Claude Agent Flow

I started this project because if I am honest I was a bit disappointed with the current crop of AI tooling. As amazing as their results often are, when the model says "I am done", it was always far from done. Maybe you asked for a mobile friendly web page and it turned out that the result wasnt in fact mobile friendly. Or maybe you asked it to fix some code and then on running the tests, you saw that it had made introduced another bug. Either way I was spending too much time hand holding and guiding the models.

I am a big Claude Code user and it supports so many great things so I thought why don't I try and build a workflow that would help me formulate my idea, research it for me, sanity check it and then build it for me all without my intervention. Obviously I would need to discuss with the AI what I wanted but once we had a good plan, I wanted my work to be turned into a "ticket" and then have the AI build it for me and not come back to me until it was "Done Done"!

But the big part was once it thought it was done, it would need to get the approval of multiple separate AI agents that would be very thorough and check it's work. "Works on mobile?", then prove it with screenshots! "Code looks good", then lets run all the tests. If anything breaks, send it back to the agent that did the work for correction. Only when the entire flow if complete and every agent is satisfied, is the job "Ready for Review"

Today it's 12 specialised agents, a skill library, and a full CI/CD integration — built entirely by running itself. What began as a simple automation became a full on factory line capable of solving multiple tickets at once. When you couple it with Claude Code for Web you can literally have AI build your ideas whilst you are out and about. It gets rather addictive :-)

When Agent Flow was first built, it was deeply opinionated about technology. The agents assumed React, TypeScript, Tailwind, Node, and Supabase. That made it fast to write but limited to one kind of project.

The pipeline now works with any technology stack — React or Vue or Angular or plain HTML, Python or Go or Rust or .NET. Agents read TECHSTACK.md at your project root to learn what your project actually uses. That file is auto-generated on first pipeline run and hand-editable at any time.

It also doubles as a "desire sheet": declare a technology you intend to use before you've written a line of it, and agents will follow your direction. Manual edits are always authoritative — the explorer never overwrites them without asking.