chore(release): 0.11.0 -- a message can say it needs no answer, and 0.10.0 gets its changelog

Bumps plugin.json, package.json, the README badge and the three skill
frontmatters, because release-plugin.mjs blocks on a plugin.json that does not
already stand at the target version.

Also closes a gap this release would otherwise have inherited: v0.10.0 shipped
without a CHANGELOG section, and the next-cost fix sat under [Unreleased] even
though it is inside v0.9.0..v0.10.0. Labelling that block 0.11.0 would have
made a second wrong claim, so 0.10.0 now has its own section, written from the
commits in the tag rather than from memory.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016iJoZVmU2guTEZcMghk88z

CHANGELOG.md

@@ -5,7 +5,7 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [Unreleased]
+## [0.11.0] - 2026-07-31
 
 ### Added
 
@@ -67,6 +67,27 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   split Rule 6 exists to hold. Selftest section 20 pins both halves together, as
   it has since 0.5.0.
 
+## [0.10.0] - 2026-07-31
+
+### Added
+
+- **`route.sh` + the `route` skill - the writer for the board's cost field.**
+  `next-cost` had a reader and no writer, so it was retyped by hand every
+  session; measured across the operator's tree, the existing board lines carried
+  eight distinct spellings of a field with one documented form. `route.sh` is a
+  pure calculator: four scored traits of the next task (`path`, `verification`,
+  `reversibility`, `scope`) plus a required rationale, and it prints the rubric
+  row, the `next-cost` value, a pasteable startup command and the one-row-cheaper
+  fallback. Escalation is asymmetric - any single trait escalates, the cheapest
+  row needs all four at the cheap end. The row table is a closed set of six, so a
+  seventh spelling cannot enter circulation, and selftest section 6 runs the
+  round trip (route emits, board parses) inside one repo instead of across two.
+
+  The table is the operator's global model rubric, moved here as the single
+  copy: two copies of one policy drift, and a table in a prose file cannot be
+  tested. Scoring is judgement and stays in the skill; turning scores into a row
+  is a lookup and costs no model calls.
+
 ### Fixed
 
 - **The board line's `next-cost` field had two specs, and one of them was