#372 · Primary category: AI Coding Assistants

flow-next

agentic-workflow ai-agent ai-workflow anthropic autonomous-agent claude-code claude-code-plugin cli code-review codex execution factory-droid marketplace openai-codex planning plugin ralph-mode sdlc spec-driven-development workflow

Repeatable agentic engineering. The workflow layer that turns AI coding agents into a disciplined factory: durable specs, fresh-context workers, adversarial cross-model reviews, receipts. Everything in your repo, zero dependencies. Claude Code · Codex · Cursor · Droid.

Project last updated:08/29/26

GitHub Stars

690

Forks

55

Contributors

9

License

MIT

Why we included this project

Once you start letting AI coding agents write real code, you quickly learn that generating the code is the easy part. The hard part is keeping the process disciplined. Flow-Next is a workflow layer that runs on top of Claude Code, Codex, Cursor, and similar agents. It turns rough intent into durable specs, breaks those into context-sized task graphs, runs each task in a fresh-context worker, and routes results through adversarial cross-model review before anything ships. Every claim of 'done' comes with a receipt, so you can audit what actually happened instead of trusting a chat transcript. Everything lives inside your repository with zero external dependencies, and removing it is as simple as deleting a folder. If you're running agents on a real codebase and want repeatable, reviewable engineering rather than one-off sessions, this is worth a close look.

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