Which coding agent wins on real work?
-
Updated
May 5, 2026 - TypeScript
Which coding agent wins on real work?
Enterprise-grade workflow plugin for coding agents, with a complete and actionable AI development engineering methodology built in, enabling high-standard, standardized development workflows in mainstream AI coding tools such as Claude Code and Codex.面向企业级编码 Agent 的工作流插件,内置完整、可落地的 AI 开发工程方法论,支持在 Claude Code、Codex 等主流 AI 编码工具中实现高标准、规范化的开发流程。
reverse engineer code to behaviors and generate tests at scale with agents
A human+AI working method as a self-amending constitution + a token/cost observatory with real measured data. Case study, dataset, reusable tools.
A loving tribute to DMA Design's classic 1991 Lemmings. Guide a single lemming through an escalating run: skip and escape, stay alive and climb the leaderboard.
Add a description, image, and links to the spec-driven-developement topic page so that developers can more easily learn about it.
To associate your repository with the spec-driven-developement topic, visit your repo's landing page and select "manage topics."