Set a Goal. Let the Agent Loop Until It's Done

This loop systematically identifies, analyzes, and resolves unresolved code review comments to improve code quality and ensure all feedback is addressed befo…

Automatically analyzes and reduces false positive alerts in your monitoring system by identifying noisy patterns and adjusting alert configurations. This age…

This loop ensures that modifications to your API specifications maintain backward compatibility with existing consumers. It uses oasdiff to detect breaking c…

Loop until API responses match the OpenAPI or JSON Schema contract — catch drift between docs and implementation.

This loop ensures that the API implementation aligns with the OpenAPI specification by repeatedly validating the contract using swagger-cli until all require…

Automatically synchronizes API documentation with the codebase to ensure no drift occurs between implementation and documented interfaces. This loop detects…

A coding loop focused on optimizing API performance to ensure P95 latency stays under a defined target threshold. This loop iteratively runs load tests, anal…

This loop identifies and remediates insecure API patterns and vulnerabilities in Node.js projects by iteratively running npm audit and applying security fixe…

This loop automates the migration of API endpoints from legacy versions (e.g., v1) to the latest supported version (e.g., v2) within a codebase. It systemati…

An automated loop for generating comprehensive, up-to-date system architecture documentation. This agent analyzes your codebase, identifies key architectural…

A prompt-driven loop that iteratively reviews and refines system architecture based on feedback until formal approval is granted. This loop helps ensure arch…

Test-first loop: write a failing test, implement the minimum code to pass, refactor, and repeat.

This loop identifies repetitive manual tasks in a project and automatically generates automation scripts to replace them. The agent iteratively analyzes work…

The prompt can be another slash command. This is how Boris Cherny works now — he writes loops that prompt Claude, instead of prompting himself.

A 15-minute watchdog over a labeled set of PRs. Popularized as the "PR Babysitter" loop (boris-cherny) in the loops! catalog.

This loop helps your team refine and organize your product backlog by ensuring items are clearly defined, properly prioritized, and ready for development. It…

Automates the verification of database backup restorability by repeatedly testing restore operations until successful or maximum iterations reached.

Automatically keeps your current Git branch synchronized with its upstream counterpart by detecting divergence, fetching updates, and resolving merge conflic…

Automatically detects and removes broken links from documentation files to improve usability and SEO.

Automates the detection and resolution of failing CI/CD workflows by iteratively inspecting the latest GitHub Actions run, analyzing failures, and applying c…

A systematic debugging loop designed to help developers identify, isolate, and create reliable reproductions of software bugs. This loop iterates through tes…

Run the production build, fix compile and bundling errors, and loop until the build succeeds.

Ship features without bloating the client bundle — loop until size checks pass under your budget threshold.