feat(DRC-3526): MCP App widget POC — 15 widget tools + config-install helper

.claude/settings.json

@@ -1,5 +1,7 @@
 {
   "enabledPlugins": {
-    "hookify@claude-plugins-official": true
+    "hookify@claude-plugins-official": true,
+    "mcp-apps@claude-plugins-official": true,
+    "mcp-server-dev@claude-plugins-official": true
   }
 }

.gitignore

@@ -16,14 +16,27 @@ build
 .noai
 .DS_Store
 
+# Test / runtime artifacts (dbt run logs, hypothesis example cache).
+# `logs/` (no leading slash) matches dbt log dirs at any depth,
+# e.g. ./logs and integration_tests/dbt/logs.
+logs/
+.hypothesis/
+
 # Dependabot CLI output
 deps-*.yml
 
 recce.yml
 STATUS.md
 
-# Ignore build artifacts from frontend
-recce/data
+# Ignore the embedded frontend build output under recce/data/, EXCEPT
+# recce/data/mcp/*.html which are tracked SOURCE files (hand-authored widget HTML
+# for MCP Apps). Ignore the directory contents, then re-include the mcp/ source
+# subdir via negation. This catches nested build output (e.g.
+# recce/data/lineage/index.html) that a flat per-extension allowlist would miss.
+recce/data/**
+!recce/data/.gitkeep
+!recce/data/mcp/
+!recce/data/mcp/**
 
 # ignore Claude logs and plans at any nesting
 **/docs/plans/**/*.md
@@ -45,3 +58,4 @@ output/*
 
 .env*
 !.env.example
+.gbrain-source

CLAUDE.md

@@ -99,3 +99,40 @@ See `js/CLAUDE.md` for frontend conventions (Storybook imports, CSS color format
 ## Individual Preferences
 
 - @~/.claude/recce.md
+
+## GBrain Search Guidance (configured by /sync-gbrain)
+<!-- gstack-gbrain-search-guidance:start -->
+
+GBrain is set up and synced on this machine. The agent should prefer gbrain
+over Grep when the question is semantic or when you don't know the exact
+identifier yet.
+
+**This worktree is pinned to a worktree-scoped code source** via the
+`.gbrain-source` file in the repo root (kubectl-style context). Any
+`gbrain code-def`, `code-refs`, `code-callers`, `code-callees`, or `query`
+call from anywhere under this worktree routes to that source by default —
+no `--source` flag needed. Conductor sibling worktrees of the same repo
+each have their own pin and their own indexed pages, so semantic results
+match the actual code on disk in this worktree.
+
+Two indexed corpora available via the `gbrain` CLI:
+- This worktree's code (auto-pinned via `.gbrain-source`).
+- `~/.gstack/` curated memory (registered as `gstack-brain-<user>` source via
+  the existing federation pipeline).
+
+Prefer gbrain when:
+- "Where is X handled?" / semantic intent, no exact string yet:
+    `gbrain search "<terms>"` or `gbrain query "<question>"`
+- "Where is symbol Y defined?" / symbol-based code questions:
+    `gbrain code-def <symbol>` or `gbrain code-refs <symbol>`
+- "What calls Y?" / "What does Y depend on?":
+    `gbrain code-callers <symbol>` / `gbrain code-callees <symbol>`
+- "What did we decide last time?" / past plans, retros, learnings:
+    `gbrain search "<terms>" --source gstack-brain-<user>`
+
+Grep is still right for known exact strings, regex, multiline patterns, and
+file globs. Run `/sync-gbrain` after meaningful code changes; for ongoing
+auto-sync across all worktrees, run `gbrain autopilot --install` once per
+machine — gbrain's daemon handles incremental refresh on a schedule.
+
+<!-- gstack-gbrain-search-guidance:end -->