ag-analisar-contexto

To identify tech debt and architectural risks, analyze code patterns like TODOs, magic numbers, and circular dependencies to generate a prioritized P0-P3 findings report. This process produces an inventory of debt items saved incrementally to guide remediation.

The best way to prioritize code quality issues is generating a P0-P3 prioritized findings report that flags critical debt, single points of failure, and security gaps. This allows teams to systematically escalate and address the most severe architectural risks first.

You track code diagnostics findings incrementally by building a concise findings document at docs/ai-state/findings.md. This captures an inventory of tech debt items and architectural risks as they are discovered throughout the project lifecycle.

Yes, you can escalate critical P0 tech debt to GitHub issues via the ag-registrar-issue integration. This automatically creates tickets for severe architectural risks and code quality issues to ensure rapid remediation by the engineering team.

Yes, codebase analysis applies to projects of varying sizes and languages. It uniformly detects tech debt indicators like magic numbers, coupling, and test coverage gaps across different codebases to produce consistent architectural risk assessments.