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-descriptiongit 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-description)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/youtube-description"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/youtube-description/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-description"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/youtube-description.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 | $0.00130 | $0.01447 |
| Opus 5.5 | $0.00052 | $0.00579 |
| Sonnet 5.5 | $0.00026 | $0.00289 |
| Haiku 4.5 | $0.00013 | $0.00145 |
Grade A, and why
youtube-description 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Description
Stage 5, the last one. Ends with a fully armed Unlisted draft and the card moved.
Does not make the video public. A person does that.
Preconditions, and check all three
Read the Notion card first. See references/notion-card.md.
| Needed | Why |
|---|---|
UTM code filled |
no code means no links to write |
Bitly imported ticked |
an unchecked box means the links are not live. Do not write a description full of dead links |
Chapters filled |
the template has a chapters block that cannot be left empty |
If any is missing, say which stage has not run and stop.
Steps
Task Progress:
- [ ] 1. Assemble the description from the template
- [ ] 2. Run the substitution check
- [ ] 3. Show the whole block and get the go ← HUMAN CHECKPOINT
- [ ] 4. Write description + tags into Studio
- [ ] 5. Read it back
- [ ] 6. Tags read back, chapters render, spacing checked
- [ ] 7. Move the card to Ready to publish
1. Assemble from the template
Read references/description-template.md. It is the canonical block. Fill the three
variables and leave everything else byte-identical.
{{CODE}}: the five-letter code, from the card.{{CHAPTERS}}: from the card,MM:SS – Title, first line00:00 – Intro.{{REFERENCED_VIDEOS}}: the videos Ben actually points at in this video.
Two things the template file covers that matter most:
- When there is no lead magnet, the "Get the free setup guide" block comes out. Three
c.benai.colinks remain instead of four. - The arrow is
⤵️and the TV is📺. Copy them, do not retype them.
references/description-block.md holds the worked example if the template's shape is unclear.
Note that the Cowork link never appears in the description, so the 2026-08-26 suffix change
from -cowork to -os does not touch this stage. Only accelerator, free, aioperator and
agency are published.
2. The substitution check
Assert, before touching Studio:
- Exactly four
c.benai.colinks with a lead magnet, exactly three without. - Every one carries the current code.
- The previous video's code appears zero times.
- Character count under 5000. Report it.
- Every
c.benai.colink resolves. Open them. A-freelink that 404s means the Kit lead magnet page was never built, which happened on 2026-08-26. That is a blocker, not a warning: stop, go finish stage 3, come back. - The block order matches what Ben promises on camera. If he says "the first link in the description", the thing he is describing has to be the first link. See the template.
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 ad330df5e6ae
- 1mo ago First seen · 128 lines · 130 tokens per session scan A 06864ddc6f95
youtube-description is a skill published in the GitHub repository naveedharri/benai-skills (74 stars, last pushed 16d ago), licensed MIT. It adds 130 tokens to every session and 1,447 once invoked, about $0.0005 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.