refactor(lint): retrofit vale-run to the ADR-0020 context contract

Description 654 -> 294 chars, Gotchas 36% -> 19%. Body 698 -> 642 words:
up from the first pass, because a clean-context audit found four defects
whose fixes are net-additive text.

The suppression-markup warning covered only one of the two paths that
write it -- the list is case-based, so a recurring false positive goes
straight to step 3 and never read step 2's warning. Hoisted above both.

The CI-failure trigger, which the description advertises, had no path to
the file holding its answer: the negative diagnosis 'if the alerts are
warnings, Vale is not what failed the build' survived only in
troubleshooting.md, which no CI-entered invocation loads. An agent would
confidently prescribe --no-exit for a failure Vale never caused.

The description had lost every prose-domain word -- no 'prose', no
'linter' -- while vale-config kept all of them, so 'check prose style'
routed to the wrong skill of the pair.

Accepts two soft SUGGESTIONs rather than dropping restored content;
neither fails the gate.

Refs #99

plugins/lint/skills/vale-run/README.md

@@ -19,5 +19,5 @@ Describe what you want to lint and how (human-readable output, CI/JSON output, f
 | File | Purpose |
 |------|---------|
 | `SKILL.md` | Core invocation, key flags, output format guidance, false-positive triage order |
-| `references/troubleshooting.md` | Inline suppression syntax, rule-specific disabling, spelling ignore lists, pre-commit integration, CI edge cases |
+| `references/troubleshooting.md` | Load when a rule appears not to apply, when writing inline suppression or spelling-ignore syntax, or when wiring Vale into pre-commit: resolved-config diagnostic (`vale ls-config`), format-specific suppression markup, rule-specific disabling, spelling ignore lists, pre-commit integration, CI edge cases |
 | `references/sources.md` | Research provenance |