refactor: detect md hard-wraps via mdast AST, not regex

Per review feedback (use a real markdown parser with an AST linked to
source positions), rewrite verify-md-wrap to parse each file with
mdast-util-from-markdown (the CommonMark parser behind remark) + the GFM
extension, then flag any `paragraph` node whose source span covers more
than one line.

Why a parser over the hand-rolled line scanner:
- It is a checker, not a formatter — it reports and never rewrites, so
  zero cosmetic churn (no emphasis-marker or table-delimiter
  normalization, which is why Prettier was rejected for this).
- The AST owns every structural exemption (fenced code of any fence
  length, tables, lists, blockquotes, HTML, headings, reference defs),
  fixing both bugs the regex version had: it now catches wrapped
  list-item / blockquote prose (a `paragraph` inside those nodes) and no
  longer false-positives on a longer ```` fence wrapping an inner ```.

Also unwrap two pre-existing hard-wrapped blockquotes (architecture.md,
adding-a-tool.md) that the stricter AST check correctly surfaced.

docs/cookbook/adding-a-tool.md

@@ -42,9 +42,7 @@ Registration is effect-based: disposing the plugin fiber unregisters the tool (w
 
 Follow tool-bash's background pattern: a `run_in_background` flag returns a task id immediately; companion tools poll incrementally and kill; completion notices arrive via `agent.inject()`. Bound buffers and spill full output to disk so nothing is silently lost.
 
-> TODO: each tool reimplements this background pattern by hand today. At some
-> point we need a generic long-running-tool layer that handles task ids,
-> incremental polling, kill, and completion notices uniformly.
+> TODO: each tool reimplements this background pattern by hand today. At some point we need a generic long-running-tool layer that handles task ids, incremental polling, kill, and completion notices uniformly.
 
 ## Permissions / sandboxing