you want to focus on specific parts of your codebase, you can add them for further analysis using:
shell1/add-files path/to/file1.py path/to/file2.js
This command allows you to specify additional files that should be included in the review process. The paths provided are relative or absolute file system locations.
- Interactive Review with Human Guidance:
- After running
/review, some findings might require human input for clarification or validation. - Use the
/walkthroughcommand to interactively go through these findings:
- After running
shell1/walkthrough
This will prompt you to review each finding, allowing you to provide feedback directly within the CLI. Your responses are recorded and used to refine the findings.
- Promote Critical Findings:
- If certain issues need immediate attention or have a higher priority than what the AI initially assessed, use:
shell1/promote path/to/file.py:line_number
This command allows you to highlight specific findings as critical, ensuring they receive more scrutiny and quicker resolution.
- Ensemble Review with Codex CLI:
- For an additional layer of review, integrate Codex CLI for a complementary perspective:
shell1 2[Read the full article at DEV Community](https://dev.to/mgobea/show-hn-adamsreview-better-multi-agent-pr-reviews-for-claude-code-3pb3) 3 4--- 5 6**Want to create content about this topic?** [Use Nemati AI tools](https://nemati.ai) to generate articles, social posts, and more.

![[AINews] The Unreasonable Effectiveness of Closing the Loop](/_next/image?url=https%3A%2F%2Fmedia.nemati.ai%2Fmedia%2Fblog%2Fimages%2Farticles%2F600e22851bc7453b.webp&w=3840&q=75)



