Arpit

Proactively retrieves focused context packages for Claude to enhance understanding before proceeding.

Enhance Claude Code's capabilities with the Claude Capsule Kit, featuring session memory, dependency analysis, and specialized agents.

Explore and understand codebase architecture with a focus on service boundaries and data flows.

Use this agent when debugging complex issues, analyzing stack traces, or tracing through code execution paths. Specializes in systematic debugging approaches, breakpoint strategies, and isolating root causes.

Refactor code safely and incrementally without changing its behavior.

Expert agent for designing technical architecture and analyzing system performance.

Manage GitHub issues efficiently during development workflows.

Manage git workflows, resolve conflicts, and maintain clean history with expert guidance.

Generate intelligent session summaries for seamless cross-device continuation.

Optimize production systems and incident response with this DevOps/SRE agent.

Conduct root cause analysis of errors and generate structured reports for verification.

Build deep understanding of codebases using multi-layer context gathering.

Analyze developer experience and product features with a focus on API design and usability.

Explore and understand database schemas and data models with a read-only agent.

Optimize context management and memory for long-running sessions.

Coordinate brainstorming sessions with specialist agents to generate actionable recommendations.

Decision matrix for optimizing task approaches in Claude, guiding delegation and direct work.

Systematic task orchestration for complex multi-step tasks. Triggers automatically when detecting: complex task, multi-step work, coordinate, orchestrate, break down. Guides through Understand → Strategy → Plan → Execute → Verify phases for comprehensive systematic approach.

Pre-commit code review using code-reviewer agent for bug detection, security analysis, and quality assurance. Manual invocation only. Use before git commits to catch issues early. Blocks commits on REQUEST_CHANGES verdict.

Systematic debugging using error-detective and debugger agents instead of manual investigation. Triggers automatically on: error, bug, broken, failing, exception, stack trace, test failure. Orchestrates RCA-first approach with parallel agent investigation.

Orchestrate multi-agent teams for parallel work across git branches.

Use this agent when analyzing security implications, designing cryptographic systems, or evaluating compliance requirements. Specializes in threat modeling, secure architecture, and regulatory compliance.

Optimize database design and performance with this specialized agent.

A specialized agent for developing and debugging AI agents and MCP integrations.

Use this agent for code review before commits or PRs. Checks for bugs, security issues, performance problems, and code quality. Provides actionable feedback with specific line references.