feat(ai-context): replace skill router with inline imperative instructions

CLAUDE.md and AGENTS.md now contain direct enforcement instructions instead
of a passive skill router table. Based on Vercel eval data showing skills
are skipped 56% of the time, and industry research on effective AGENTS.md
patterns from 2,500+ repos.

Key changes:
- Always/When/Never three-tier boundary structure
- RFC 2119 language (MUST, NEVER) for critical rules
- Exact tool commands with parameters inline
- Self-check checklist forcing model to verify its own work
- ~77 lines, well within the <150 line adherence threshold

Skills are still installed as bonus depth for Claude Code's skill system.

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

gitnexus/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gitnexus",
-  "version": "1.3.7",
+  "version": "1.3.6",
   "description": "Graph-powered code intelligence for AI agents. Index any codebase, query via MCP or CLI.",
   "author": "Abhigyan Patwari",
   "license": "PolyForm-Noncommercial-1.0.0",

gitnexus/src/cli/analyze.ts

@@ -357,8 +357,10 @@ export const analyzeCommand = async (
 
   console.log('');
 
-  // KuzuDB's native module holds open handles that prevent Node from exiting.
-  // ONNX Runtime also registers native atexit hooks that segfault on some
-  // platforms (#38, #40). Force-exit to ensure clean termination.
-  process.exit(0);
+  // ONNX Runtime registers native atexit hooks that segfault during process
+  // shutdown on macOS (#38) and some Linux configs (#40). Force-exit to
+  // bypass them when embeddings were loaded.
+  if (!embeddingSkipped) {
+    process.exit(0);
+  }
 };