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-link-setupgit 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-link-setup)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/youtube-link-setup"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/youtube-link-setup/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-link-setup"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/youtube-link-setup.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 | $0.00157 | $0.01275 |
| Opus 5.5 | $0.00063 | $0.00510 |
| Sonnet 5.5 | $0.00031 | $0.00255 |
| Haiku 4.5 | $0.00016 | $0.00128 |
Grade A, and why
youtube-link-setup 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 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.
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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Link Setup
Stage 3. Takes the CSV and code from benai-utm-creator and makes them real: short links
live on c.benai.co, lead magnet page live in Kit if there is one, every link verified.
Owns the links only. Does not touch the video description or YouTube Studio.
Needs nothing from the video itself, so it can run while YouTube is still processing.
Steps
Task Progress:
- [ ] 1. Confirm the backhalves are free
- [ ] 2. Show the links and get the go ← HUMAN CHECKPOINT
- [ ] 3. Import to Bitly
- [ ] 4. Lead magnet page built, published and tested end to end
- [ ] 5. Verify every link resolves
- [ ] 6. Tick Bitly imported on the Notion card
1. Confirm the backhalves are free
Open https://c.benai.co/<code>-accelerator. A 404 means the code is clean. Anything that
resolves means links for this code already exist: stop and report rather than duplicating.
2. The human checkpoint
Show the full list of links with their destinations and say plainly what the import costs: Bitly's monthly quota is finite and links are awkward to unpick. Wait for an explicit go.
Say how many links are being imported. Five and six are both correct answers depending on the lead magnet, and the operator should see which one is happening.
3. Import to Bitly
Two paths. Pick by what exists, and say which one you are using.
- Token present (
BITLY_TOKENin the environment): usereferences/bitly-import-api.md. Deterministic, no browser. Run it yourself; never show the operator a command and never echo the token into the transcript or a note. - No token: use
references/bitly-bulk-upload.md. Point-and-click in the browser, six steps, no terminal. This is the normal path.
4. Lead magnet, if there is one
Only when the Ship Brief said yes. Read references/kit-lead-magnet.md.
The slug must be exactly <code>-free. Any other slug breaks the free link with no visible
error anywhere.
The Kit redirect takes the long URL, never the Bitly short link. Routing it through Bitly loses the attribution the page exists to capture.
What ships with it
4 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 · +157 tokens per session 86a3b73bc853
- 1mo ago First seen · 102 lines · 0 tokens per session scan A 228fc8dc0072
youtube-link-setup is a skill published in the GitHub repository naveedharri/benai-skills (74 stars, last pushed 16d ago), licensed MIT. It adds 157 tokens to every session and 1,275 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-12.
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.