docs: close the self-contradictions left by the branch's own cuts

CONTEXT.md used two terms it no longer defines. This branch deleted the
Preload tax and Skill context contract entries as audit finding 31, but
the Hand-invoked skill definition and the example dialogue still used
both, bolded, which is this file's convention for a defined term. The
definitional file contradicted itself while AGENTS.md tells every
session to read it as authoritative. Rephrased in place, the way
e2e957e handled the one the audit's own note records.

ADR-0024 said 10 .bats files deploy across 6 skills; ADR-0025 merged
two of those directories the next day, on this branch, leaving 5. It
was also the only ADR ADR-0025 invalidated without an amendment banner,
as was ADR-0016, which still named agent-audit in the present tense as
the live enforcer. Both get the banner the other nine carry, and the
figure and names are corrected in place as well, since these sit in
text asserting present fact rather than a superseded decision.

ADR-0019's correction block from 1614bce was inserted mid-paragraph and
swallowed the original's trailing sentence, leaving the quote malformed
and the next line starting lowercase mid-sentence. gates.md took the
same correction and is not affected.

In the audit note: two of §12's five open follow-ups were already
closed (e4ed343 repointed the a8cd5e8 citations at 598a7c3; #101 closed
2026-09-16, so Closes #101 is a no-op), the same stale hash sat at :330
with a wrong line number, the vale-wrap counts had drifted from 63/19
to 65/14 and are now pinned to a commit per §1's own convention, and
the deleted-suite tally said eight where the diff shows nine.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NwD8Egs5r4ndqeFLmhusX2

CONTEXT.md

@@ -30,10 +30,10 @@ _Avoid_: router body, thin body
 
 **Hand-invoked skill**:
 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`
-takes the flag. Check inbound routes before declaring one. Exemplar: `zoom-out`.
+withholds it from the model-visible listing entirely, so it costs nothing in always-on context 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` takes the flag. Check inbound routes before declaring one. Exemplar: `zoom-out`.
 _Avoid_: manual skill, disabled skill
 
 **Delegation discipline**:
@@ -155,9 +155,9 @@ _Avoid_: namespace, category
 > **Dev:** "This one only fires when someone types the slash command. Does its description still need
 > trigger words?"
 > **Maintainer:** "No — that's a **hand-invoked skill**. The host withholds it from the model-visible
-> listing, so it pays no **preload tax** at all and the description is human-facing text."
+> listing, so it costs nothing in always-on context and the description is human-facing text."
 > **Dev:** "Then the body can be as long as it needs to be?"
-> **Maintainer:** "Different budget. The **skill context contract** gates the body whether or not the
+> **Maintainer:** "Different budget. ADR-0020's authoring rules gate the body whether or not the
 > skill is model-invoked — the description competes with every other skill's description, the body
 > competes with the caller's live conversation. Four mutually exclusive flows means a **dispatch
 > body**: table in `SKILL.md`, one `references/` file per flow."