Ontoly Software Graph

Use this skill when the user asks Codex to understand a TypeScript repository's architecture, dependency graph, request flow, service ownership, configuration usage, impact radius, package topology, or security-sensitive code paths.

Ontoly is a deterministic Software Graph compiler. It does not answer questions with AI. It builds graph evidence that Codex can query before falling back to source search.

Workflow

1. Check whether .ontoly/SoftwareGraph.json exists.

2. If the graph is missing or stale, ask before installing dependencies or writing generated graph files. Then run:

   pnpm add -D @0xsarwagya/ontoly-cli
   pnpm ontoly build .
   

3. Inspect graph quality before answering:

   pnpm ontoly coverage .
   pnpm ontoly stats .
   

4. Prefer Ontoly graph queries before repository-wide source search:

   pnpm ontoly architecture --json
   pnpm ontoly report dependencies --format markdown
   pnpm ontoly report routes --format markdown
   pnpm ontoly query impact <node-id>
   pnpm ontoly trace <node-id-or-name>
   

5. Start Ontoly MCP when the environment supports MCP-backed tools:

   pnpm ontoly mcp
   

6. Use source files only when the graph is missing, stale, low confidence, or insufficient for the question.

Common Questions

• "Explain this repository."
• "Which service owns authentication?"
• "Trace the login flow."
• "What breaks if I remove this repository/service/function?"
• "Which packages depend on this module?"
• "Where is this environment variable read?"
• "Which routes are protected by auth?"

Evidence Rules

When answering, cite graph evidence:

• graph hash
• node ids
• relationship types
• source spans when available
• diagnostics or confidence warnings
• fallback reason if source files were inspected

Never claim certainty beyond Ontoly evidence. If graph coverage is incomplete, say exactly which part is inferred or unresolved.