Agent Reference

Super senior Rails developer with impeccable taste and an exceptionally high bar for Rails code quality. Reviews with strict conventions while being pragmatic on new isolated code.

Key Principles

• Existing Code Modifications - Very strict. Added complexity needs strong justification.
• New Code - Pragmatic. If it's isolated and works, it's acceptable.
• Turbo Streams - Simple turbo streams MUST be inline arrays in controllers.
• Testing as Quality - Hard-to-test code = poor structure that needs refactoring.
• Naming (5-Second Rule) - Must understand what a view/component does in 5 seconds from its name.
• Namespacing - Always use class Module::ClassName pattern.
• Duplication > Complexity - Simple duplicated code is better than complex DRY abstractions.

claude agent kieran-rails-reviewer "Review the UserController"

Brutally honest Rails code review from David Heinemeier Hansson's perspective. Focuses on Rails conventions, simplicity, and avoiding over-engineering.

Key Focus Areas

• Identifies deviations from Rails conventions
• Spots JavaScript framework patterns infiltrating Rails
• Tears apart unnecessary abstractions
• Challenges overengineering and microservices mentality

claude agent dhh-rails-reviewer

Reviews Python code with an exceptionally high quality bar. Enforces type hints, Pythonic patterns, and modern Python 3.10+ syntax.

Key Focus Areas

• Type hints for all functions
• Pythonic patterns and idioms
• Modern Python syntax
• Import organization
• Module extraction signals

claude agent kieran-python-reviewer

Reviews TypeScript code with an exceptionally high quality bar. Enforces type safety, modern patterns, and clean architecture.

Key Focus Areas

• No any without justification
• Component/module extraction signals
• Import organization
• Modern TypeScript patterns
• Testability assessment

claude agent kieran-typescript-reviewer

Performs security audits, vulnerability assessments, and OWASP compliance checks. Essential for any code handling authentication, payments, or sensitive data.

Security Checks

• Input validation analysis
• SQL injection risk assessment
• XSS vulnerability detection
• Authentication/authorization audit
• Sensitive data exposure scanning
• OWASP Top 10 compliance
• Hardcoded secrets search

claude agent security-sentinel "Audit the payment flow"

Analyzes code for performance issues, bottlenecks, and scalability concerns. Projects performance at 10x, 100x, and 1000x scale.

Analysis Areas

• Algorithmic complexity (Big O notation)
• N+1 query pattern detection
• Proper index usage verification
• Memory management review
• Caching opportunity identification
• Network usage optimization
• Frontend bundle impact

claude agent performance-oracle

Analyzes code changes from an architectural perspective. Evaluates system structure, SOLID principles, and API contracts.

Analysis Areas

• Overall system structure understanding
• Change context within architecture
• Architectural violation identification
• SOLID principles compliance
• Microservice boundary assessment
• API contract evaluation

claude agent architecture-strategist

Reviews database migrations, data models, and data persistence code. Ensures data safety and privacy compliance.

Review Areas

• Migration safety and reversibility
• Data constraint validation
• Transaction boundary review
• Referential integrity preservation
• Privacy compliance (GDPR, CCPA)
• Data corruption scenario checking

claude agent data-integrity-guardian

Analyzes code for design patterns, anti-patterns, naming conventions, and duplication. Uses tools like jscpd for duplication detection.

Detection Areas

• Design patterns (Factory, Singleton, Observer, etc.)
• Anti-patterns and code smells
• TODO/FIXME comments
• God objects and circular dependencies
• Naming consistency
• Code duplication

claude agent pattern-recognition-specialist

Ensures code is as simple and minimal as possible. Applies YAGNI rigorously and challenges unnecessary abstractions.

Simplification Checks

• Analyze every line for necessity
• Simplify complex logic
• Remove redundancy and duplication
• Challenge abstractions
• Optimize for readability
• Eliminate premature generalization

claude agent code-simplicity-reviewer

Gathers comprehensive documentation and best practices for frameworks, libraries, or dependencies.

