Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add biggora/claude-plugins-registry/plugin install project-delivery-orchestratorWrote 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/biggora/claude-plugins-registry/youtube-thumbnail)<a href="https://agentmods.dev/skills/biggora/claude-plugins-registry/youtube-thumbnail"><img src="https://agentmods.dev/badge/skills/biggora/claude-plugins-registry/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/biggora/claude-plugins-registry/youtube-thumbnail"><img src="https://agentmods.dev/badge/skills/biggora/claude-plugins-registry/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 | $0.00099 | $0.10111 |
| Opus 5 | $0.00049 | $0.05056 |
| Sonnet 5 | $0.00020 | $0.02022 |
| Haiku 4.5 | $0.00010 | $0.01011 |
Grade D, and why
youtube-thumbnail scanned grade D with 5 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 8d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
r = requests.post("http://127.0.0.1:7860/sdapi/v1/txt2img", json=payload, timeout=120) Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
env = os.environ.copy() Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| 3 | **MCP Imagen 4** (Vertex AI) | `which mcp-imagen-go` + `~/.gemini/settings.json` | ★★★★★ | Vertex AI pricing | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
r = requests.get("http://127.0.0.1:7860/sdapi/v1/samplers", timeout=3) Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
r = subprocess.run(["which", "mcp-imagen-go"], How it starts
The opening of the file, as written. The whole thing — 1,065 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Thumbnail Generation Skill (2026 Edition)
Overview
This skill enables fully autonomous generation of professional YouTube thumbnails
in 11 strategic styles from THUMBNAILS.md. Zero user interaction required after the
initial request. The agent auto-selects style, builds a prompt, generates the base
image via the best available AI backend, applies compositing and text via Pillow,
and saves a final 1280×720 PNG to /mnt/user-data/outputs/thumbnail.png.
When to Trigger This Skill
Trigger when the user:
- Says "create a thumbnail", "make a thumbnail", "generate a YouTube thumbnail"
- Provides a video title or topic and needs a visual
- Wants product video covers, presentation title slides, or channel art
- Needs batch thumbnail creation or automation for a YouTube workflow
Architecture: Two-Layer Pipeline
[User Request]
│
▼
[Layer 1: AI Image Generation] ← Base image via best available backend
│
▼
[Layer 2: Pillow Compositing] ← Resize to 1280×720, effects, text overlay
│
▼
[Output: /mnt/user-data/outputs/thumbnail.png]
Backend Priority Table
Auto-detect each backend by testing availability. Use the first one that works.
| # | Backend | Detection Method | Quality | Cost |
|---|---|---|---|---|
| 1 | A1111 Local SD | GET localhost:7860/sdapi/v1/samplers |
★★★★ | Free (own GPU) |
| 2 | ComfyUI Local | GET localhost:8188/history |
★★★★ | Free (own GPU) |
| 3 | MCP Imagen 4 (Vertex AI) | which mcp-imagen-go + ~/.gemini/settings.json |
★★★★★ | Vertex AI pricing |
| 4 | Gemini API (Nano Banana 2) | GEMINI_API_KEY env + google-genai installed |
★★★★ | Free quota |
| 5 | fal.ai FLUX | FAL_KEY env + fal-client installed |
★★★★ | $0.03/MP |
| 6 | OpenAI gpt-image-1 | OPENAI_API_KEY env + openai installed |
★★★★ | ~$0.04/img |
| 7 | Pillow-only fallback | Always available | ★★ | Free |
The 11 Thumbnail Styles
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.
- 8d ago First seen · 1,065 lines · 99 tokens per session scan D a201808fa2a6
youtube-thumbnail is a skill published in the GitHub repository biggora/claude-plugins-registry (2 stars, last pushed 11d ago), licensed MIT. It adds 99 tokens to every session and 10,111 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it D with 5 findings (sends data to an external url, harvests environment variables, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.