enable memory-core plugin for OpenClaw [ci skip]

- Add memory-core to plugins.allow and plugins.slots.memory
- Add /app/extensions to plugin load paths
- Update CLAUDE.md memory instructions to reference native tools

.claude/CLAUDE.md

@@ -9,7 +9,7 @@
 - **GitHub API**: `curl` with tokens from tfvars (`gh` CLI blocked by sandbox)
 
 ## Instructions
-- **"remember X"**: Use `memory-tool store "content" --category facts --tags "tag1,tag2"` (via exec) for persistent cross-session memory. Also update this file + `AGENTS.md` (if shared knowledge), commit with `[ci skip]`. To recall: `memory-tool recall "query"`. To list: `memory-tool list`. To delete: `memory-tool delete <id>`. Do NOT use MCP tools like `memory_store` — they don't exist. Use the CLI.
+- **"remember X"**: Use `memory-tool store "content" --category facts --tags "tag1,tag2"` (via exec) for persistent cross-session memory. Also update this file + `AGENTS.md` (if shared knowledge), commit with `[ci skip]`. To recall: `memory-tool recall "query"`. To list: `memory-tool list`. To delete: `memory-tool delete <id>`. The native `memory_search` and `memory_get` tools are also available for searching indexed memory files. For **storing** new memories, always use the `memory-tool` CLI via exec.
 - **Apply with SOPS**: Use `scripts/tg` wrapper instead of raw `terragrunt` — auto-decrypts secrets
 - **New services need CI/CD** (Woodpecker) and **monitoring** (Prometheus/Uptime Kuma)
 - **New service**: Use `setup-project` skill for full workflow

stacks/openclaw/main.tf

@@ -148,10 +148,10 @@ resource "kubernetes_config_map" "openclaw_config" {
         }
       }
       plugins = {
-        allow = []
-        slots = {}
+        allow = ["memory-core"]
+        slots = { memory = "memory-core" }
         load = {
-          paths = ["/home/node/.openclaw/extensions"]
+          paths = ["/home/node/.openclaw/extensions", "/app/extensions"]
         }
       }
       commands = {