refactor(examples)!: remove two example bundles; 0.2.0 in CHANGELOG

Replaces sector-specific example material with generic, fictitious
examples: removes the two full-scale example bundles under examples/ (18
files) and every reference to them in README Contents and CHANGELOG
(neutral wording in the 0.1.0 entry; history untouched). The
falsification-reviewer worked example now uses a building-energy scenario
with the same structure, judgement (undecided) and evidence states. One
word in the author's own commentary in docs/plan/ is made generic; the
quoted source text is unchanged.

Remaining examples: bygg-energi-mikro, nav-golden-hierarchy,
nav-golden-escape.

Cuts [Unreleased] as [0.2.0] - 2026-09-23 with its link reference.
CHANGELOG.md is the only file that carries the repository version. No tag.

scripts/check-excluded-topics.py: red (180 hits / 20 files / 68 paths)
-> green (0 hits / 50 tracked paths, self-test passed), measured after
git add with the local term list in place.

Valgt 0.2.0 fordi fjerningen er brytende for konsumentene, og pre-1.0
semver bærer brudd som minor-bump. Valgt én commit for fjerning og
versjonskutt fordi CHANGELOG-teksten for begge er samme endring.

BREAKING CHANGE: consumers that vendor shared/examples/ lose the two
directories on the next subtree pull.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

README.md

@@ -5,8 +5,8 @@ Framework-neutral shared core of the portfolio-optimiser method: the normative s
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
 
 This repository is the **source of truth** for everything in the portfolio-optimiser method
-that is **independent of any AI agent framework**. It holds no runnable code — only
-normative specifications, example data, and expected outcomes.
+that is **independent of any AI agent framework**. It holds no runnable code of the method — only
+normative specifications, example data, and expected outcomes, plus one repository hygiene check.
 
 Two reference implementations consume it, unchanged, as a `git subtree` at `shared/`:
 
@@ -34,26 +34,10 @@ specifications alone, without reverse-engineering the reference code.
   golden-extraction format.
 - [`CONCEPT.md`](CONCEPT.md) — the business concept, written for a non-specialist (e.g. a
   business developer at another company). Written in Norwegian.
-- [`examples/bygg-energi-mikro/`](examples/bygg-energi-mikro/) — the first example knowledge
+- [`examples/bygg-energi-mikro/`](examples/bygg-energi-mikro/) — the example knowledge
   bundle (OKF / LLM-wiki): one office building, one LED-retrofit measure, with a seed expert
   verdict encoding the realization gap and a golden-suite of expected validator outcomes. A small
-  **dev fixture** for exercising the agentic loop; the two full-scale bundles below
-  ([`veglys-fv-soer`](examples/veglys-fv-soer/), [`tunnel-hauglia`](examples/tunnel-hauglia/))
-  are the realistic ones.
-- [`examples/veglys-fv-soer/`](examples/veglys-fv-soer/) — an example knowledge bundle at realistic
-  scale: a county-road street-lighting portfolio with two candidate measures (LED replacement of
-  2 500 of 9 500 HPS luminaires, and adaptive control), a seed expert verdict, the IR projection
-  the deterministic validator reads, and the project's cost baseline. The realization gap is a
-  parameter error — burn hours overestimated — on a Norwegian evidence base where many
-  installations have no metering at all. Project layer fictional, literature layer real and cited.
-  Written in Norwegian.
-- [`examples/tunnel-hauglia/`](examples/tunnel-hauglia/) — an example knowledge bundle at realistic
-  scale, same file layout as the veglys bundle: a two-tube road tunnel with two candidate measures
-  (3-step to 13-step dimming of the entrance and transition zones, and passive portal screening).
-  Its realization gap arises in operation rather than in the parameters, so the seed verdict carries
-  `gap_source: control-tracking-overestimation` where both bygg-energi-mikro and veglys-fv-soer
-  carry `hours-of-use-overestimation` — a second gap class, so a learning loop exercised here has seen
-  more than one cause. Project layer fictional, literature layer real and cited. Written in Norwegian.
+  **dev fixture** for exercising the agentic loop.
 - [`examples/nav-golden-hierarchy/`](examples/nav-golden-hierarchy/) and
   [`examples/nav-golden-escape/`](examples/nav-golden-escape/) — the **nav-golden** fixture class:
   `bundle/` in, `expected-read-context.md` out, exercising the navigation contract (method-spec §3
@@ -71,6 +55,11 @@ specifications alone, without reverse-engineering the reference code.
 - [`docs/plan/`](docs/plan/) — the decision record: how each ruling in the specifications above was
   arrived at, including the ones that were later reversed. Working documents, not normative, and
   written in a mix of Norwegian and English.
+- [`scripts/check-excluded-topics.py`](scripts/check-excluded-topics.py) — a repository hygiene
+  gate (Python 3, standard library only): fails if any tracked path or text file matches a term
+  list kept outside the tree (in the clone's git directory), after a self-test proves the pattern
+  can find. Without that list it reports SKIPPED and exits 3. Not part of the method; run it from
+  this repository's root with `python3 scripts/check-excluded-topics.py`.
 
 ## Vendoring this repository