Agent Claude Code
Use this agent for system design decisions, architecture reviews, and ADR (Architecture Decision Record) creation. Ensures comprehensive cross-service, security, and performance analysis. Invoke when designing new services, major service modifications, cross-service communication changes, database technology…
Agent Claude Code
Implement backend features using project-specific patterns. Handles commands, queries, entities, event handlers, migrations, and background jobs. Use for backend-only implementation tasks requiring full pattern knowledge.
Agent Claude Code
Use this agent when refining requirements, writing user stories, creating acceptance criteria, analyzing business processes, or bridging technical and non-technical stakeholders.
Agent Claude Code
Use this agent for comprehensive code review after implementing features, before merging PRs, or when assessing code quality and technical debt. Produces report-driven reviews with file-by-file analysis and holistic assessment.
Agent Claude Code
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise. Use after implementing features or fixes to clean up code.
Agent Claude Code
Use this agent when you need to work with database systems, including querying for data analysis, diagnosing performance bottlenecks, optimizing database structures, managing indexes, implementing backup and restore strategies, setting up replication, configuring monitoring, managing user permissions, or when you need…
Agent Claude Code
Use this agent to investigate issues, diagnose errors, analyze system behavior, examine logs and CI/CD pipelines, debug test failures, or identify performance bottlenecks. Produces diagnostic reports with root cause analysis.
Agent Claude Code
Use this agent to manage technical documentation -- detect impacted docs from code changes, update project and business feature docs, maintain doc-code synchronization, and produce documentation summary reports.
Agent Claude Code
E2E testing agent for any test framework (Playwright, Selenium, Cypress, etc.). Use for generating E2E tests from recordings or specs, updating visual baselines, or maintaining test-to-spec traceability. Auto-detects project's E2E stack.
Agent Claude Code
Use this agent for any work on the portable .claude AI-harness framework ITSELF — creating, editing, auditing, or refactoring skills, agents, workflows, hooks, project-config, SYNC protocols, framework docs, and the Codex mirrors. Use proactively whenever a request would modify files under .claude/ (or the generated…
Agent Claude Code
Frontend specialist. Use when creating or modifying frontend components, stores, forms, services, or templates. Adapts to the project's detected UI stack (Angular, React, Vue, Svelte, etc.) via project-reference docs — enforces project base classes, state-management conventions, styling methodology, and…
Agent Claude Code
Execute implementation phases from parallel plans. Handles backend and frontend tasks using project-specific patterns. Designed for parallel execution with strict file ownership boundaries. Use when implementing a specific phase from /plan output.
Agent Claude Code
Stage, commit, and push code changes with conventional commits. Use when user says "commit", "push", or finishes a feature/fix.
Agent Claude Code
Generate and manage integration tests for microservices. Long-running agent that creates test specs, generates integration test files, and verifies traceability. Use for integration test generation, test spec-to-code conversion, or test review.
Agent Claude Code
Use this agent when significant technical difficulties occur: test suites fail repeatedly despite fix attempts, critical bugs found in production, implementation approaches prove flawed requiring redesign, external dependencies cause blocking issues, performance bottlenecks significantly impact UX, security…
Agent Claude Code
General-purpose agent for web research, knowledge synthesis, and structured report generation. Use for research tasks, course material creation, marketing analysis, and business evaluation.
Agent Claude Code
Performance analysis and optimization agent. Use when investigating slow queries, N+1 patterns, bundle size issues, lazy loading opportunities, memory leaks, or API latency bottlenecks. Covers backend (database queries, API latency, memory) and frontend (bundle size, render perf, subscription leaks) — adapts to the…
Agent Claude Code
Use this agent to research, analyze, and create comprehensive implementation plans for new features, system architectures, or complex technical solutions. Invoke before starting significant implementation work or when evaluating technical trade-offs.
Agent Claude Code
Use this agent when working with product ideas, backlog management, prioritization decisions, sprint planning, or stakeholder communication. Specializes in value-driven decision making and requirement clarification.
Agent Claude Code
Use this agent when you need comprehensive project oversight and coordination, including tracking progress against implementation plans, consolidating reports from multiple agents, analyzing task completeness, and providing detailed status summaries of achievements and next steps.
Agent Claude Code
Use this agent when running quality gates, verifying compliance with standards, creating audit trails, tracking quality metrics, or generating review checklists.
Agent Claude Code
Use this agent when you need to conduct comprehensive research on software development topics, including investigating new technologies, finding documentation, exploring best practices, or gathering information about plugins, packages, and open source projects. Excels at synthesizing information from multiple sources…
Agent Claude Code
Use this agent when you need to quickly locate relevant files across a large codebase using external agentic tools (Gemini, OpenCode, etc.). Useful when beginning work on features spanning multiple directories, searching for files, debugging sessions requiring file relationship understanding, or before making changes…
Agent Claude Code
Use this agent when you need to quickly locate relevant files across a large codebase to complete a specific task. Useful when beginning work on features spanning multiple directories, searching for files, debugging sessions requiring file relationship understanding, or before making changes that might affect multiple…
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: