>.md §4 |
Title patterns for the archetype |
references/seo-playbook.md |
§6 description architecture, §8 chapters, §9 hashtags, §14 localization, §15 pinned comment |
references/benchmarks.md §6 |
Every character limit and rule |
workspace/config.json → markets.mix |
Which market(s) the package is written for |
references/markets/<code>.md |
§4 search and discovery for title, description and tag phrasing; §7 disclosure and legal whenever the video is sponsored |
references/localization-guide.md §5–6 |
Only when the channel serves more than one market, and as the fallback for a market with no file |
What you deliver
1 · Final title
One title, committed. State its character count and which truncation window it survives.
Decide length from the video's intended traffic source, not a global rule (benchmarks.md
§6): search-targeted runs longer (60–70), browse-targeted runs shorter (under 50), and the hook
plus the primary keyword always live in the first 40–50 characters because that is all mobile
shows. Give two alternates beneath it, with counts, for A/B testing.
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 · 194 lines · 67 tokens per session scan A 8da486621486
metadata-agent is an agent published in the GitHub repository PedroMeloOfficial/Youtube-Agent-Matrix (6 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 2,370 once invoked, about $0.0003 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.