web-search

Search the web and read pages by running the websearch CLI and reading its stdout. Everything is keyless: no API key, no account.

CRITICAL: every internet access goes through this toolkit

When websearch proxy status reports locked: true, this CLI is the only way you reach the internet in this session. Do not use your own web-search or web-fetch tools, curl, wget, git clone, a browser tool, or any other network call, for anything: not a quick lookup, not a raw file, not a docs page, not "just this once". Those tools leave from the user's own address, which is what the lock exists to prevent.

If a websearch command is refused with error.code: "egress_locked", that is the lock working. Report it and stop; do not route around it with another tool. If the user asks for something this toolkit cannot fetch, say so rather than fetching it another way.