fetcher

File-based inter-agent messaging. Check inbox, send bugs/requests to other projects, acknowledge resolved issues. Use for cross-project agent communication.

Search arXiv for academic papers. Use when user says "find papers on", "search arxiv", "look up research", "academic papers about", "what papers exist on", "use your arxiv tool", or asks about scientific/ML research topics.

Step back and critically reassess project state. Use when asked to "assess", "step back", "fresh eyes", "check alignment", "sanity check", "health check", or "evaluate what's working". Offer to run after major changes (don't auto-run).

Free web and local search via Brave Search API. Use when user says "brave search", "search with brave", "brave web search", "brave local search", "local search", "find businesses near", or "near me".

Submit code review requests to multiple AI providers (GitHub Copilot, Anthropic Claude, OpenAI Codex, Google Gemini) and get patches back. Use when user says "code review", "review this code", "get a patch for", or needs AI-generated unified diffs for code fixes.

Fetch up-to-date library documentation from Context7 API. Use when user asks "how do I use this library", "show me docs for", "library documentation", "API reference for", or needs current documentation for any code library.

Distill PDF, URL, or text into Q&A pairs stored in memory. Use --context for domain-focused extraction.

Convert a document (PDF, URL, text) into Q&A pairs stored in memory.

Verifies relationships between a source text (e.g. Episode, Task) and existing Knowledge Graph lessons. Runs KNN/Hybrid search to find candidates, then uses LLM (scillm) to verify "verifies", "contradicts", or "related" stances with strict rationales.

Episodic Memory Archiver. Stores full conversation transcripts with embeddings and analysis into ArangoDB. Use this to save the "User Story" or "Chain of Thought".

Fetch web pages, PDFs, and documents with automatic fallbacks and content extraction. Use when user says "fetch this URL", "download this page", "crawl this website", "extract content from", "get the PDF", or provides URLs needing retrieval.

MEMORY FIRST - Query memory BEFORE scanning any codebase. Use when encountering ANY problem, error, or task. Call "recall" FIRST, then scan codebase only if nothing found. Triggers: "check memory", "recall", "have we seen", "remember how".

Generate test PDF fixtures with known, extractable content. Creates PDFs with sections, tables, figures, requirements, equations, and annotations. Use when user needs "create test PDF", "generate PDF fixture", "make sample PDF for testing".

Paid research assistant with real-time web search. Use when user asks "what's the latest", "current pricing for", "recent news about", "search the web for", "fact check this", "what's new in", or needs up-to-date information beyond training data.

Extract Question-Reasoning-Answer pairs from text. Use --context for domain-focused extraction. Validates answers are grounded in source text.

Provision, manage, and terminate RunPod GPU instances for LLM training. Use when user says "spin up GPU", "create RunPod instance", "terminate pod", "check GPU status", "provision training server", or needs cloud GPU resources.

LLM completions and Lean4 theorem proving via scillm. Use when user needs "batch LLM calls", "parallel completions", "prove this mathematically", "formal verification", "Lean4 proof", or "JSON extraction from text".

Sync .agents/skills with the canonical agent-skills repo. Use when asked to "sync skills", "publish skills", or "pull skills" between projects.

Control Chrome browser via CLI - navigate, click, type, screenshot, read pages. Use when user says "open browser", "click on", "fill form", "take screenshot", "navigate to", "automate browser", or needs any browser automation task.

Parse and extract code symbols using tree-sitter. Use when you need to extract functions, classes, or understand code structure from files or code blocks.

Extract transcripts from YouTube videos. Use when user says "get transcript", "transcribe this video", "what does this YouTube video say", "extract captions", "youtube transcript", or provides a YouTube URL and wants the text content.