refine(pseudo): drop one-screen cap, allow prose in a supporting role

Remove the hard one-screen length limit entirely; replace the
former cap (rule 9) with a single-altitude guidance that leans
on the reference markers to let the user steer the zoom instead
of a fixed length.

Loosen the prose ban: prose is now allowed, but only in a
supporting role — the pseudocode block stays the centre of every
answer and prose explains what the code cannot show on its own.
Iron Law, overview, rule 1, worked example, frontmatter, and
README updated to match.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

README.md

@@ -38,8 +38,9 @@ human-readable pseudocode for explaining code — each answer opens
 with a source-file-and-line anchor, marks notable steps with
 reference markers the user can point back at, sketches the
 layout of the data structures the code touches alongside the
-flow, reduces the irrelevant to stubs, omits low-level
-mechanics, and never runs longer than one screen. It dispatches
+flow, reduces the irrelevant to stubs, and omits low-level
+mechanics. Prose is allowed only in a supporting role — the
+pseudocode block stays the centre of every answer. It dispatches
 no agents.
 
 Vocabulary is configurable. A **cycle** is one round in the