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 naveedharri/benai-skills --skill youtube-shipgit clone --depth 1 https://github.com/naveedharri/benai-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/naveedharri/benai-skills/youtube-ship)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/youtube-ship"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/youtube-ship/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/naveedharri/benai-skills/youtube-ship"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/youtube-ship.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 | $0.00145 | $0.01519 |
| Opus 5.5 | $0.00058 | $0.00608 |
| Sonnet 5.5 | $0.00029 | $0.00304 |
| Haiku 4.5 | $0.00015 | $0.00152 |
Grade A, and why
youtube-ship scanned grade A 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`youtube-transcript-api` and `curl` both fail; do not retry them. How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Ship
One video, five stages, four human checkpoints. Ends at an armed Unlisted draft. A person clicks Publish. This skill never does.
Before anything: report state, do not act
State lives on the video's Notion card, never in chat. That is what makes any stage runnable standalone, days apart, and resumable after a dead session.
Read the card first and say out loud which stages are already done. See
references/notion-card.md for the database, the properties and the reading rules.
The short version of the reading rules:
| Property | Empty means |
|---|---|
Video ID |
nothing has run; you do not even have a video |
UTM code |
stage 2 has not run |
Bitly imported unchecked |
the links are not live, so do not write a description full of dead links |
Chapters |
stage 4 has not run |
Stage 0: the Ship Brief
Collect every judgment call in one approval, before any stage runs. Read
references/ship-brief.md for the full list and the wording to use.
If a new question comes up mid-run, that question belonged in the Brief. Add it there rather than asking it twice.
The chain, in this order
1. youtube-studio-setup → video saved at Unlisted, wizard walked
2. benai-utm-creator → six UTM links, five-letter code, Bitly CSV
3. youtube-link-setup → links live on c.benai.co
4. youtube-chapters-tags → chapters and tags
5. youtube-description → description assembled and written into the draft
Why stage 1 is first
Measured on 2026-08-25 during the Juan walkthrough. A video sitting as a Studio draft has no caption track, so there is no transcript, so there are no chapters. YouTube generates captions only after the video is saved at a real visibility and its checks finish.
The old order put chapters first and deadlocked: chapters needed a transcript, the transcript needed Unlisted, and Unlisted was the last step of the old stage 4.
So: walk the wizard first. Land at Unlisted. Then chapters become possible.
What to do while YouTube processes
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.
- 1mo ago Changed · +1 lines 40be1172e480
- 1mo ago First seen · 113 lines · 145 tokens per session scan A d6f52ac1d917
youtube-ship is a skill published in the GitHub repository naveedharri/benai-skills (74 stars, last pushed 16d ago), licensed MIT. It adds 145 tokens to every session and 1,519 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-12.
Other skills, from other repositories
project
A single starting point for setting up an AI-assisted project in Claude Cowork. It asks questions about the work, reviews available add-ons, and creates project instructions, custom agents, and connected workflows.
doc-html-slide
A renderer that turns presentation content into a single HTML slide deck that opens directly in a browser. It creates a 16:9 slide sequence with navigation, fullscreen viewing, printing to PDF, and speaker-note controls.
cs-channel-message
A channel-message writing tool for search ads, advertising, customer relationship messages, and app notifications. It uses the NCM sequence—Need, Channel, Moment, Message, and CTA—to adapt wording to where and when customers see it.
media-higgsfield-explainer
A Higgsfield workflow for making non-photorealistic narrated explainer videos. It pairs each narration line with a 10-second animated clip and joins the clips into one finished video.
setup-mcp-connector
A step-by-step setup guide for connecting Cowork to services such as Google Drive, Notion, and Higgsfield, plus Korean public-data, document, statistics, architecture, and law services. It explains authentication, API keys, test calls, and troubleshooting.
media-gpt-image-prompt
An image-prompt writing tool that turns a natural-language idea into detailed prompts for GPT Image 2.5. It can also adapt the same idea for Gemini 3 Pro Image and Midjourney.