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-metadata-updatergit 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-metadata-updater)<a href="https://agentmods.dev/skills/nikhilbhansali/youtube-data-skills/youtube-metadata-updater"><img src="https://agentmods.dev/badge/skills/nikhilbhansali/youtube-data-skills/youtube-metadata-updater/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-metadata-updater"><img src="https://agentmods.dev/badge/skills/nikhilbhansali/youtube-data-skills/youtube-metadata-updater.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 | $0.00176 | $0.03572 |
| Opus 5 | $0.00088 | $0.01786 |
| Sonnet 5 | $0.00035 | $0.00714 |
| Haiku 4.5 | $0.00018 | $0.00357 |
Grade A, and why
youtube-metadata-updater 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 — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Metadata Updater
⚠️ THIS SKILL CHANGES YOUR CHANNEL
Every other skill in this suite is read-only. This one is not. It holds the single write credential in the suite (
youtube.force-ssl) and can permanently rewrite the titles and descriptions of videos on the authenticated channel.
- Analytics stays on the read-only token (
token.json). The two tokens are separate files and are never merged.- Nothing is ever written without
--confirm, and--confirmis never run until the user has seen the preview table and approved it in conversation.- Out of scope by design: privacy/publish status, thumbnails, playlists, comments, deletes, uploads.
part="status"is never even requested.- Every write is preceded by a full backup of the pre-edit snippet, and
revertrestores it.
What it can change
| Field | Editable here | Notes |
|---|---|---|
snippet.title |
Yes | ≤100 chars, no < or > |
snippet.description |
Yes | ≤5000 UTF-8 bytes, no < or > |
snippet.tags |
No — preserved | Re-sent unchanged on every update |
snippet.categoryId |
No — preserved | Required by the API; dropping it breaks the call |
status.privacyStatus |
Never | Never fetched, never sent |
| Thumbnails, playlists, comments | Never | Different endpoints, not implemented |
One-time setup
This skill reuses the Google Cloud project and client_secret.json from the
youtube-channel-insights setup. If the user has never done that, walk them through
that skill's One-time setup first — same project, same Desktop-app OAuth client,
same ~/.config/youtube-skills/client_secret.json. Only YouTube Data API v3 needs to
be enabled for this skill.
Then grant the write scope:
pip3 install google-api-python-client google-auth-oauthlib
python3 scripts/auth_write.py
A browser opens and Google asks for one extra permission — manage your YouTube
account (youtube.force-ssl). Accepting it writes a separate token:
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 · 286 lines · 176 tokens per session scan A 09e5c1beb9b3
youtube-metadata-updater is a skill published in the GitHub repository nikhilbhansali/youtube-data-skills (2 stars, last pushed 25d ago), licensed MIT. It adds 176 tokens to every session and 3,572 once invoked, about $0.0009 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 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…