AI code reviews grounded in 12 classic engineering books — decay risk diagnostics with book citations, severity labels, and 6 analysis modes including full-sweep auto-fix
-
Updated
May 1, 2026 - JavaScript
AI code reviews grounded in 12 classic engineering books — decay risk diagnostics with book citations, severity labels, and 6 analysis modes including full-sweep auto-fix
The Architecture Review Agent is an open-source AI agent sample that reviews software architectures and generates interactive diagrams automatically.
AI-powered architecture documentation framework with ADRs, reviews, and pragmatic mode. Now available as Claude Code Plugin for easiest installation.
A navigator for system and human design — structure-first, question-driven, reasoning-safe
Evidence-based review skill for diff, project, and artifact review across code, readiness, architecture, requirements, and risk.
Collect high-level AWS Well-Architected review data for a workload.
Argus - Multi-agent code quality & architecture review plugin for Claude Code. Runs parallel analysis agents with cross-validation to catch real issues, not false positives.
Security skill collection for Claude Code and Codex — SAST, DAST, binary analysis, architecture review, code clustering, and assessment-as-code workflows
A simplicity-first skill for reviewing architecture, refactors, APIs, and testing strategy without adding unnecessary complexity.
Claude Code plugin for Enterprise Architects and Solution Architects — architecture review, gap analysis, risk radar, trade-off analysis, TOGAF-aware document scaffolding.
CLI tool that accepts architecture briefs and generates structured reviews with risk assessments, questions, and checklists via LLM (with stub mode).
GitHub Profiller
AIDEN — Architecture Intake & Decision Engine
AWS presales and cloud advisory focused on architecture review, early decision support, and cost and security governance.
Organize scattered AI agent rules into a unified skill-based architecture for better control and modularity.
Multi-perspective code review council for Claude Code. 3 advisors by default, 10 agents in deep mode (Opus + Codex). Evidence chains, adversarial self-test, dual-path verdict. Based on Karpathy's LLM Council.
Simplify software decisions by applying a skill that favors local, clear solutions before adding complexity or layers.
Add a description, image, and links to the architecture-review topic page so that developers can more easily learn about it.
To associate your repository with the architecture-review topic, visit your repo's landing page and select "manage topics."