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 DeepKolor/deepkolor-agent-skills --skill youtube-thumbnail-agentgit clone --depth 1 https://github.com/DeepKolor/deepkolor-agent-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/deepkolor/deepkolor-agent-skills/youtube-thumbnail-agent)<a href="https://agentmods.dev/skills/deepkolor/deepkolor-agent-skills/youtube-thumbnail-agent"><img src="https://agentmods.dev/badge/skills/deepkolor/deepkolor-agent-skills/youtube-thumbnail-agent/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/deepkolor/deepkolor-agent-skills/youtube-thumbnail-agent"><img src="https://agentmods.dev/badge/skills/deepkolor/deepkolor-agent-skills/youtube-thumbnail-agent.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 | $0.00111 | $0.00488 |
| Opus 5 | $0.00056 | $0.00244 |
| Sonnet 5 | $0.00022 | $0.00098 |
| Haiku 4.5 | $0.00011 | $0.00049 |
Grade A, and why
youtube-thumbnail-agent 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 12d 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.
What it actually says
YouTube Thumbnail Agent
Lite edition — routing and core rules for agent discovery. Full prompt templates, platform playbooks, and production workflows run on DeepKolor.
Click-optimized 1280×720 thumbnails — face + hook text, bold text hooks, or product hero layouts.
When to use
See description in frontmatter — the agent loads it at startup for routing.
Workflow
- Always 16:9; keep subject and hook text in safe zones (avoid bottom-right duration badge area).
- High contrast, readable at small size; one clear focal point.
- Use image-to-image when preserving a real face, product, or screenshot.
Defaults
aspectRatio=16:9, resolution=1K
Tool: create_image_task
{
prompt: string,
scene: "text-to-image" | "image-to-image",
aspectRatio?: string,
imageUrls?: string[],
resolution?: "1K"
}
Available when your agent runtime exposes DeepKolor generation tools. Otherwise use this skill as a prompt-engineering guide and adapt tool names to your stack.
Boundaries
- YouTube thumbnails only — not general posters or paid ad banners.
Output
After generation, reply briefly: what was created, key parameters, and one useful next step. Return a full prompt only when the user explicitly asks.
Full version
Production-grade references (SOPs, templates, platform rules) ship inside DeepKolor — not in this public lite package.
What ships with it
1 file 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.
- 12d ago First seen · 56 lines · 111 tokens per session scan A b4e4bbea5ca3
youtube-thumbnail-agent is a skill published in the GitHub repository DeepKolor/deepkolor-agent-skills (2 stars, last pushed 23d ago), licensed MIT. It adds 111 tokens to every session and 488 once invoked, about $0.0006 per session on Opus 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 2026-08-31.
Other skills, from other repositories
videoagent-image-studio
Tired of juggling 8 API keys? This skill gives you one-command access to Midjourney, Flux, Ideogram, and more, with zero setup. Use when you want to generate any image without worrying about API keys.
youtube
Use whenever the user mentions YouTube, video uploads, channel management, playlists, video SEO, or any YouTube Data API operation. Manages videos, playlists, comments, captions, subscriptions, thumbnails, analytics, and more.
youtube-transcribe
A tool that downloads YouTube videos or subtitles, turns speech into text, and can translate English into Chinese in a bilingual Markdown file.
gpt-image-2-prompt-engine
A structured prompt-writing tool for GPT-Image-2, using reusable JSON templates and a four-step workflow. It is designed for controlled commercial images such as product photos, posters, infographics, brand visuals, UI screenshots, and character designs.
photo-revival
Turn ordinary photos or everyday snapshots into poetic hand-drawn illustrations with large white-paper negative space, vivid localized color, subtle collage accents, and tiny handwritten captions. Use when a user wants a real photo reimagined as an illustration rather than filtered, beautified, or photorealistically…
faceless-youtube
Use when creating and automating faceless YouTube channels using AI-generated scripts, TTS voiceovers, stock footage, and automated publishing workflows with zero on-camera presence.