yt-breakdown

yt-breakdown is a skill for Claude Code from not0lucky/tubescout. It costs 96 tokens per session (809 once invoked), scanned A, original, MIT.

A method for examining YouTube videos by reading their transcripts, listing factual claims, and checking how well those claims can be trusted.

In plain words
What is it for?
Reviewing one or more videos, extracting exact figures and methods, checking the creator's incentives and evidence, and comparing claims across videos.
Why use it?
It helps separate supported information from sales pitches, survivor stories, missing failures, and claims that cannot be verified.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; mentions Codex.

Part of the tubescout plugin — 6 skills, 1 MCP server shipped together

Good fit Reviewing one or more videos, extracting exact figures and methods, checking the creator's incentives and evidence, and comparing claims across videos.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/not0lucky/tubescout/yt-breakdown
Install

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.

Any agent
npx skills add not0lucky/tubescout --skill yt-breakdown
Clone the repo
git clone --depth 1 https://github.com/not0lucky/tubescout

Made for: Claude Code.

Or install tubescout, the plugin that ships this one along with the rest of its 6 skills, 1 MCP server.

Wrote 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.

agentmods badge for yt-breakdown

README.md
[![agentmods](https://agentmods.dev/badge/skills/not0lucky/tubescout/yt-breakdown/github.svg)](https://agentmods.dev/skills/not0lucky/tubescout/yt-breakdown)
Your own site
<a href="https://agentmods.dev/skills/not0lucky/tubescout/yt-breakdown"><img src="https://agentmods.dev/badge/skills/not0lucky/tubescout/yt-breakdown/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.

agentmods 80×15 button for yt-breakdown

Your own site · 80×15
<a href="https://agentmods.dev/skills/not0lucky/tubescout/yt-breakdown"><img src="https://agentmods.dev/badge/skills/not0lucky/tubescout/yt-breakdown.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 809 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00096 $0.00809
Opus 5 $0.00048 $0.00404
Sonnet 5 $0.00019 $0.00162
Haiku 4.5 $0.00010 $0.00081

Measured 12d ago against content hash efc2f48cf92e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

yt-breakdown 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.

skills/yt-breakdown/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

yt-breakdown

Turn business/tech YouTube into verified intelligence instead of taking the creator's word. Works on 1–10 videos; with multiple videos, cross-reference them.

Process

  1. Fetch. For each URL/ID: get_video (metadata + engagement) and get_transcript (batch with get_transcripts when >2 videos). If a transcript fails, say so and continue with the rest — never summarize a video you couldn't read.
  2. Extract claims. From each transcript, list every concrete claim: revenue figures, growth timelines, conversion rates, methods, tools named. Quote numbers exactly — never round or embellish them.
  3. Skeptic pass — for each video answer:
    • Incentive: what does the creator sell (course, community, ebook, their channel itself)? The pitch is usually in the last 20% of the transcript.
    • Survivorship: is this one winner speaking, or a repeatable process? What failures are mentioned or conspicuously absent?
    • Verifiability: which claims are shown (dashboards, names, dates) vs asserted?
    • Freshness: check publish date — does the tactic still work, or did the platform/algorithm change since?
  4. Cross-reference (multi-video): where do independent creators agree? Agreement across creators with different incentives is the strongest signal in this method.
  5. Ground in context. Before writing the report, scan the conversation for what the user is actually doing (their business, stack, skills, goals, videos already analyzed earlier in the chat). New videos get compared against previously analyzed ones — agreements, contradictions, and which creator's evidence is stronger.
  6. Report. Lead with the verdict, then per-video: what it actually says (with the real numbers), what survives the skeptic pass, what doesn't. End with "what this means for you" grounded in the user's actual situation — their leverage and their gaps, not generic advice. If nothing is known about the user, say what context would change the verdict instead of guessing.

Read the full file on GitHub · 55 lines

Changes

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.

  1. 12d ago First seen · 55 lines · 96 tokens per session scan A efc2f48cf92e

Subscribe to this mod's changes

yt-breakdown is a skill published in the GitHub repository not0lucky/tubescout (0 stars, last pushed 16d ago), licensed MIT. It adds 96 tokens to every session and 809 once invoked, about $0.0005 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.