Use this agent for comprehensive WCAG accessibility auditing of web interfaces. Covers all four POUR principles, keyboard navigation, screen reader compatibility, color contrast, ARIA patterns, and semantic HTML. Requires Playwright MCP for live browser testing.
Adversarial code reviewer. Assumes the worst about every change. Identifies failure modes, security gaps, race conditions, and edge cases that optimistic reviewers miss. Read-only — critiques but never fixes.
Detects misapplied, unnecessary, or missing design patterns in code. Proactively identifies over-engineering (pattern soup, speculative generality), under-engineering (God objects, anemic models), and language-idiomatic replacements for ceremonial patterns. Use during code review or when structural concerns are the…
Find similar implementations, usage examples, or existing patterns that can be modeled after. Provides concrete code examples with file locations and context.
Use this agent for comprehensive design review on front-end pull requests or UI changes. Trigger when a PR modifies UI components, styles, or user-facing features; when verifying visual consistency, accessibility, or UX quality; when testing responsive design; or when ensuring new UI meets world-class standards.…
AI slop detection and removal specialist. Scans code comments, documentation, and prose for AI-generated noise and removes or rewrites them to maximize signal-to-noise ratio.
Use this agent to review E2E and integration tests for quality, skeleton compliance, test isolation, and maintainability. Invoke after writing tests or during code review of test files. Focuses on structural correctness and test design, not application logic.
Create distinctive, production-grade frontend interfaces that avoid generic AI aesthetics. Use when building web components, pages, or applications from scratch or from a design direction. Implements with bold aesthetic choices, semantic HTML, accessibility baked in, and Playwright verification.
Use this agent to coordinate multiple subagents for large, multi-faceted tasks. Decomposes work into dependency-aware subtasks, delegates to specialist agents, aggregates results, and handles failures. Invoke when a task spans multiple domains (e.g., code + tests + docs + security), requires parallel workstreams, or…
Use this agent for performance-focused analysis of application code, database queries, and system architecture. Invoke when profiling bottlenecks, optimizing slow queries, reducing bundle size, or detecting memory leaks. Produces a structured performance report with prioritized findings.
Use this agent when you need a thorough code review that balances engineering excellence with development velocity. Invoke after completing a logical chunk of code, implementing a feature, or before merging a pull request. Focuses on substantive issues while also addressing style.
Use this agent for systematic code refactoring — code smell detection, extract method, rename symbol, dead code removal, dependency inversion, and safe transformation patterns. Invoke when improving code structure without changing behavior, paying down tech debt, or preparing code for a new feature.
Use this agent for security-focused code review to identify HIGH-CONFIDENCE vulnerabilities with real exploitation potential. Minimizes false positives with >80% confidence threshold. Based on Anthropic's claude-code-security-review methodology.
Reviews architecture decisions, system designs, and technical proposals against distributed systems best practices. Identifies missing resilience patterns, scalability risks, data consistency hazards, and anti-patterns. Use for RFC reviews, design document audits, ADR evaluation, or architecture Q&A. Complements…
Specialist debugging agent for root cause analysis. Delegate to when a bug requires focused investigation. Follows the four-phase systematic debugging methodology. Will not propose fixes until root cause is confirmed.
Expert UI/UX design critic and advisor who provides research-backed, opinionated feedback on interfaces. Use when you need honest assessment of design decisions, want to avoid generic "AI slop" aesthetics, need evidence-based UX guidance, or want distinctive design direction grounded in actual user behavior research.…
Reviews AWS architecture for cost efficiency, security posture, resilience, and operational excellence. Evaluates service selection, IaC design, networking topology, and cross-cutting concerns. Use when designing new AWS workloads, reviewing existing infrastructure code, or preparing for a Well-Architected Review.
Specialist for AWS infrastructure-as-code using CloudFormation, CDK, and SAM. Use for authoring templates, reviewing IaC for correctness and security, migrating CloudFormation to CDK, and interpreting change sets or cdk diff output. Applies AWS Well-Architected principles and enforces security defaults.
★not rated 2 2mo agoA67 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: