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/commands/matt-dionis/claude-code-configs/ai-advanced-features-setup)<a href="https://agentmods.dev/commands/matt-dionis/claude-code-configs/ai-advanced-features-setup"><img src="https://agentmods.dev/badge/commands/matt-dionis/claude-code-configs/ai-advanced-features-setup/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/commands/matt-dionis/claude-code-configs/ai-advanced-features-setup"><img src="https://agentmods.dev/badge/commands/matt-dionis/claude-code-configs/ai-advanced-features-setup.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 | $0.00017 | $0.03740 |
| Opus 5.5 | $0.00007 | $0.01496 |
| Sonnet 5.5 | $0.00003 | $0.00748 |
| Haiku 4.5 | $0.00002 | $0.00374 |
Grade A, and why
ai-advanced-features-setup 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 — 569 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up Advanced AI SDK Features
Configure cutting-edge AI SDK capabilities for: $ARGUMENTS
Current Advanced Features Analysis
Existing advanced implementations: !grep -r "experimental\|reasoning\|computer\|streamUI" . --include="*.ts" --include="*.tsx" | head -5
Provider-specific features: !grep -r "o1-preview\|deepseek\|computer_20241022\|responses" . --include="*.ts" | head -5
Experimental configurations: !grep -r "experimental_" . --include="*.ts" | head -5
Advanced Feature Categories
Reasoning Models: O1-Preview, O3-mini, DeepSeek R1 with thinking capabilities Computer Use: Claude 3.5 Sonnet screen interaction and automation Generative UI: Dynamic component streaming with streamUI Edge Optimization: Vercel Edge Runtime performance enhancements Experimental: Cutting-edge AI SDK experimental features
Your Task
- Analyze project requirements for advanced AI capabilities
- Configure reasoning models with thinking mode and extended context
- Set up computer use tools for automation and testing
- Implement generative UI with dynamic component generation
- Optimize for edge deployment with performance enhancements
- Enable experimental features safely with proper fallbacks
- Add comprehensive monitoring for advanced feature usage
- Create testing strategies for cutting-edge capabilities
Implementation Requirements
Reasoning Models Integration
- O1-Preview and O3-mini setup with thinking tokens
- DeepSeek R1 configuration for enhanced reasoning
- Thinking mode visibility and streaming
- Extended context window management
- Reasoning-specific prompt engineering
Computer Use Capabilities
- Claude 3.5 Sonnet computer use tool setup
- Screen interaction and automation
- Browser automation and testing
- File system operations
- Cross-platform compatibility
Generative UI Features
- streamUI implementation for dynamic components
- Real-time component generation
- Interactive widget creation
- Chart and visualization streaming
- Form and dashboard generation
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 · 569 lines · 17 tokens per session scan A c0ccad3a3cc5
ai-advanced-features-setup is a command published in the GitHub repository Matt-Dionis/claude-code-configs (619 stars, last pushed 1y ago), licensed MIT. It adds 17 tokens to every session and 3,740 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
audit-prompt
Evaluate an existing prompt for clarity, effectiveness, and edge cases.
laravel-ai-sdk
Build AI features with the first-party Laravel AI SDK (Laravel 13+); use the laravel:ai-sdk skill exactly as written.
vlm-ocr-evaluation
Run the vlm-ocr skill in its evaluate phase: compare candidate OCR systems against a stratified human-transcribed ground-truth sample and pick a model on measured CER/WER before committing to a bulk run.
dare-llm-integration
Integração segura e eficiente com LLMs (Gemini, Claude, OpenAI, Ollama) em projetos DARE.