market-scanlisted

# Market scan ## Orient through the interface - Work from the repository root; the root constitution holds the bootstrap and capability-catalog commands. Before invoking a capability for the first time, read only its `describe` output or that leaf command's `--help`. - Compose calls around unresolved evidence. Do not execute every capability, preload all help, or force a fixed screening rail. ## Establish the environment - Start with the market snapshot appropriate to the user's as-of request. Treat each source and breadth section independently; a composite response can be usable while one section is unavailable. - Actual trade traction is a separate bottom-up gate. Without the user's own recent pilot, breakout, or stop-out feedback, preserve `needs_input` rather than promoting QQQ or breadth alone to a favorable regime. - QQQ versus 21 EMA is environmental context only. Leaders and real trade behavior decide whether apparent strength has earned confidence. - Read persistent overbought action with shallow pullbacks as possible lockout demand, not an automatic sell signal. Also surface leader/index divergence and the evidence that would refute the regime read. - If the environment is hostile or evidence is materially incomplete, reduce the discovery depth and return watch-only conditions. Sparse qualified leadership is itself evidence; never loosen hard gates to fill a list. ## Find leaders without manufacturing a score - Use provider-ranked sectors, industries, and lead