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>

examples/minimal-setup/CLAUDE.md

@@ -0,0 +1 @@
+# My Project

examples/minimal-setup/README.md

@@ -0,0 +1,17 @@
+# Minimal Setup Example
+
+This example demonstrates a bare-minimum Claude Code project — just a single-line CLAUDE.md with no other configuration.
+
+## What to expect
+
+Running `node ../../scanners/posture.mjs .` from this directory will show:
+
+- **Low utilization score** — most features are unused
+- **Low maturity level** — no hooks, no rules, no settings
+- **Multiple feature gap findings** — all tiers flagged
+
+## Why this matters
+
+Even a single CLAUDE.md file is enough for Claude Code to work. But without permissions, hooks, rules, or MCP configuration, you're leaving significant capability on the table.
+
+Compare with the [optimal-setup](../optimal-setup/) example to see what a fully-configured project looks like.