feat(ms-ai-architect): C2.1 onboarding skriver bruker-sti + 11-agent fallback + docs [skip-docs]

- onboard.md (orkestrator): resolver absolutt $ORG_DIR via Bash + mkdir -p, gir
  agenten stien. allowed-tools +Bash. Status/resume globber bruker-sti.
- onboarding-agent.md: skriver de 5 org-filene til den absolutte bruker-stien
  (~/.claude/ms-ai-architect/org/), aldri plugin-rot.
- 11 org-bevisste agenter: uniform Virksomhetskontekst-blokk -> bruker-sti +
  note om ambient injeksjon + subagent-fallback (grep-verifisert 11/11).
  Risiko 1 BEVIST: Task-subagent arver IKKE SessionStart-injeksjon; Read/Glob
  ekspanderer ~ -> fallback lesbar uten Bash.
- README + plan: sti-referanse + C2.1-resultat. CLAUDE.md uendret (ingen sti-ref).

Verifisert: validate PASSED · kb-integrity 192/192 · discovery 13/13.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

README.md

@@ -170,7 +170,7 @@ The plugin delegates specialized work to 12 purpose-built agents. Each agent has
 | `license-mapper-agent` | Cross-reference licenses vs. platform capabilities | ms-ai-advisor | `/architect:license` |
 | `diagram-generation-agent` | Architecture diagrams via Imagen 3 / Mermaid | Prompt templates | `/architect:diagram` |
 | `summary-agent` | Executive summary and decision memo synthesis | All assessment outputs (incl. ROS) | `/architect:summary` |
-| `onboarding-agent` | 5-phase structured org interview | Writes org/*.md | `/architect:onboard` |
+| `onboarding-agent` | 5-phase structured org interview | Writes ~/.claude/ms-ai-architect/org/*.md (user-owned, survives reinstall) | `/architect:onboard` |
 | `ai-act-assessor` | EU AI Act classification, obligations, and compliance assessment | ms-ai-governance (ai-act-*) | `/architect:classify`, `/architect:requirements`, `/architect:transparency`, `/architect:frimpact`, `/architect:conformity` |
 
 ### Orchestration Pattern