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 frankxai/claude-skills-library --skill acos-visual-gengit clone --depth 1 https://github.com/frankxai/claude-skills-libraryWrote 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/frankxai/claude-skills-library/acos-visual-gen)<a href="https://agentmods.dev/skills/frankxai/claude-skills-library/acos-visual-gen"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/acos-visual-gen/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/frankxai/claude-skills-library/acos-visual-gen"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/acos-visual-gen.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 | $0.00069 | $0.01051 |
| Opus 5.5 | $0.00028 | $0.00420 |
| Sonnet 5.5 | $0.00014 | $0.00210 |
| Haiku 4.5 | $0.00007 | $0.00105 |
Grade A, and why
acos-visual-gen 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 1mo 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ACOS Visual Generator
What This Skill Does
Creates research-grounded images by:
- Researching the topic via web search
- Extracting key facts for accuracy
- Constructing a detailed image prompt
- Generating via Nano Banana MCP (Gemini 2.5 Flash Image)
Prerequisites
- Nano Banana MCP server configured
- WebSearch tool available
Quick Start
User: "Create a 3D infographic about quantum computing"
Process:
1. WebSearch → Extract key facts
2. Construct prompt with style instructions
3. mcp__nanobanana__generate_image()
4. Return image with sources
Visual Styles
| Style | Description |
|---|---|
standard |
Clean scientific illustration, modern, professional |
minimalist |
Bauhaus, flat vector, 2-3 colors, negative space |
photorealistic |
Cinematic lighting, 8K, detailed textures |
3d |
Dark Premium 3D — navy background, glass/chrome surfaces, neon accents. NEVER claymorphic |
technical |
Da Vinci notebook, ink sketch, annotations |
futuristic |
Cyberpunk HUD, neon, holographic |
vintage |
19th century lithograph, sepia, engraving |
cartoon |
Educational comic, vibrant, cel-shaded |
Audience Levels
| Level | Target |
|---|---|
elementary |
Ages 6-10, bright, simple, fun icons |
highschool |
Standard textbook, clean, accurate |
college |
Academic journal, high detail, data-rich |
expert |
Technical schematic, extremely dense |
Step-by-Step Process
Step 1: Research
WebSearch("{topic} facts key information 2026")
Extract 3-5 verifiable facts.
Step 2: Construct Prompt
Create a {aspect_ratio} {style_description} infographic about {topic}.
VISUAL STYLE: {style_instruction}
AUDIENCE: {audience_instruction}
INCLUDE:
- {fact_1_visualized}
- {fact_2_visualized}
- {fact_3_visualized}
COMPOSITION:
- Clear layout with visual hierarchy
- Text should be large and legible
- Include labels and annotations
Step 3: Generate
mcp__nanobanana__generate_image({
prompt: "{constructed_prompt}",
aspect_ratio: "16:9",
model_tier: "pro",
enable_grounding: true,
thinking_level: "high",
resolution: "high"
})
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.
- 1mo ago First seen · 165 lines · 69 tokens per session scan A de150f3d04fc
acos-visual-gen is a skill published in the GitHub repository frankxai/claude-skills-library (47 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 1,051 once invoked, about $0.0003 per session on Opus 5.5. 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
scaffold-exercises
A directory scaffold for course exercises, with sections, exercise folders, and optional problem, solution, or explanation versions. It creates the required Markdown files and checks the result with the repository's linter.
teach
A teaching-workspace guide for creating lessons, reference sheets, learning records, and resource notes around a topic the user wants to learn.
token-saver
Token optimization guide for Claude Code. This skill should be used when the user wants to reduce API costs, learn model routing strategies, or understand how to use free/cheaper tools (Ollama, Haiku) instead of burning expensive Claude tokens on routine tasks. Triggers on: save tokens, reduce costs, token tips, cheap…
wayfinder
A planning method that maps a large, uncertain project into linked decision tickets in a repository's issue tracker. An issue tracker is a system for recording and organizing project work.
domain-modeling
A practice for building and maintaining a project’s domain model: the shared terms, concrete scenarios, and recorded architecture decisions that describe what the software is about.
migrate-to-shoehorn
A testing guide for Shoehorn, a TypeScript library that lets tests provide only the fields they need from a larger data type.