You are integrating Claude Code into your Continuous Integration/Continuous Deployment (CI/CD) pipeline. The system runs automated code reviews, generates test cases, and provides feedback on pull requests. You need to design prompts that provide actionable feedback and minimize false positives.

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

Which configuration change directly enforces both of those per-invocation caps?