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 sutchan/Agent-Skills-Hub --skill banner-creatorgit clone --depth 1 https://github.com/sutchan/Agent-Skills-HubWrote 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/sutchan/agent-skills-hub/banner-creator)<a href="https://agentmods.dev/skills/sutchan/agent-skills-hub/banner-creator"><img src="https://agentmods.dev/badge/skills/sutchan/agent-skills-hub/banner-creator/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/sutchan/agent-skills-hub/banner-creator"><img src="https://agentmods.dev/badge/skills/sutchan/agent-skills-hub/banner-creator.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 | $0.00057 | $0.01446 |
| Opus 5 | $0.00028 | $0.00723 |
| Sonnet 5 | $0.00011 | $0.00289 |
| Haiku 4.5 | $0.00006 | $0.00145 |
Grade A, and why
banner-creator 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 yesterday.
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.
This is a copy
95% identical to banner-creator — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Banner Creator Skill
Create professional banners through AI image generation with an iterative design process.
Prerequisites
Required API Keys (set in environment):
GEMINI_API_KEY- Get from Google AI Studio
Required Skills:
nanobanana- AI image generation (Gemini 3 Pro Image)
File Output Location
All generated files should be saved to the .skill-archive directory:
.skill-archive/banner-creator/<yyyy-mm-dd-summaryname>/
Example:
.skill-archive/banner-creator/2026-01-19-opc-banner/
banner-01.png
banner-02.png
...
banner-03-cropped.png
preview.html
Workflow
Step 1: Discovery & Requirements
Before generating, gather requirements from user:
Ask about:
-
Purpose - Where will the banner be used?
- GitHub README
- Twitter/X header
- LinkedIn banner
- Website hero
- YouTube channel art
-
Target ratio/size - See references/formats.md:
2:1(1280x640) - GitHub README3:1(1500x500) - Twitter header16:9(1920x1080) - Website hero
-
Style preference:
- Match existing logo/brand?
- Pixel art / 8-bit retro
- Minimalist / flat design
- Gradient / modern
- Illustrated / artistic
-
Content elements:
- Brand name / project name?
- Tagline / slogan?
- Logo character to include?
-
Color preferences:
- Existing brand colors?
- Let AI decide?
Wait for user confirmation before proceeding!
Step 2: Generate Banner Variations
Generate 20 banner variations using the nanobanana skill:
# Generate single banner
python3 <nanobanana_skill_dir>/scripts/generate.py "{style} banner for {brand}, {description}, {text elements}" \
--ratio 21:9 -o .skill-archive/banner-creator/<date-name>/banner-01.png
# Batch generate 20 banners
python3 <nanobanana_skill_dir>/scripts/batch_generate.py "{style} banner for {brand}, {description}, {text elements}" \
-n 20 --ratio 21:9 -d .skill-archive/banner-creator/<date-name> -p banner
What ships with it
15 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.
- .claude-plugin/plugin.json 706 B
- examples/images/banner-01.png 127 KB
- examples/images/banner-02.png 271 KB
- examples/images/banner-03.png 237 KB
- examples/images/banner-04.png 91 KB
- examples/images/banner-05.png 476 KB
- examples/images/banner-06.png 385 KB
- examples/images/github-banner-01.png 1353 KB
- examples/images/github-banner-02.png 1525 KB
- examples/images/github-banner-03.png 1215 KB
- examples/images/opc-banner-final.png 153 KB
- examples/opc-banner-creation.md 1.6 KB
- references/formats.md 2.3 KB
- scripts/crop_banner.py 4.0 KB runs code
- templates/preview.html 6.4 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.
- yesterday Changed · -5 lines · +43 tokens per session a2eb56b22ea3
- 11d ago First seen · 198 lines · 14 tokens per session scan A f3dee13c5006
banner-creator is a skill published in the GitHub repository sutchan/Agent-Skills-Hub (2 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 1,446 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to banner-creator, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
iflytek-hyper-tts
A text-to-speech tool that turns written text into an MP3 recording. It can use an authorized voice and adjust speaking speed, volume, and pitch.
iflytek-voiceclone-tts
A tool for creating a speech model from recorded audio and then generating speech that uses the cloned voice. Voice cloning means training software to imitate a person’s voice.
animated-sketch-diagram
A tool for making animated diagrams and flowcharts in a hand-drawn ink style, with paper-like backgrounds, simple icons, and moving dots along connections. It produces a self-contained HTML file and can also create a looping GIF.
iflytek-video-translate
A tool that translates a video’s speech into another language and creates dubbed audio. Video localization means adapting video content for viewers who speak a different language.
iflytek-speed-transcription
Ultra-fast speech transcription using iFLYTEK Speed Transcription API. Transcribe audio files (WAV/PCM/MP3) up to 5 hours in 20 seconds per hour. Supports Chinese, English, and 202+ Chinese dialects with automatic language detection. Use when user asks to transcribe audio files, convert speech to text, or mentions…
iflytek-image-understanding
An image-analysis tool that describes pictures and answers questions about what they contain. It uses an AI vision service, which interprets visual content rather than only reading text files.