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 agentmods add skills/agentic-dev3o/devx-plugins/banana-youtubenpx skills add agentic-dev3o/devx-plugins --skill banana-youtubegit clone --depth 1 https://github.com/agentic-dev3o/devx-pluginsWhat 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 | $0.00054 | $0.01376 |
| Opus 5 | $0.00027 | $0.00688 |
| Sonnet 5 | $0.00011 | $0.00275 |
| Haiku 4.5 | $0.00005 | $0.00138 |
Grade A, and why
banana-youtube 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 2d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Thumbnail Maker
Input: $ARGUMENTS (optional — video topic or thumbnail description)
If $ARGUMENTS is provided, use it as the video topic and skip to prompt building. If empty, ask what the video is about.
Requirements
uvinstalledGEMINI_API_KEYenvironment variable set (get one at https://aistudio.google.com/apikey)
Workflow
- Understand — Parse the user's request. Identify the video topic, target emotion, and channel style. If the subject or intent is unclear, ask ONE clarifying question.
- Build prompt — Construct a detailed Gemini prompt using the Prompt Formula below. Prioritize dramatic facial expressions, bold colors, and high visual contrast.
- Configure — ALWAYS use 16:9, 2K, and the Pro model. These are non-negotiable for thumbnails.
- Generate — Run the script.
- Deliver — Report the saved file path. Do NOT read the image file back. Offer to iterate: adjust expression, background color, composition, or prompt.
Prompt Formula
Build every thumbnail prompt using this structure:
[Subject with Expression] + [Dramatic Reaction/Gesture] + [Bold Colored Background] + [Close-Up Rule-of-Thirds] + [Hyper-Saturated Photography with Rim Lighting]
Rules
- Positive framing: Describe what IS in the image, never what is absent.
- Strong verb opener: Start with Generate, Create, Capture, Render, Design, Compose.
- Faces sell clicks: Always include a face with an exaggerated expression — wide eyes, open mouth, raised eyebrows, shocked grin.
- Bold backgrounds: Use solid, saturated colors (electric blue, hot pink, neon green, deep orange) or dramatic gradients.
- Rim lighting: Add a strong backlight or rim light to separate the subject from the background and create a cinematic pop.
- Text space: Reserve approximately one-third of the frame for text overlay — typically the opposite side from the subject.
- No celebrity likenesses: Never reference real public figures. Describe features generically.
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.
- 2d ago First seen · 112 lines · 54 tokens per session scan A b9be80e53f6b
banana-youtube is a skill published in the GitHub repository agentic-dev3o/devx-plugins (11 stars, last pushed 14d ago), licensed MIT. It adds 54 tokens to every session and 1,376 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…