Capabilities

• Fetch official framework and library documentation
• Identify version-specific constraints and deprecations
• Search GitHub for real-world usage examples
• Analyze gem/library source code using bundle show
• Synthesize findings with practical examples

claude agent framework-docs-researcher "Research Hotwire Turbo patterns"

Researches and gathers external best practices, documentation, and examples for any technology.

Capabilities

• Leverage multiple sources (Context7 MCP, web search, GitHub)
• Evaluate information quality and recency
• Synthesize into actionable guidance
• Provide code examples and templates
• Research issue templates and community engagement

claude agent best-practices-researcher "Find pagination patterns"

Archaeological analysis of code repositories to understand evolution and patterns.

Analysis Techniques

• Trace file evolution using git log --follow
• Determine code origins using git blame -w -C -C -C
• Identify patterns from commit history
• Map key contributors and expertise areas
• Extract historical patterns of issues and fixes

claude agent git-history-analyzer "Analyze changes to User model"

Conducts thorough research on repository structure, documentation, and patterns.

Analysis Areas

• Architecture and documentation files (ARCHITECTURE.md, README.md, CLAUDE.md)
• GitHub issues for patterns and conventions
• Issue/PR templates and guidelines
• Implementation patterns using ast-grep or rg
• Project-specific conventions

claude agent repo-research-analyst

Verifies whether bug reports are actual bugs through systematic reproduction. Classifies bugs and provides severity assessment.

Classification Types

• Confirmed - Bug reproduced successfully
• Cannot Reproduce - Unable to reproduce
• Not a Bug - Expected behavior
• Environmental - Environment-specific issue
• Data - Data-related issue
• User Error - User misunderstanding

claude agent bug-reproduction-validator

Addresses code review comments by implementing requested changes and reporting resolutions.

Workflow

• Analyze code review comments
• Plan the resolution before implementation
• Implement requested modifications
• Verify resolution doesn't break functionality
• Provide clear resolution reports

claude agent pr-comment-resolver

Runs linting and code quality checks on Ruby and ERB files. Uses Haiku model for efficiency.

Tools Run

• bundle exec standardrb - Ruby file checking/fixing
• bundle exec erblint --lint-all - ERB templates
• bin/brakeman - Security scanning

claude agent lint

Analyzes specifications and plans for user flows and gap identification. Uses Sonnet model for analysis.

Analysis Areas

• Map all possible user flows and permutations
• Identify gaps, ambiguities, and missing specifications
• Consider different user types, roles, permissions
• Analyze error states and edge cases
• Generate critical questions requiring clarification

claude agent spec-flow-analyzer

Reviews and edits text content to conform to Every's specific style guide.

Style Checks

• Title case in headlines, sentence case elsewhere
• Company singular/plural usage
• Remove overused words (actually, very, just)
• Enforce active voice
• Apply formatting rules (Oxford commas, em dashes)

claude agent every-style-editor

Systematic UI/UX design refinement through iterative improvements. Takes screenshots, analyzes, implements changes, and repeats.

Process

• Take focused screenshots of target elements
• Analyze current state and identify 3-5 improvements
• Implement targeted CSS/design changes
• Document changes made
• Repeat for specified iterations (default 10)

claude agent design-iterator

Automatically detects and fixes visual differences between Figma designs and web implementations. Uses Sonnet model.

Workflow

• Extract design specifications from Figma
• Capture implementation screenshots
• Conduct systematic visual comparison
• Make precise code changes to fix discrepancies
• Verify implementation matches design

claude agent figma-design-sync

Verifies UI implementations match Figma design specifications. Uses Opus model for detailed analysis.

Comparison Areas

• Layouts and structure
• Typography (fonts, sizes, weights)
• Colors and themes
• Spacing and alignment
• Different viewport sizes

claude agent design-implementation-reviewer

Creates/updates README files following Ankane-style template for Ruby gems. Optimized for conciseness with every sentence kept to 15 words or less.

Section Order

1. Header (title + description)
2. Installation
3. Quick Start
4. Usage
5. Options
6. Upgrading
7. Contributing
8. License

Style Guidelines

• Imperative voice throughout
• 15 words max per sentence
• Single-purpose code fences
• Up to 4 badges maximum
• No HTML comments

claude agent ankane-readme-writer