Second pass with the avoid-ai-writing detector

The skill's detector scored the README, PARITY.md and the extracted
comment prose. Fixed what it flagged: hollow intensifiers, "in order
to", "additionally", "the whole point", bold sentences in docs, and
bold that had wrapped across comment lines. Comment prose scores a
maximum of 4 out of 100 across the repo.

One sweep rule mangled four comments ("which is the entire point of X"
lost its clause); repaired, and the rule now keeps the clause.

Comments and strings only. 1208 tests pass, counted from the XML.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

scripts/instrumented.sh

@@ -2,8 +2,8 @@
 # Run the on-device suites against a relay you named, on an emulator with no
 # history.
 #
-# **Two ways an instrumented run silently points at PRODUCTION, and this
-# script closes both.**
+# Two ways an instrumented run silently points at PRODUCTION, and this
+# script closes both.
 #
 #   1. The suites DEFAULT to a live host when no relay argument is passed,
 #      `FeatureUseTest` to relay1.flamenet.io, `LiveSignUpFleetTest` to