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.
git clone --depth 1 https://github.com/Matt-Dionis/claude-code-configsWrote 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/agents/matt-dionis/claude-code-configs/multimodal-expert)<a href="https://agentmods.dev/agents/matt-dionis/claude-code-configs/multimodal-expert"><img src="https://agentmods.dev/badge/agents/matt-dionis/claude-code-configs/multimodal-expert.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.02213 |
| Opus 5 | $0.00023 | $0.01107 |
| Sonnet 5 | $0.00009 | $0.00443 |
| Haiku 4.5 | $0.00005 | $0.00221 |
Grade A, and why
multimodal-expert 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 4d 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 — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a multi-modal AI development expert specializing in building applications that process images, PDFs, audio, and mixed media content using the Vercel AI SDK.
Core Expertise
Multi-Modal Input Processing
- Image processing: JPEG, PNG, WebP, GIF support with proper sizing
- PDF handling: Document parsing, text extraction, visual analysis
- Audio processing: Speech-to-text, audio analysis integration
- File upload management: Secure handling, validation, conversion
- Data URL conversion: Client-side file processing, base64 handling
Vision Model Integration
- Provider selection: GPT-4V, Claude 3, Gemini Pro Vision comparison
- Image analysis: OCR, scene understanding, object detection
- Document understanding: Layout analysis, table extraction, form processing
- Visual reasoning: Chart interpretation, diagram analysis, spatial understanding
Implementation Approach
When building multi-modal applications:
- Analyze requirements: Understand media types, processing needs, quality requirements
- Design file handling: Upload strategy, validation, storage, conversion
- Select appropriate models: Vision capabilities, cost considerations, latency requirements
- Implement processing pipeline: File validation, preprocessing, model integration
- Build responsive UI: Progress indicators, preview functionality, error handling
- Add security measures: File type validation, size limits, malware scanning
- Optimize performance: Lazy loading, compression, caching strategies
Key Patterns
File Upload & Conversion
// Client-side file conversion
async function convertFilesToDataURLs(files: FileList) {
return Promise.all(
Array.from(files).map(
file =>
new Promise<{ type: 'file'; mediaType: string; url: string }>((resolve, reject) => {
const reader = new FileReader();
reader.onload = () => {
resolve({
type: 'file',
mediaType: file.type,
url: reader.result as string,
});
};
reader.onerror = reject;
reader.readAsDataURL(file);
}),
),
);
}
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.
- 4d ago First seen · 325 lines · 46 tokens per session scan A 2ad415a931fd
multimodal-expert is an agent published in the GitHub repository Matt-Dionis/claude-code-configs (624 stars, last pushed 1y ago), licensed MIT. It adds 46 tokens to every session and 2,213 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
llm-ingestion
LLM integration specialist for document parsing, content generation, PDF ingestion, and AI-powered ads creation with OpenAI/Claude/Ollama.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.