psd-coding-system

System architecture design and technical decision making for complex features

Backend development specialist for APIs, server logic, and system integration

Database specialist for schema design, query optimization, and data migrations

Frontend development specialist for UI components, React patterns, and user experience

LLM integration specialist for AI features, prompt engineering, and multi-provider implementations

Shell scripting semantics, exit codes, JSON parsing, and hook integration specialist

UX heuristic evaluation specialist for interface design, usability assessment, and user experience optimization

Advanced AI agent leveraging Google Gemini 3.1 Pro for deep analysis, multimodal reasoning, and complex problem-solving.

Advanced AI agent for second opinions, complex problem solving, and design validation. Leverages GPT-5.3-Codex via codex for deep analysis.

Analyzes accumulated learnings and agent memory to identify patterns, recurring errors, and improvement opportunities

Technical documentation specialist for API docs, user guides, and architectural documentation

Performance optimization specialist for web vitals, database queries, API latency, and system performance

Testing specialist for comprehensive test coverage, automation, and quality assurance

Two-phase knowledge lookup (local → online) with mandatory deprecation validation before recommending external APIs or frameworks

Validates frameworks and APIs are not deprecated, sunset, or EOL before recommending them. Checks official docs, changelogs, and migration guides.

Git archaeology agent for blame analysis, change velocity, hot file detection, and ownership mapping

Searches knowledge base for relevant past learnings before implementing new features

Codebase onboarding and deep research agent for architecture mapping, tech stack identification, and convention discovery

Gap analysis for feature specs, user flow permutations, and edge case identification

Validates AI-agent architecture parity, prompt consistency, and agent workflow correctness

Reviews code for SOLID compliance, anti-pattern detection, and architectural integrity with structured checklists

Enforces YAGNI, flags unnecessary complexity, premature abstractions, and over-engineering. Every line is a liability.

PII and compliance scanning agent for GDPR, FERPA, and sensitive data handling validation

Validates ID mappings, foreign key integrity, and data transformation logic against production reality

Go/No-Go checklists for risky deployments (migrations, schema changes, critical paths)

Detects code duplication, repeated patterns, and copy-paste violations with systematic threshold-based analysis

Python code reviewer for type hints, async patterns, security, and Pythonic best practices

ORM-agnostic schema drift detection comparing model definitions, migrations, and raw SQL schemas

Expert security analyst for code review, vulnerability analysis, and best practices validation

Security specialist for vulnerability analysis, penetration testing, and security hardening

SQL code reviewer for injection prevention, query performance, schema design, and migration safety

Swift code reviewer for optionals, memory management, concurrency, and iOS/macOS best practices

TypeScript/JavaScript code reviewer for type safety, async patterns, and framework best practices

Dependency analysis before deletions to prevent breaking changes

Multi-file consistency, version tracking, and configuration drift detection specialist

Data validation at extraction boundaries (UTF-8, encoding, database constraints)

Use this agent when you have created a plan (e.g., implementation plan, architecture design, refactoring strategy, feature specification) and need to validate and iteratively improve it before execution. This agent should be invoked: - After drafting any significant technical plan that will guide implementation work - When you need expert validation of architectural decisions or approach - Before committing to a complex refactoring or feature development path - When the plan involves multiple components or has potential edge cases Examples: <example> Context: User asked for a plan to implement caching for the BlitzSERP API. user: "I need to add response caching to reduce redundant Google queries" assistant: "I'll create a comprehensive caching implementation plan for the BlitzSERP API." [Assistant creates detailed plan] assistant: "I've drafted a plan for implementing response caching with RocksDB. Now I'm going to use the plan-validator agent to validate and refine this plan through iterative feedback from Codex." [Uses Agent tool to invoke plan-validator with the plan] </example> <example> Context: User requested a refactoring plan for the parser module. user: "The parser.rs file is getting too large. Can you create a plan to refactor it into smaller modules?" assistant: "I'll analyze the current parser structure and create a refactoring plan." [Assistant analyzes code and creates plan] assistant: "I've created a modular refactoring plan that splits parser.rs into widget-specific modules. Let me validate this plan using the plan-validator agent to ensure we haven't missed any dependencies or edge cases." [Uses Agent tool to invoke plan-validator] </example>

Data pipeline correctness, metrics accuracy, and statistical validation specialist

Validates bug reports with documented reproduction attempts, evidence collection, and systematic root cause verification

Automatic lightweight learning capture — deduplicates against existing learnings and writes to docs/learnings/

Pre-implementation research orchestrator for /work — dispatches knowledge lookup, codebase research, external validation, git history, and parallel specialist agents

Post-implementation validation orchestrator for /work — dispatches language reviewers and deployment verification agents based on changed files

System architecture design and technical decision making for complex features

Collaborative requirements exploration — flesh out ideas before scoping or implementing

Automate the 6-file version bump ritual — increment, patch, changelog, commit, tag, push

Auto-generate a Keep-a-Changelog entry from recent git history

Clean up merged branches, close issues, and extract compound learning insights

Enhance a plan with parallel research agents validating each section against best practices

Auto-evolve the plugin — analyzes learnings, checks releases, compares competition, contributes patterns

Research and create well-structured GitHub issues for feature requests, bug reports, or improvements

Autonomous end-to-end workflow — implement, test, review, fix, and capture learnings in one shot

Transform ideas into comprehensive product specifications and user stories

Address feedback from pull request reviews systematically and efficiently

Scope classification and tiered planning for features, fixes, and improvements — scales from quick tasks to full PRDs

Security audit for code review and vulnerability analysis

Configure which review agents activate for this project during /review-pr

Orchestrate parallel agent teams using Claude Code's experimental Agent Teams feature

Comprehensive testing command for running, writing, and validating tests

Triage FreshService ticket and create GitHub issue

Implement solutions for GitHub issues or quick fixes

Parallel development using git worktrees — work on multiple branches simultaneously

3 hooks across 3 events