An enterprise-grade AI R&D SOP for Claude Code, built for Java developers. An out-of-the-box full-lifecycle workflow covering system design, coding, code review, automated testing, and deployment to help you deliver industrial-grade code without rework.
This repository also configures its own agents. See what fish-claude-code tells them →
Agent Claude Code
A Java software architect and technical partner for making design decisions before implementation. It handles system design, performance plans, technology choices, architecture reviews, and database modelling, but does not write implementation code.
Agent Claude Code
A code-review agent that examines code before it is committed, during refactoring, or for security problems. It reports review comments and a score but does not write code.
Agent Claude Code
PostgreSQL database specialist for query optimization, schema design, security, and performance. Use PROACTIVELY when writing SQL, creating migrations, designing schemas, or troubleshooting database performance. Incorporates Supabase best practices.
Agent Claude Code
A cloud-native operations specialist for Docker, Kubernetes, Docker Compose, and CI/CD systems. Cloud-native means running applications in containers and managing them with modern deployment tools.
Agent Claude Code
A Java software-development agent that implements code from design documents, writes unit tests, and fixes bugs. It focuses on Spring Cloud Alibaba, defensive programming, and concurrent code.
Agent Claude Code
Expert planning specialist for complex features and refactoring. Use PROACTIVELY when users request feature implementation, architectural changes, or complex refactoring. Automatically activated for planning tasks.
Agent Claude Code
An automated testing agent for writing unit and integration tests. It uses the red-green-refactor process, meaning tests are written to fail, made to pass with code, and then cleaned up.
Agent Claude Code
Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.
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: