feat(ultraplan-local): v1.6.0 — /ultraresearch-local deep research command

Add /ultraresearch-local for structured research combining local codebase
analysis with external knowledge via parallel agent swarms. Produces research
briefs with triangulation, confidence ratings, and source quality assessment.

New command: /ultraresearch-local with modes --quick, --local, --external, --fg.
New agents: research-orchestrator (opus), docs-researcher, community-researcher,
security-researcher, contrarian-researcher, gemini-bridge (all sonnet).
New template: research-brief-template.md.

Integration: --research flag in /ultraplan-local accepts pre-built research
briefs (up to 3), enriches the interview and exploration phases. Planning
orchestrator cross-references brief findings during synthesis.

Design principle: Context Engineering — right information to right agent at
right time. Research briefs are structured artifacts in the pipeline:
ultraresearch → brief → ultraplan --research → plan → ultraexecute.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

NOTICE.md

@@ -0,0 +1,40 @@
+# Attribution Notice
+
+## Microsoft Learn Documentation
+
+This project contains adapted material derived from [Microsoft Learn](https://learn.microsoft.com) documentation, which is licensed under the [Creative Commons Attribution 4.0 International License (CC BY 4.0)](https://creativecommons.org/licenses/by/4.0/).
+
+The original documentation is copyright Microsoft Corporation and contributors.
+
+### What has been adapted
+
+The reference files in the skill-specific `references/` directories have been:
+
+- **Translated** from English to Norwegian
+- **Reorganized** into a domain-specific knowledge structure
+- **Synthesized** across multiple source articles into consolidated reference documents
+- **Augmented** with original analysis, decision guidance, and Norwegian public sector context
+
+### Source verification
+
+The majority of reference files (~98%) include a "Kilder og verifisering" section at the end of each file, listing the specific Microsoft Learn URLs used as sources. These URLs were verified at the time of generation via the [Microsoft Learn MCP server](https://github.com/nicholasgriffintn/microsoft-learn-mcp).
+
+### Code samples
+
+Code samples derived from Microsoft Learn documentation are used under the [MIT License](https://opensource.org/licenses/MIT), consistent with MicrosoftDocs repository licensing.
+
+## Original content
+
+The following content is original work and not derived from Microsoft Learn:
+
+- Plugin architecture (commands, agents, hooks, orchestrator)
+- The "Cosmo Skyberg" architect persona and decision methodology
+- Diagram prompt templates (`architecture/diagram-prompt-templates.md`)
+- Decision trees and synthesis across multiple platform domains
+- Norwegian public sector governance analysis
+
+## Trademarks
+
+Microsoft, Azure, Microsoft 365, Copilot, Copilot Studio, Power Platform, and other product names are trademarks or registered trademarks of Microsoft Corporation. Their use in this project is for identification purposes only and does not imply endorsement by Microsoft.
+
+This project is not endorsed by, affiliated with, or sponsored by Microsoft Corporation.