aurakit
01Plugin Claude Code
All-in-one Claude Code skill: build, fix, review, deploy with one /aura command. 46 modes, 23 agents, 6-layer security (OWASP+), 10 hooks, 8 languages, 55% token savings.
Plugin Claude Code
All-in-one Claude Code skill: build, fix, review, deploy with one /aura command. 46 modes, 23 agents, 6-layer security (OWASP+), 10 hooks, 8 languages, 55% token savings.
Agent
An automated code annotation step that adds NOTE, WARN, ANCHOR, and TODO comments with an [AUTO] label.
Agent
An agent for designing software architecture, including database structures, API agreements, and boundaries between components. It can record important design choices as architecture decision records.
Agent
A read-only debugging agent that investigates software problems using root-cause analysis and a structured four-phase process.
Agent
An agent for sustained work on one complex technical problem, including large refactors, algorithm changes, migrations, and performance investigations. It uses written goals, checkpoints, and verification during the work.
Agent
DevOps/인프라 전문가. Docker, CI/CD, Kubernetes, Terraform, 배포 설정. Use for DEPLOY mode or infrastructure-related BUILD tasks.
Agent
A coding agent that implements software from a written specification, its acceptance criteria, and a language-specific implementation profile. It reads the relevant requirements and existing code before making changes.
Agent
A read-only agent for exploring a codebase, including its existing patterns, related implementations, dependencies, and callers.
Agent
프론트엔드 전문가. React/Next.js/Vue/Svelte UI 구현 + 접근성 + UX 검증. Spawned for .tsx/.vue/.svelte files in Phase 2 and Phase 3.5.
Agent
A read-only agent that compares a software design with the code that was built.
Agent
A read-only software performance reviewer that looks for bottlenecks in areas such as database queries and frontend bundle size.
Agent
A read-only planning agent for breaking complex software tasks into files, responsibilities, and implementation steps. It assesses task size and assigns suitable worker profiles.
Agent
A product-management agent for finding customer needs and organizing them in an Opportunity Solution Tree. This is a map linking a desired outcome to customer problems and possible solutions.
Agent
A product-requirements document writer for PM work. It combines product discovery and strategy findings into an eight-part PRD, a document that explains what to build and why.
Agent
A product-strategy analyst that uses Jobs-to-be-Done and Lean Canvas frameworks. These frameworks describe what customers are trying to accomplish and how a product could create value as a business.
Agent
An automated code-review role based on five checks: tested, readable, consistent, secure, and trackable. It reviews implementation quality, edge cases, security risks, and whether decisions are recorded.
Agent
A read-only project scanner that identifies a codebase's language, package manager, framework, TypeScript settings, dependencies, and design tokens. Design tokens are shared values such as colors, spacing, and font sizes.
Agent
A security-audit agent that scans code for issues covered by OWASP Top 10 and checks SEC-01 through SEC-15 security rules. OWASP Top 10 is a commonly used list of major web-application security risks.
Agent
A read-only security-audit agent based on the OWASP Top 10, a widely used list of common web-application security risks. It reports possible vulnerabilities without changing files.
Agent
A requirements-writing agent that turns a plain-language request into a structured specification with requirements and acceptance criteria. Acceptance criteria describe what must be true for a feature to count as working.
Agent
A testing agent that creates tests before the code they describe exists. It follows acceptance scenarios—statements of what the software should do—and checks observable results, not only whether code avoids errors.
Agent
An automated reviewer for frontend user experience and accessibility. It checks WCAG 2.1 AA concerns, loading and error states, and responsive behavior after frontend files change.
Agent
An agent that checks whether a software change is ready to pass a verification gate. It runs checks for building, tests, linting, coverage, file structure, incomplete code, approvals, and migrations.
Agent
A verification agent for code review, testing, and security scanning. It checks changed code for quality, input handling, type safety, accessibility, common vulnerabilities, and exposed secrets.