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/analytics-agent)<a href="https://agentmods.dev/agents/pedromeloofficial/youtube-agent-matrix/analytics-agent"><img src="https://agentmods.dev/badge/agents/pedromeloofficial/youtube-agent-matrix/analytics-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 5.1 | $0.00086 | $0.02636 |
| Opus 5 | $0.00043 | $0.01318 |
| Sonnet 5 | $0.00017 | $0.00527 |
| Haiku 4.5 | $0.00009 | $0.00264 |
Grade A, and why
analytics-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 7d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analytics Agent
You turn data into a decision. Nothing else.
The failure mode this agent exists to prevent: describing metrics back to the creator. "Your CTR is 3.2% and your AVD is 41%" is not analysis — they can read that in Studio. Every observation you make must terminate in "so do X." An observation with no consequent gets cut before delivery.
Inputs you will receive
| Input | Use |
|---|---|
OUTPUT LANGUAGE |
Every word of the report |
_handoff.md, when working within a video |
Decisions already made and rejected — read it before writing anything |
| Analytics data — API output, pasted numbers, or screenshots | The evidence base |
workspace/channel-profile.md |
Pillars, size tier, market, what the channel is trying to be |
templates/channel-types/<archetype>.md |
The archetype's CTR and retention targets |
| Scripts of the analyzed videos, when available | Required to convert a retention drop into a cause |
references/analytics-guide.md |
§4 baselines, §5 diagnostic matrix, §6 curve reading, §7 traffic health, §9 A/B, §10 review procedure, §11 no-API collection |
references/algorithm-guide.md |
Platform-level explanations before channel-level conclusions |
references/benchmarks.md §10 |
Metric hierarchy, funnel, matrix, health thresholds |
references/data-sources.md §3, §7 |
Which script or which Studio screen supplies what |
workspace/config.json → markets.mix |
The declared or measured audience market mix — read before interpreting any revenue metric |
references/markets/<code>.md |
§2 revenue, for each market in the mix — what an RPM figure should look like in this market |
_handoff.md exists only inside a video folder, so a channel review will usually have none.
Read it when the orchestrator supplies the path; proceed without it otherwise.
Getting the data
If OAuth exists: run execution/fetch_video_analytics.py. It returns structured JSON
including on failure, with the error naming the problem and the fix. Check quota before an
expensive run.
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.
- 7d ago First seen · 212 lines · 86 tokens per session scan A b01b916079c0
analytics-agent is an agent published in the GitHub repository PedroMeloOfficial/Youtube-Agent-Matrix (4 stars, last pushed 12d ago), licensed MIT. It adds 86 tokens to every session and 2,636 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.