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.
npx skills add nikhilbhansali/youtube-data-skills --skill youtube-channel-insightsgit clone --depth 1 https://github.com/nikhilbhansali/youtube-data-skillsWrote 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/nikhilbhansali/youtube-data-skills/youtube-channel-insights)<a href="https://agentmods.dev/skills/nikhilbhansali/youtube-data-skills/youtube-channel-insights"><img src="https://agentmods.dev/badge/skills/nikhilbhansali/youtube-data-skills/youtube-channel-insights/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/nikhilbhansali/youtube-data-skills/youtube-channel-insights"><img src="https://agentmods.dev/badge/skills/nikhilbhansali/youtube-data-skills/youtube-channel-insights.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 | $0.00160 | $0.03806 |
| Opus 5 | $0.00080 | $0.01903 |
| Sonnet 5 | $0.00032 | $0.00761 |
| Haiku 4.5 | $0.00016 | $0.00381 |
Grade B, and why
youtube-channel-insights scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 600 ~/.config/youtube-skills/client_secret.json How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Channel Insights
Analyze your own channel with the data only the channel owner can see. The other skills in this suite read public data; this one authenticates as you and pulls retention, traffic sources, watch time, demographics, subscriber attribution, and revenue from the YouTube Analytics API v2.
| Question | Public Data API | This skill |
|---|---|---|
| How many views? | Yes | Yes |
| How long did people watch? | No | Yes (watch time, avg view %) |
| Where did viewers drop off? | No | Yes (retention curve) |
| Where did the traffic come from? | No | Yes (Search / Suggested / Browse) |
| Who is the audience? | No | Yes (age, gender, country, device) |
| Which videos gained subscribers? | No | Yes |
| What did it earn? | No | Yes (with --with-revenue) |
One-time setup
The user does this once, then never again. Walk them through it if python3 scripts/auth.py --check reports anything missing.
- Create or reuse a Google Cloud project — console.cloud.google.com. Any project works, including one already used for a Data API key.
- Enable both APIs in APIs & Services > Library:
- YouTube Data API v3 (used to attach titles, durations, and publish dates to analytics rows)
- YouTube Analytics API (the actual insights) Both are required. Missing the Analytics API is the single most common cause of a 403.
- Configure the OAuth consent screen — APIs & Services > OAuth consent screen:
- User type: External
- Fill in app name and your email
- Add your own Google account under Test users
- Then PUBLISH the app to Production. This matters: while the consent screen sits in Testing mode, Google expires refresh tokens after 7 days, so you would have to re-authorize every week. Publishing without Google verification is fine for a personal, single-user tool — you will see an "unverified app" warning at sign-in and can click through via Advanced > Go to (app).
- Create an OAuth client ID — APIs & Services > Credentials > Create Credentials > OAuth client ID:
- Application type: Desktop app
- Download the JSON
- Save the file as
~/.config/youtube-skills/client_secret.json:mkdir -p ~/.config/youtube-skills mv ~/Downloads/client_secret_*.json ~/.config/youtube-skills/client_secret.json chmod 600 ~/.config/youtube-skills/client_secret.json - Install dependencies and authorize:
A browser opens. Sign in with the Google account that owns the channel. The token lands inpip3 install google-api-python-client google-auth-oauthlib python3 scripts/auth.py # analytics + channel read access python3 scripts/auth.py --with-revenue # also unlock revenue / RPM metrics~/.config/youtube-skills/token.json(mode 600) and refreshes itself from then on.
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 · 265 lines · 160 tokens per session scan B 76af781a4bf4
youtube-channel-insights is a skill published in the GitHub repository nikhilbhansali/youtube-data-skills (2 stars, last pushed 25d ago), licensed MIT. It adds 160 tokens to every session and 3,806 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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…