Skip to main content

Build High-Quality Flutter Apps, Faster

You're already using AI to write Flutter code. Now make it write code you trust. A structured workflow from spec to PR — where problems are caught in the spec, not in the PR review.

Join the Waitlist

AI coding tools are fast. But fast at what, exactly?

AI agents are great at working fast, following patterns, and writing lots of code — when you give them the right structure. But they can go off-track when they infer missing requirements, make product decisions, or guess at your conventions. AI is a multiplier — of whatever process you give it. The speed is real. The confidence isn't.

"My AI-generated code is inconsistent across the project."

Different patterns in every file. Provider used three different ways. No one — including the AI — remembers what was decided.

"I spend more time reviewing AI code than writing it myself."

The AI produces something, but you can't trust it without reading every line. That's not faster — it's just different work.

"Tests? The AI wrote them all at once and they all pass. Suspiciously."

Horizontal test slicing is the AI default. Write all tests, then make them pass. The result: tests that prove nothing and break at the first real change.

"I gave it a vague prompt and got exactly what I deserved."

Without a proper spec, the AI fills in the blanks with guesses. And you don't discover the wrong assumptions until the PR review.

"Every session starts from zero."

You solved this exact problem last week. But the context is gone and the AI has no memory of what worked. Without a way to capture and reuse insights, every session reinvents the wheel.

"I can't work on two features at once without everything collapsing."

Branch switching, stashing, environment files — the overhead of parallel development kills your momentum.

Now imagine a different workflow

A spec is ~200 lines. The code it produces is ~3,000+. Catching a wrong assumption in the spec takes seconds. Catching it in the code could take hours. The entire point of this workflow is to make changes early, when they're cheap.

You describe what you want to build. The AI writes a detailed spec — then a second pass tears it apart, finding gaps and wrong assumptions before a single line of code is written.

Then it builds, phase by phase, committing as it goes. TDD discipline is enforced — red, green, refactor — not the "write all tests then all code" default. A review checks the result against Flutter best practices. And when you're done, you can capture the insights so the next session starts smarter.

What if your AI agent actually worked this way?

Introducing the

Agentic Coding Toolkit

Agentic Coding Toolkit (ACT) is a collection of commands, agents, skills, and Flutter knowledge that structures your AI-assisted development workflow. Designed to bring spec-driven development, structured workflows, and deep Flutter expertise to every coding session.

Fully compatible with Claude Code and OpenCode — the two leading AI coding CLIs.

Six commands. One predictable workflow

From spec to PR with guardrails at every step

1

1. Spec

You describe the feature. The AI keeps asking clarifying questions, ensuring all the user flows, edge cases, and error scenarios are covered.

2

2. Refine

Optional but recommended

A second pass roasts the spec — looking for gaps, wrong assumptions, and misalignment with your existing codebase.

3

3. Plan

Turn the spec into a detailed multi-phase plan with actionable checklists, ready for implementation. Research agents gather Flutter patterns, check SDK docs, and inspect your codebase conventions.

4

4. Work

The AI executes the plan phase by phase — making commits as it goes, running tests continuously, and creating a PR when done.

5

5. Review

Optional

Automated code review against Flutter conventions, architectural principles, and your project patterns.

6

6. Compound

Optional but recommended

Capture reusable insights and decision patterns from the session. Next time, the knowledge is already there.

Everything your AI agent needs to write code you trust

Six pillars that transform AI-assisted Flutter development from chaotic to predictable

Spec-Driven Development

AI works from detailed specs, not vague prompts. Each spec includes user flows, edge cases, and error scenarios — then gets adversarially reviewed for gaps before planning begins.

Structured Workflows

A repeatable cycle where each stage produces artifacts that feed the next. Spec to plan to implementation to review to knowledge capture — with guardrails at every step.

TDD Discipline

Vertical-slice TDD enforcing red-green-refactor, one test at a time. The AI writes a failing test, makes it pass, then refactors — the way TDD is supposed to work.

Robot Testing

Encode user journeys as robot-driven widget tests with stable selectors and deterministic test seams. Real user flows, not isolated unit checks.

Flutter Patterns & Principles

10 principles. 15+ patterns. Breaking changes docs. Setup recipes. All baked into every planning and review step — not as an afterthought, but as the foundation.

Git Workflow

Conventional commits, automatic PR creation with smart descriptions, and full git worktree support for isolated parallel feature development.

