Trigram-indexed regex search for large codebases. Loads automatically on startup to accelerate all grep/search operations. Implements sparse n-gram indexing with frequency-weighted trigram decomposition, bloom-filter adjacency masks, and mmap'd posting lists for sub-50ms regex matching across 500k+ files.
Generate styled HTML reports using the Terminal Dashboard theme. Use when the user needs to create an HTML report, dashboard, data visualization, or styled output document. Triggers include requests to "generate a report", "create an HTML file", "make a dashboard", "visualize data", "export to HTML", or any task requiring formatted HTML output with the project's visual identity.
Execute and monitor options orders via Interactive Brokers. Use when placing trades, monitoring fills, or managing orders. Triggers on "execute order", "place trade", "buy calls", "sell puts", "bull call spread", "bear put spread", "monitor fills", "check order status", or any IB order-related task.
MenthorQ data extraction — CTA positioning, dashboards, screeners, forex, summaries, and QUIN AI screener prompts. Triggers on "menthorq", "cta positioning", "menthorq dashboard", "menthorq screener", "quin screener", "menthorq forex", or any MenthorQ-related query.
Generate tweet copy and a matching infographic image for sharing trades on X (Twitter). Use when the user says "tweet-it", "tweet this trade", "create a tweet", "X post", or wants to share a trade on social media. Produces tweet text (ready to copy), an infographic card image, and a self-contained preview page with copy buttons for both text and image.
Cloud-based AI browser agent for autonomous web tasks. Use when you need to perform complex browser automation tasks autonomously, scrape websites that require AI reasoning, fill forms intelligently, extract structured data from web pages, or perform multi-step web workflows. Triggers include "autonomous browsing", "AI browser", "browser-use", "scrape with AI", "extract structured data from website", "fill out form intelligently", "navigate website and find", or when the task requires reasoning about page content rather than just clicking elements. Prefer this over web-fetch when the task involves multiple steps, requires understanding page semantics, or when you need structured output.
Web searching and content fetching. Use Exa MCP tools (web_search_exa, company_research_exa, get_code_context_exa) as the PRIMARY method for web search, company research, and content retrieval. Fall back to agent-browser only when Exa cannot handle the task (e.g., interactive forms, authentication, screenshots, JavaScript-rendered content). Triggers include "search the web", "find information about", "look up", "research this company", "fetch this page", "scrape data from a page", "open a website", or any task requiring web content.
Implement file-system-based context engineering for agentic AI projects. Use when building persistent memory systems, context pipelines, token-budget management, context repositories, or agentic file system abstractions. Triggers on "context engineering", "context pipeline", "context management", "persistent memory", "token budget", "context constructor", "context evaluator", "agentic file system", "context rot", "memory lifecycle", or any task involving structured management of LLM context windows, history/memory/scratchpad tiers, or governance of context artifacts across agent sessions. Also use when asked to add memory, traceability, or context governance to an existing agentic project.