refactor(kyberforge): move audit guidance out of the per-run rubric load

skill-audit loaded roughly 4,268 words of rubric on every run, most of it
criteria for findings a clean skill never triggers. The auditing guidance moves
into finding-criteria.md, read only when a finding is actually raised, cutting
a clean audit to about 999 words. The named-skill exemption is replaced with
properties, so the rubric stops carrying a list that ages the moment a skill
is renamed.

apm-workflow's `type:` trap sat in one flow while biting several, so it is
promoted to a common gate reachable from all of them; its claim to be
self-contained was untrue once it started routing to apm-install. skill-author's
contract had drifted from body-discipline.md and is realigned, and agent-audit's
field inventory is brought in line with the same split.

plugins/kyberforge/skills/forge/SKILL.md

@@ -1,12 +1,11 @@
 ---
 name: forge
 description: >
-  Use when the user wants to build, add, or improve something but has not yet
-  named the artifact type — skill, agent, plugin, or marketplace entry; "a
-  skill for the gitea plugin, or an agent?". Grills the intent, classifies the
-  artifact, then routes to the matching author skill. Do not use when the type
-  is already named — invoke `skill-author`, `agent-author` or `apm-workflow`
-  directly.
+  Use when the user wants to build or improve something but has not yet named
+  the artifact type — skill, agent, plugin, or marketplace entry; "a skill for
+  the gitea plugin, or an agent?". Routes to the matching author skill. Do not
+  use when the type is already named — invoke `skill-author`, `agent-author`
+  or `apm-workflow` directly.
 metadata:
   category: factory
   source_keys:
@@ -18,11 +17,11 @@ metadata:
 ## Gotchas
 
 - forge is an optional guided entry point, not a gate — `skill-author`, `skill-audit`, `agent-author`, `agent-audit` and `apm-workflow` all stay directly invokable, and forge never intercepts a direct call to one.
-- Claude Code's skill-level `context: fork` frontmatter field and the `/fork` subagent command are opposites despite the shared word: `context: fork` isolates (fresh context, no parent access), while `/fork` inherits the full conversation. Every routing branch below turns on that distinction.
+- Claude Code's skill-level `context: fork` frontmatter field and the `/fork` subagent command are opposites despite the shared word: `context: fork` isolates (fresh context, no parent access), while `/fork` inherits the full conversation. The route reference each classification loads spends that distinction: `references/author-routes.md` chooses between the two, `references/apm-routes.md` rules the fork out.
 
 ## Step 1 — Grill the intent
 
-Call `bin:grill-with-docs` unless a grill session has already run and is available in the context.
+Call `grill-with-docs` unless a grill session has already run and is available in the context.
 
 Grilling regularly overturns the artifact type assumed at the start, or splits one idea into several artifacts, so it runs before classification rather than confirming it. Run it inline in the current conversation — grilling is interactive and a subagent cannot hold the back-and-forth.
 
@@ -48,4 +47,4 @@ When the intent spans several rows, chain the routes in dependency order — an
 ## Step 3 — Closing gates, common to every route
 
 - **Resolve before closing.** A route is finished only when its verification reports nothing unresolved. An actionable finding reopens the route; it is never reported onward as a caveat.
-- **Bump the package version.** If the finished route's completion message carries no evidence of a package version bump, read `references/version-bump.md`.
+- **Bump the package version.** A skill route always lands here: `skill-author` moves only a skill's own `metadata.version`, which is not the package `apm.yml`'s number — so read `references/version-bump.md` after one. `agent-author` and the apm routes bump the package themselves at plugin scope; after those, read it only when their output does not say they did.