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-thumbnail-generategit 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-thumbnail-generate)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/youtube-thumbnail-generate"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/youtube-thumbnail-generate/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-thumbnail-generate"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/youtube-thumbnail-generate.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 | $0.00169 | $0.04210 |
| Opus 5 | $0.00084 | $0.02105 |
| Sonnet 5 | $0.00034 | $0.00842 |
| Haiku 4.5 | $0.00017 | $0.00421 |
Grade C, and why
youtube-thumbnail-generate scanned grade C 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 7d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
If the spec is missing or has `[FILL]` blocks: don't refuse. Fall back to the locked Ben AI thumbnail visual language (see `references/visual-language.md` for the full catalog). Built-in defaults: How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Thumbnail Generate
One-shot thumbnail generation. Takes a concept (plus optional reference image and count), infers everything else, ships 3 variants and a manifest.
Inputs
Two things, ideally both in the user's first message:
- Concept — what the thumbnail should show. A sentence or phrase. ("Claude Code Skills, why it changes everything for solo founders")
- Reference image(s) (optional but recommended, may be multiple) — a past thumbnail, a photo of Ben, a second subject, a style anchor, a real logo PNG, or any combination. Determines the mode AND ALL of them must be passed into the generation. Never silently drop a user-supplied reference; if they gave you one, it has to end up in
medias[]. If they gave you a LIST, read EVERY image in the list, then pass every relevant one tomedias[](don't pre-select just one). Also: every reference image MUST be visually read (via theReadtool on the file path) before the prompt is built, so the prompt captures each reference's actual style, texture, palette, composition, and recurring motifs rather than relying only on the style spec defaults.
If the user mentions a reference image but does not provide a path or attachment, ASK for the path BEFORE doing anything else. Examples that require asking: "use my previous thumbnail as a ref" (which file?), "include the Anthropic logo" (where is the PNG?), "match this style" (which image?). Ask in one short line: "Got it — what's the file path for the reference image?" Do not guess, do not proceed, do not generate without seeing the path.
Optional third: variant count. Defaults to 3. Max 4.
If the concept is missing or genuinely unclear, ask ONE combined question:
"What should the thumbnail show, and how many variations do you want? (default 3)"
Do not split into multiple questions. Do not ask about mode, model, or palette; all of that is inferred or read from the style spec.
Identity Anchor (no Soul required)
Every new-with-ben thumbnail uses a reference photo of Ben as the identity anchor, passed as medias[0]. The photo lives at Projects/youtube/thumbnails/refs/ben_reference_{YYYY-QQ}.jpg.
What ships with it
6 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.
- 7d ago First seen · 220 lines · 169 tokens per session scan C e2a1dbcdf77c
youtube-thumbnail-generate is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed today), licensed MIT. It adds 169 tokens to every session and 4,210 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
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.
media-audio-gen
An audio-generation skill for turning text into speech, cloning a voice from a sample, dubbing videos into other languages, and creating sound effects.
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.
media-higgsfield-identity
A Higgsfield workflow for keeping a person, character, product, or other visual reference consistent across generated images. It chooses between a trained identity model and a one-image reference method.
media-notebooklm-slide-prompt
A prompt builder that turns lecture, class, or seminar notes into instructions for NotebookLM Studio to create slides. It also creates image prompts for each slide using Nano Banana, Google's image-generation model.
design-logo
A brand-aware logo design workflow that reads a project's visual rules, chooses a logo type, and prepares a vector or symbol-based logo request.