principle-minimize-reader-load

Count two things: layers of indirection between a question and its answer, and hidden mutable state the reader must track. Collapse one-caller wrappers and pass-through layers, then shrink state scope from globals toward locals and pure functions.

Remove a layer when it costs more reader effort than it saves: wrappers with a single caller, adapters with no second implementation, or pass-through layers that repeat the same methods. A layer should compress complexity, not just rename it.

Skip it when the trigger is not evidenced, when a narrower operational skill covers the same decision, or when citing it would not change any choice. The Skill explicitly HOLDs instead of applying the principle decoratively.

Cyclomatic complexity counts branches; reader load measures the work a human does to trace code. A flat file with 50 globals can be harder to reason about than a layered design, so this Skill tracks indirection depth and state scope instead.

It returns a HOLD when required inputs are missing: no concrete situation object, no evidence the trigger fires, or a conflict with a stated user constraint. A HOLD names the gap rather than inventing inputs to keep moving.