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 benai-utm-creatorgit 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/benai-utm-creator)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/benai-utm-creator"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/benai-utm-creator/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/benai-utm-creator"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/benai-utm-creator.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 | $0.00141 | $0.01289 |
| Opus 5.5 | $0.00056 | $0.00516 |
| Sonnet 5.5 | $0.00028 | $0.00258 |
| Haiku 4.5 | $0.00014 | $0.00129 |
Grade A, and why
benai-utm-creator 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ben AI UTM Creator
Stage 2. One video title in, six links and a CSV out. Replaces the manual formula work in the UTM creator sheet.
Needs only the title, so run it while YouTube processes the upload rather than waiting.
Steps
Task Progress:
- [ ] 1. Get the exact video title
- [ ] 2. Generate links + CSV
- [ ] 3. Settle the free link
- [ ] 4. Review with the operator
- [ ] 5. Save the CSV where the operator can reach it
- [ ] 6. Write the code to the Notion card
1. Get the exact video title
Take it from Studio, not from the Notion card's name. The card often carries a working title or a list of candidate variations; the code has to derive from the title that actually ships.
2. Generate links + CSV
Run scripts/utm_creator.py "<video title>" yourself. The operator never runs this. They
should not see a command, be asked to open a terminal, or be told a path they have to type.
The script prints the slug, the five-letter code, all six links with their backhalfs, and writes the CSV. Do not hand-build any URL.
It self-checks before writing and exits 1 without producing a file if utm_content is not
lowercase or disagrees between the Long URL and the UTM Content column. If it refuses, fix the
cause in the script. Never hand-edit the CSV to get past it.
Destination table and derivation rules are in references/destinations.md. Read it only if a
value looks wrong or someone wants a destination changed.
3. Settle the free link
Six links get generated, but only five are wanted when there is no lead magnet.
The -free backhalf points at benai.kit.com/<code>-free. That page only exists if the lead
magnet was built. With no lead magnet the link resolves to nothing, and the description
template has a hardcoded line pointing at it, so the video would ship a dead link in front of
every viewer.
- Lead magnet yes: keep all six.
youtube-link-setupbuilds the Kit page. - Lead magnet no: drop the
-freerow from the CSV before delivering, import five, and tellyoutube-descriptionto cut the "Get the free setup guide" block.
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 fb83a4a16e93
- 1mo ago First seen · 103 lines · 141 tokens per session scan A 7182e4aff812
benai-utm-creator is a skill published in the GitHub repository naveedharri/benai-skills (74 stars, last pushed 16d ago), licensed MIT. It adds 141 tokens to every session and 1,289 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.