CCA-F: Claude Certified Architect — Foundations

You are integrating Claude Code into a Continuous Integration/Continuous Deployment (CI/CD) pipeline. The system performs automated code reviews, generates test cases, and gives feedback on pull requests. You need to design prompts that deliver actionable feedback while minimizing false positives.

During initial testing of the automated review pipeline, you find that reviews of large PRs (50+ changed files) sometimes require more than 20 minutes and cost $8-12 per run because of extensive agentic loops – Claude reads files, runs analysis tools, and iterates repeatedly. Your team requires each invocation to abort when it reaches a fixed iteration count and a fixed dollar amount, enforced by Claude Code itself rather than by the surrounding job runner.

Which configuration change directly enforces both per-invocation caps?