#401 · Primary category: AI Coding Assistants

vibecode-pro-max-kit

agentic ai-agents ai-coding-assistant ai-development ai-workflow anthropic claude claude-code cli-tools code-quality codex coding-agents cursor developer-tools llm openai prompt-engineering typescript vibe-coding vibecoding

Spec-driven coding harness with self-improving context memory, 15 agents, and 33 skills for autopilot workflows in Claude Code and Codex.

Project last updated:06/21/26

GitHub Stars

1.1K

Forks

231

Contributors

1

License

MIT

Why we included this project

Most AI coding agents lose the plot between sessions, so the harness's real value is keeping a long task on rails. It wraps Claude Code, Codex, Cursor, or any other agent in a seven-phase process that runs from research through spec to execution, and writes progress notes to disk at each step so a memory reset mid-task doesn't lose the thread. The /goal token keeps the agent running until a feature is done, self-healing loops re-check their own fixes up to ten times, and the setup scan builds project context and keeps docs current as you ship. Product owners can write requirements as plain-language user stories before any code exists, while engineers mostly get less context rot and fewer re-derived conclusions on larger codebases.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category