Back to directory

AI Agent Project — Production-Grade Configuration

A configuration bundle for Claude Code that adds a structured Spec-Plan-Build-Test-Review-Ship workflow, ten role-based subagents, mandatory coding rules, and slash commands for common development tasks.

AI Agent Project — Production-Grade Configuration

This repository is a production-grade configuration for Claude Code AI agents. It defines a development workflow with six phases: Spec, Plan, Build, Test, Review and Ship, each triggered by its own slash command, plus supporting commands for debugging, simplifying code and fixing issues.

It ships ten specialized agents split into development roles (frontend, backend, systems architecture), quality roles (code review, testing, security auditing, QA) and product roles (project management, UI/UX design, copywriting and SEO), along with thirteen mandatory rules covering code quality, architecture and operations, and reference checklists for security, testing, performance and accessibility.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.