Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/bradautomates/head-of-contentnpx agentmods add skills/bradautomates/head-of-content/youtube-researchWrote 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/skills/bradautomates/head-of-content/youtube-research)<a href="https://agentmods.dev/skills/bradautomates/head-of-content/youtube-research"><img src="https://agentmods.dev/badge/skills/bradautomates/head-of-content/youtube-research/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/skills/bradautomates/head-of-content/youtube-research"><img src="https://agentmods.dev/badge/skills/bradautomates/head-of-content/youtube-research.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 | $0.00136 | $0.01756 |
| Opus 5 | $0.00068 | $0.00878 |
| Sonnet 5 | $0.00027 | $0.00351 |
| Haiku 4.5 | $0.00014 | $0.00176 |
Grade A, and why
youtube-research scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Research
Research high-performing YouTube outlier videos, analyze top content with AI, and generate actionable reports.
Prerequisites
TUBELAB_API_KEYenvironment variable. Get key from https://tubelab.net/settings/apiGEMINI_API_KEYenvironment variable (for video analysis)google-genaiandrequestsPython packages
Workflow
Step 1: Create Run Folder
mkdir -p youtube-research/$(date +%Y-%m-%d_%H%M%S)
Step 2: Get Channel ID
Read .claude/context/youtube-channel.md to get the channel ID.
Step 3: Fetch Channel Videos
python scripts/get_channel_videos.py CHANNEL_ID --format summary
This returns JSON with the channel's video titles and view counts.
Step 4: Analyze Channel
Analyze the channel data to extract:
- keywords: 4 search terms for the channel's direct niche
- adjacent-keywords: 4 search terms for topics the same audience watches
- audience: 2-3 profiles with objections, transformations, stakes
- formulas: Reusable title templates
See references/channel-analysis-schema.md for the full schema and example output.
Step 5: Search for Outliers
Run the outlier search with both keyword sets:
python .claude/skills/youtube-research/scripts/find_outliers.py \
--keywords "keyword1" "keyword2" "keyword3" "keyword4" \
--adjacent-keywords "adjacent1" "adjacent2" "adjacent3" "adjacent4" \
--output-dir youtube-research/{run-folder} \
--top 5
This runs two searches:
- Direct niche: keywords with 5K+ views threshold
- Adjacent audience: adjacent-keywords with 10K+ views threshold
Output files:
outliers.json- All outliers normalized for video analysisreport.md- Basic markdown reportthumbnails/*.jpg- Video thumbnailstranscripts/*.txt- Video transcripts
Step 6: Filter Relevant Videos for Analysis
Read outliers.json and the user's niche from .claude/context/youtube-channel.md.
CRITICAL: Select MAX 3 videos that are most relevant to the user's niche. Filter by:
- Title relevance: Title contains keywords related to user's niche/topics
- Transcript relevance: If transcript exists, check it mentions relevant topics
- Direct niche priority: Prefer videos from direct keyword search over adjacent
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 223 lines · 136 tokens per session scan A 599ca69c972e
youtube-research is a skill published in the GitHub repository bradautomates/head-of-content (234 stars, last pushed 7mo ago), licensed MIT. It adds 136 tokens to every session and 1,756 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…