The complete toolkit at a glance

Everything that ships with the Agentic Coding Toolkit

Command What it does
/act:workflow:spec Create detailed specifications with user flows, edge cases, and error scenarios
/act:workflow:refine-spec Adversarially review specs for gaps, wrong assumptions, and codebase misalignment
/act:workflow:plan Turn specs into phased implementation plans with codebase-aware context and TDD guidance
/act:workflow:work Execute plans phase-by-phase with auto commits, testing, and PR creation
/act:workflow:review 4 review modes: official, lite, full, focused
/act:workflow:compound Capture reusable insights and decision patterns

Built for Flutter developers who use AI agents

You're past tab-autocomplete. You've used Claude Code or OpenCode to build real features — and you've seen what happens when the AI works without guardrails. Architecture drifts. Tests pass for the wrong reasons. Every session starts from scratch.

You don't want to stop using AI. You want it to work your way — following your patterns, writing proper specs, and producing code you'd actually approve in a PR review.

Whether you're working solo or on a team, ACT gives you that structure.

This isn't for vibe coders. It's for engineers who care about what they ship.

Get notified when ACT launches

The toolkit launches soon. I'm using it daily on real projects and polishing the rough edges. Sign up to get notified when it's ready for you.

No spam, ever. Unsubscribe at any time.

About the Author

Hello, I'm Andrea

Andrea Bizzotto

I'm a Flutter GDE and I've been writing code professionally for over 15 years. With my Flutter tutorials and courses, I've helped thousands of developers become better at building Flutter apps over at Code with Andrea.

The Agentic Coding Toolkit is the system I use daily to build Flutter apps with AI assistance — and now it's available to you.

Frequently asked questions

What is the Agentic Coding Toolkit?
A collection of commands, agents, skills, and Flutter knowledge that structures your AI-assisted development workflow. It works with Claude Code and OpenCode CLI to give your AI agent the guardrails and expertise it needs to produce consistent, high-quality Flutter code.
Do I need Claude Code or OpenCode to use this?
Yes. The toolkit is built for Claude Code CLI and OpenCode CLI. You need at least one of these AI coding tools installed. You'll also need to pay for your desired LLM model (either via API key or subscription).
Why OpenCode?
OpenCode is an excellent open-source CLI tool with full support for custom commands, skills, and subagents. Best of all: it works with all the major models — not just Claude. ACT is fully compatible with both Claude Code and OpenCode.
Is this a VS Code extension?
No. It's a CLI-level toolkit that works in your terminal alongside Claude Code or OpenCode. It's editor-agnostic.
Does it work with my existing Flutter project?
Yes. The toolkit installs globally and works with any Flutter or Dart project. It doesn't modify your project structure — it adds development workflows on top.
Can I use ACT for non-Flutter projects?
The workflows work the same way — spec, plan, work, and the same git commands. The agent will simply skip the Flutter-specific guidance, though the Flutter knowledge base is still loaded and will incur some token usage.
What Flutter patterns and packages does it support?
The knowledge base covers 10 principles, 15+ patterns, and breaking changes for Dart and Flutter. Some package-specific knowledge is already included for Riverpod, Drift, and Sentry, and this will be expanded to other packages in the future.
How is this different from free Claude Code plugins?
There are many open-source toolkits of this kind — some are specific to certain web frameworks, others are general-purpose. They can structure workflows but have zero Flutter-specific knowledge. ACT is the only toolkit with deep Flutter/Dart domain expertise — patterns, principles, breaking changes, and setup recipes built into every step.
Can I use this for Dart CLI projects too?
Yes. The toolkit includes /dart-create for Dart CLI projects and the knowledge base applies to both Flutter and Dart development.
How do I install it?
Two commands: clone the repository and run the install script. Takes about a minute.
How do I update it?
Run /act:update from any project. It checks for updates and shows the changelog before applying.
What does the workflow actually produce?
The most important artifact is, of course, working software. But each cycle also generates specs in ai_specs/, implementation plans, code review reports in ai_reviews/, and reusable knowledge in ai_docs/solutions/. These persist in your project and inform future sessions.
Will this slow down my AI agent?
The structured workflow adds steps, but each step prevents rework that would cost more time later. Certain steps (like /plan) allow you to choose a --lite or --full version depending on the level of detail needed.
Does it work with teams?
Yes. The workflow produces artifacts (specs, plans, reviews, solutions) that live in your repo. Team members see the same specs, follow the same patterns, and build on the same captured knowledge.
Is the source code included?
Yes. The toolkit is a set of markdown-based commands, skills, and knowledge files — all fully readable. You're free to take inspiration and build your own skills alongside it. Note: the license does not permit forking or reselling the toolkit itself.
Can I get a refund?
Yes. 30-day money-back guarantee, no questions asked. If it's not the right fit, email contact@codewithandrea.com and I'll refund you within 24 hours.
What happens to my access if I get a refund?
After a refund, you lose access to the private GitHub repository and all future updates. You're welcome to try again later if your needs change.

Stop reviewing AI code line by line

Give your AI agent the guardrails, Flutter expertise, and structured workflow it needs to produce code you trust.

Join the Waitlist