A prompt-driven loop that iteratively reviews and refines system architecture based on feedback until formal approval is granted. This loop helps ensure architectural decisions are validated and aligned with project goals through continuous review cycles.
Resolve architecture feedback
Run this loop by executing the kickoff prompt in your coding environment, then iteratively apply feedback using the check command until approval is received.
Start the Loop
Execute the kickoff prompt to begin the architecture review process with your initial setup and context.
Run Check Command
After making changes, run the 'architecture review' check command to validate improvements against feedback.
Inspect Results
Examine the output of the check command to determine if further refinements are needed or if approval has been granted.
Iterate or Exit
Based on the check results, either make additional refinements and repeat the loop or exit if approval is confirmed.
Implement changes based on architecture feedback and current context
Run 'architecture review' command to validate changes against feedback
Review
This loop systematically identifies, analyzes, and resolves unresolved code review comments to improve code quality and ensure all feedback is addressed before merging.
Review
An automated workflow loop that iteratively reviews and improves pull request code quality to achieve merge readiness. This loop focuses on code standards, testing, documentation, and best practices through self-paced agent iterations.
Review
A self-paced loop for coding agents to iteratively review and improve their pull request quality before submission. The agent acts on the codebase, runs automated checks, inspects results, and refines changes until all quality criteria are met.
Analyze check results to identify remaining issues or approval confirmation
Continue loop if issues remain, exit if approval is granted
Start the "Architecture Review Loop" loop. Goal: Resolve architecture feedback Max iterations: 10 Between iterations run: architecture review Exit when: Approval granted I'd like to start an architecture review loop. Please analyze the current system architecture in this codebase and provide a comprehensive review focusing on [SPECIFIC_AREA] based on the following feedback: [FEEDBACK_POINTS]. Begin by documenting the key architectural components and identifying areas that need improvement based on the provided feedback. Self-pace this loop. After each iteration, run `architecture review` and evaluate the output, and only continue if the exit condition is not met (Approval granted). Stop when the exit condition passes or 10 iterations are reached. Give a short status update each pass.
