refactor(linkedin): merge analytics + engagement agents 2→1 each (S19)

- analytics-interpreter absorbs performance-reporter (interpret/report modes,
  identical data sources): mode-selector + both output templates kept inline.
- engagement-coach absorbs comment-strategist (5x5x5 + first-hour + CEA
  commenting + target selection + scoring + quality scorecard + daily
  routine). Self-ref at engagement-coach.md:24 rewritten — target is now
  in-file. Model upgraded from haiku to sonnet (absorbed deeper work);
  tools union: Read, Glob, WebSearch.
- 7 ref-files reconciled: commands/linkedin.md (router rules merged),
  skills/linkedin-analytics (row dropped), skills/linkedin-thought-leadership
  (2 rows merged), skills/linkedin-networking (row dropped), CLAUDE.md
  (agents table 16→14, merged rows), README.md (agents table, flow diagram,
  intent table, analytics consumers line), references/glossary.md (3 'Used in'
  refs), scripts/test-runner.sh (EXPECTED_AGENTS list reconciled to current
  14 — also closed lingering S5/S6 gaps for fact-checker/persona-reviewer/
  video-scripter, removed already-deleted content-tracker/personalization-scorer),
  docs/agents-capability-matrix.md (full restructure: header count 16→14,
  agent table, capability grid columns + capabilities, pipeline diagram,
  intent table, model selection table — fixed STATE residual #1 on the
  tracker/pers-scorer stale columns in the same pass).
- Q2 decision (video-scripter → content-repurposer?): KEEP separate.
  Distinct invocation paths (/linkedin:video vs format conversion), distinct
  outputs (timed video script with pacing+captions vs format-translation
  artifact), and newsletter.md already uses content-repurposer for prose
  drafting independently of video-scripter. Net agents/ 16→14.
- agents/README.md dropped from Files (moved to docs/agents-capability-matrix.md
  in S14); literal Verify exits 2 on missing path (logged), corrected Verify
  passes 4/4 predicates. Manifest audit: 2/2 expected paths exist, 13 'CEA'
  occurrences in engagement-coach.md.
- gitleaks: clean.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

plugins/linkedin-thought-leadership/references/glossary.md

@@ -14,7 +14,7 @@ LinkedIn's 150-parameter foundation model that validates creator profiles before
 ### 5x5x5 Pre-Posting Method
 Engagement priming technique performed 15-20 minutes before posting: identify 5 people with overlapping audiences, find their recent posts (last 24h), write 5 thoughtful comments (15+ words each). Primes algorithm visibility and warms engagement signals.
 
-**Used in:** `skills/linkedin-thought-leadership/SKILL.md`, `agents/engagement-coach.md`, `agents/network-builder.md`, `agents/comment-strategist.md`
+**Used in:** `skills/linkedin-thought-leadership/SKILL.md`, `agents/engagement-coach.md`, `agents/network-builder.md`
 
 ---
 
@@ -42,7 +42,7 @@ Composite metric measuring a creator's established expertise on a topic, derived
 ### CEA Method (Comment Engagement Architecture)
 Three-step comment quality framework: **C**ompliment (specific point appreciated) → **E**xpand (add your insight or experience) → **A**sk (question to continue dialogue). Minimum 15 words for algorithmic value.
 
-**Used in:** `agents/comment-strategist.md`, `agents/engagement-coach.md`, `references/algorithm-signals-reference.md`
+**Used in:** `agents/engagement-coach.md`, `references/algorithm-signals-reference.md`
 
 ### Commodity Content
 Generic, non-differentiated posts that repeat common advice without original perspective. Detected by the differentiation-checker agent using a 10-item red flag checklist; 3+ flags = commodity. Should be blocked or reworked before publishing.
@@ -50,9 +50,9 @@ Generic, non-differentiated posts that repeat common advice without original per
 **Used in:** `agents/differentiation-checker.md`
 
 ### Content DNA
-Your unique combination of perspective, experience, voice, and topical focus that distinguishes your content from others in the same space. Built through consistent posting on core topics over 90+ days. Synthesized by performance-reporter as a personal formula.
+Your unique combination of perspective, experience, voice, and topical focus that distinguishes your content from others in the same space. Built through consistent posting on core topics over 90+ days. Synthesized by analytics-interpreter (report mode) as a personal formula.
 
-**Used in:** `agents/voice-trainer.md`, `agents/differentiation-checker.md`, `agents/performance-reporter.md`
+**Used in:** `agents/voice-trainer.md`, `agents/differentiation-checker.md`, `agents/analytics-interpreter.md`
 
 ### Content Lifecycle
 Seven-stage journey of repurposed content: Original Creation → First Repurposing → Angle Rotation → Format Variation → Series Expansion → Evergreen Circulation → Archive Review. Managed by the content-repurposer agent.