multi-searchlisted

# Multi-Search Find the requested content through the shared Core's MCP tools or CLI. Tool schemas and CLI help define parameters. For CLI, read [cli.md](references/cli.md). Keep the user's target and constraints. ## Choose execution - **Assigned search executor:** follow [search.md](references/search.md) directly. This branch takes precedence; never delegate again. - **Known URL or cached source:** fetch/read directly using [verification.md](references/verification.md); no search or delegation needed. - **Direct mode:** only if the user requests it or the host has no subagent capability. Disclose this mode and follow [search.md](references/search.md). Missing setup or failed dispatch is an explicit error; do not silently switch models or rerun the search in the main Agent. - **Otherwise, new search:** before retrieving candidates, use one host subagent with a configured or explicitly available lightweight model. Read [subagents.md](references/subagents.md) for dispatch and handoff. The user need not request delegation each time; model choice belongs to the host. ## Complete the request 1. The executor removes only clearly irrelevant candidates and returns all remaining candidates with original previews and source IDs/URLs, match reasons, inspection levels, failures, and gaps. Retain uncertainty; no quota. 2. The main Agent reviews those previews and makes the final selection. Find-only requests can return matching links with inspection levels.