docs: retire ADR-0020's stale measurements and fix a CONTEXT.md code span

971e148 de-pinned three stale present-tense figures in gates.md and left ADR-0020's
copy of each, while CONTEXT.md points readers at the ADR for the current number. All
three were wrong at HEAD, re-measured against a `git archive` of the tree rather
than the working copy:

- "26 description FAILs, 9 body FAILs, 2 dangling targets, 58 SUGGESTIONs" is now
  0 / 0 / 0 / 29.
- "pre-commit run --all-files is red on 10 alerts" is 0 errors in 39 files.
- apm-orchestrate was cited as a 900-word body FAIL. It is 876 words, a SUGGESTION.
  git-orchestrate at 933 and gitea-orchestrate at 1,199 were correct.

Marked historical with a dated amendment and the measured current values, following
the convention already in this file. The "realistic landing is somewhere in that
33-58% band" projection is left alone: it is a forecast rather than a measurement,
and the realised 55.3% falls inside it.

The Enforcement table claimed exhaustiveness while listing only ERROR and SUGGESTION
for boundary targets; gates.md documents a third verdict, INFO "DID NOT RUN". Added.

CONTEXT.md carried shell-escaped backticks inside a markdown code span, which closes
the span early and leaves an unterminated double-backtick span that swallows the
rest of the glossary entry — in the definition of a term this branch introduces. It
also called the ADR's pre-retrofit 23,427 the current preload figure; the measured
value is 10,478, recorded here so the glossary and the gate agree.

ADR: 0020

CONTEXT.md

@@ -16,8 +16,12 @@ decisions.
 
 **Preload tax**:
 The always-on context cost of every installed skill's `name` and `description`, charged from the
-first token of every session whether the skill is invoked or not. Measurement method and current
-figure: ADR-0020.
+first token of every session whether the skill is invoked or not. Measurement method: ADR-0020. Its
+**23,427 characters is the pre-retrofit baseline, not a current reading** — measured at the decision
+commit, before #99. Across the same 39 skills it is **10,478 characters** (~2,620 tokens) as of
+2026-09-01. Both figures move with the corpus, so re-derive rather than quote either: sum
+`len(name) + len(description)` over the frontmatter of every `plugins/*/.apm/skills/*/SKILL.md`,
+folding block scalars as `scripts/skill-size-check.sh` does.
 _Avoid_: context cost, token overhead
 
 **Skill context contract**:
@@ -44,7 +48,7 @@ _Avoid_: router body, thin body
 A skill reached only by typing its slash command, declared `disable-model-invocation: true`. The host
 withholds it from the model-visible listing entirely, so it pays no preload tax and its description
 becomes human-facing text. The flag also hard-blocks the Skill tool, so **no other skill can route to
-a hand-invoked skill** — a `Call \`x\`` step in another skill's body stops working the moment `x`
+a hand-invoked skill** — a `` Call `x` `` step in another skill's body stops working the moment `x`
 takes the flag. Check inbound routes before declaring one. Exemplar: `zoom-out`.
 _Avoid_: manual skill, disabled skill