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-thumbnailgit 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)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/youtube-thumbnail"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/youtube-thumbnail/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"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/youtube-thumbnail.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 | $0.00204 | $0.03564 |
| Opus 5.5 | $0.00082 | $0.01426 |
| Sonnet 5.5 | $0.00041 | $0.00713 |
| Haiku 4.5 | $0.00020 | $0.00356 |
Grade C, and why
youtube-thumbnail 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 2mo 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.
Read `Context/youtube-thumbnail-style.md` if it exists; pull palette, framing library, expression library, lighting, prohibited list, and anchor refs. If it is missing or has `[FILL]` blocks, do not refuse: fall back to How it starts
The opening of the file, as written. The whole thing — 143 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 must end up in
medias[]. If they gave you a LIST, read EVERY image in the list, then pass every relevant one (don't pre-select just one). Every reference image MUST be visually read with theReadtool before the prompt is built (see rule 2).
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.
If the user did NOT attach a photo of Ben and there is no ben_reference_*.jpg in refs/, ask once for a photo. Without it, new-with-ben cannot produce a faithful Ben rendering.
What ships with it
19 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.
- references/brand-examples/01-claude-second-brain-sales.jpg 188 KB
- references/brand-examples/02-skill-10x-claude-output.jpg 195 KB
- references/brand-examples/03-claude-tag-slack.jpg 220 KB
- references/brand-examples/04-every-way-claude-second-brain.jpg 104 KB
- references/brand-examples/05-de-slop-ai-output.jpg 189 KB
- references/brand-examples/06-6-things-wrong-ai-os.jpg 204 KB
- references/brand-examples/07-claude-managed-agents-sell-ai.jpg 231 KB
- references/brand-examples/08-stop-using-claude-without-agentic-os.jpg 228 KB
- references/brand-examples/09-12-claude-plugins-skills-mcps.jpg 210 KB
- references/brand-examples/10-every-claude-cowork-feature.jpg 214 KB
- references/brand-examples/README.md 3.7 KB
- references/manifest.md 1.4 KB
- references/models.md 7.0 KB
- references/niche-research.md 4.7 KB
- references/prompt-builder.md 14 KB
- references/skill-rules.md 1.6 KB
- references/troubleshooting.md 8.4 KB
- references/variation-ideation.md 7.8 KB
- references/visual-language.md 9.3 KB
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.
- 2mo ago First seen · 143 lines · 204 tokens per session scan C 8f952274b81d
youtube-thumbnail is a skill published in the GitHub repository naveedharri/benai-skills (78 stars, last pushed 28d ago), licensed MIT. It adds 204 tokens to every session and 3,564 once invoked, about $0.0008 per session on Opus 5.5. 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.
youtube-thumbnail compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| youtube-thumbnailnaveedharri/benai-skills | Skill | 78 | 28d ago | MIT | C | 204 | Claude Code |
| projectmodu-ai/moai-cowork | Skill | 315 | 29d ago | Apache-2.0 | A | 475 | Claude Code |
| doc-html-slidemodu-ai/moai-cowork | Skill | 315 | 29d ago | Apache-2.0 | A | 438 | Claude Code |
| cs-channel-messagemodu-ai/moai-cowork | Skill | 315 | 29d ago | Apache-2.0 | A | 465 | Claude Code |
| media-higgsfield-explainermodu-ai/moai-cowork | Skill | 315 | 29d ago | Apache-2.0 | A | 244 | Claude Code |
| media-gpt-image-promptmodu-ai/moai-cowork | Skill | 315 | 29d ago | Apache-2.0 | A | 334 | Claude Code |
| career-portfoliomodu-ai/moai-cowork | Skill | 315 | 29d ago | Apache-2.0 | A | 124 | Claude Code |