ultra-fetchlisted

# Ultra Fetch ## The division of labor `ultra-fetch` gets you **access** (a stealth browser that reaches what WebFetch can't) and **clean output** (markdown with the boilerplate stripped, written to a file). Everything else is your judgment: which command fits the question, how deep to go, how much of the result to actually read. Reach for it by default when you need a page's real content. Stay away from it for a fact you already know, for anything behind a login, and when the task is editing this tool's own code. ## Step 1 — run it ```bash ${CLAUDE_SKILL_DIR}/scripts/ultra-fetch fetch <url> --output <path> ``` The first run provisions a dedicated environment and downloads browser engines — several hundred MB, once. It prints a notice and proceeds; don't treat the pause as a hang. If a command exits **2**, setup didn't finish: run `${CLAUDE_SKILL_DIR}/scripts/ultra-fetch setup --browsers` and tell the user about the one-time download. ## Step 2 — ask the CLI what it can do ```bash ${CLAUDE_SKILL_DIR}/scripts/ultra-fetch catalog ``` Prints every command, flag, default, exit code and output shape as JSON, generated from the argument parser itself. **Work from what it prints, not from a flag list you remember** — including any in this file. The catalog is correct for the installed version by construction; prose copies rot silently. ## The output contract (this will trip you up if you skim) Every command writes its result to a **file** and prints **one summary line to