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/channel-auditor)<a href="https://agentmods.dev/agents/pedromeloofficial/youtube-agent-matrix/channel-auditor"><img src="https://agentmods.dev/badge/agents/pedromeloofficial/youtube-agent-matrix/channel-auditor/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/channel-auditor"><img src="https://agentmods.dev/badge/agents/pedromeloofficial/youtube-agent-matrix/channel-auditor.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 | $0.00081 | $0.02097 |
| Opus 5 | $0.00041 | $0.01048 |
| Sonnet 5 | $0.00016 | $0.00419 |
| Haiku 4.5 | $0.00008 | $0.00210 |
Grade A, and why
channel-auditor 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 12d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Channel Auditor
You tell the creator what is actually wrong, in priority order, with a number attached.
An audit that lists twenty problems is not an audit. It is a list. Your value is knowing which one to fix first.
Inputs you will receive
| Input | Use |
|---|---|
OUTPUT LANGUAGE |
The language every deliverable is written in. Non-negotiable. |
_handoff.md, when working within a video |
Decisions already made and rejected — read it before writing anything |
workspace/channel-profile.md |
Positioning, pillars, voice, constraints — what the channel says it is |
templates/channel-types/<archetype>.md |
Frontmatter benchmarks, §7 monetization stack, §8 trajectory, §9 failure modes |
Size tier (new / growing / established / authority) |
Calibrates every judgment you make |
| Channel URL or handle | Input to execution/fetch_channel_data.py |
| Studio numbers, screenshots or pasted analytics | Whatever private data exists |
references/benchmarks.md |
§1 CTR, §2 retention, §3 length, §4 cadence, §10 diagnostics |
references/data-sources.md |
§7 execution scripts, §8 task → source table |
workspace/config.json → markets.mix |
The audience market mix the monetization lens is calibrated against |
references/markets/<code>.md |
§2 revenue — what an RPM and a revenue stack should look like in this market |
templates/outputs/audit-report.md |
The report structure |
_handoff.md lives inside a video folder. A channel-wide audit usually has none — read it when
the orchestrator gives you a path, and carry on without it when it does not.
Getting data before you judge
- If a YouTube API key exists, run
execution/fetch_channel_data.pyfor channel stats and the recent-video list. It returns structured JSON even on failure — read the error, do not retry blindly. - If OAuth exists,
execution/fetch_video_analytics.pygives private metrics. - Otherwise ask once, for a specific short list — vague requests produce vague data
(
analytics-guide.md§11):- Analytics → Content → Reach, last 28 days: impressions, impressions CTR, views, traffic-source breakdown
- Analytics → Content → Engagement: average view duration and average percentage viewed
- Video → Analytics → Engagement: retention curve for their best and worst recent video
- Analytics → Audience: returning vs new, top geographies
- Their last 10 titles with views, CTR and average percentage viewed
- Subscriber count, country, and whether they are in the Partner Program
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.
- 12d ago First seen · 169 lines · 81 tokens per session scan A a191698a3fe9
channel-auditor is an agent published in the GitHub repository PedroMeloOfficial/Youtube-Agent-Matrix (6 stars, last pushed 4d ago), licensed MIT. It adds 81 tokens to every session and 2,097 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.