feat: add data-platform plugin (v4.0.0)

Add new data-platform plugin for data engineering workflows with:

MCP Server (32 tools):
- pandas operations (14 tools): read_csv, read_parquet, read_json,
  to_csv, to_parquet, describe, head, tail, filter, select, groupby,
  join, list_data, drop_data
- PostgreSQL/PostGIS (10 tools): pg_connect, pg_query, pg_execute,
  pg_tables, pg_columns, pg_schemas, st_tables, st_geometry_type,
  st_srid, st_extent
- dbt integration (8 tools): dbt_parse, dbt_run, dbt_test, dbt_build,
  dbt_compile, dbt_ls, dbt_docs_generate, dbt_lineage

Plugin Features:
- Arrow IPC data_ref system for DataFrame persistence across tool calls
- Pre-execution validation for dbt with `dbt parse`
- SessionStart hook for PostgreSQL connectivity check (non-blocking)
- Hybrid configuration (system ~/.config/claude/postgres.env + project .env)
- Memory management with 100k row limit and chunking support

Commands: /initial-setup, /ingest, /profile, /schema, /explain, /lineage, /run
Agents: data-ingestion, data-analysis

Test suite: 71 tests covering config, data store, pandas, postgres, dbt tools

Addresses data workflow issues from personal-portfolio project:
- Lost data after multiple interactions (solved by Arrow IPC data_ref)
- dbt 1.9+ syntax deprecation (solved by pre-execution validation)
- Ungraceful PostgreSQL error handling (solved by SessionStart hook)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

plugins/data-platform/hooks/hooks.json

@@ -0,0 +1,10 @@
+{
+  "hooks": {
+    "SessionStart": [
+      {
+        "type": "command",
+        "command": "${CLAUDE_PLUGIN_ROOT}/hooks/startup-check.sh"
+      }
+    ]
+  }
+}

plugins/data-platform/hooks/startup-check.sh

@@ -0,0 +1,54 @@
+#!/bin/bash
+# data-platform startup check hook
+# Checks for common issues at session start
+# All output MUST have [data-platform] prefix
+
+PREFIX="[data-platform]"
+
+# Check if MCP venv exists
+PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-$(dirname "$(dirname "$(realpath "$0")")")}"
+VENV_PATH="$PLUGIN_ROOT/mcp-servers/data-platform/.venv/bin/python"
+
+if [[ ! -f "$VENV_PATH" ]]; then
+    echo "$PREFIX MCP venv missing - run /initial-setup or setup.sh"
+    exit 0
+fi
+
+# Check PostgreSQL configuration (optional - just warn if configured but failing)
+POSTGRES_CONFIG="$HOME/.config/claude/postgres.env"
+if [[ -f "$POSTGRES_CONFIG" ]]; then
+    source "$POSTGRES_CONFIG"
+    if [[ -n "${POSTGRES_URL:-}" ]]; then
+        # Quick connection test (5 second timeout)
+        RESULT=$("$VENV_PATH" -c "
+import asyncio
+import sys
+async def test():
+    try:
+        import asyncpg
+        conn = await asyncpg.connect('$POSTGRES_URL', timeout=5)
+        await conn.close()
+        return 'OK'
+    except Exception as e:
+        return f'FAIL: {e}'
+print(asyncio.run(test()))
+" 2>/dev/null || echo "FAIL: asyncpg not installed")
+
+        if [[ "$RESULT" == "OK" ]]; then
+            # PostgreSQL OK - say nothing
+            :
+        elif [[ "$RESULT" == *"FAIL"* ]]; then
+            echo "$PREFIX PostgreSQL connection failed - check POSTGRES_URL"
+        fi
+    fi
+fi
+
+# Check dbt project (if in a project with dbt_project.yml)
+if [[ -f "dbt_project.yml" ]] || [[ -f "transform/dbt_project.yml" ]]; then
+    if ! command -v dbt &> /dev/null; then
+        echo "$PREFIX dbt CLI not found - dbt tools unavailable"
+    fi
+fi
+
+# All checks passed - say nothing
+exit 0