uvx --from git+https://github.com/dauquangthanh/hanoi-rainbow.git rainbow init <PROJECT_NAME>

uvx --native-tls --from git+https://github.com/dauquangthanh/hanoi-rainbow.git rainbow init <PROJECT_NAME>

Why install?

• ✅ Available everywhere in your terminal
• ✅ Easy to upgrade with uv tool upgrade
• ✅ Cleaner than shell aliases
• ✅ Better tool management

Project Setup

You can use the Rainbow CLI to bootstrap your project, which will bring in the required artifacts in your environment. Run:

rainbow init <project_name>

Or initialize in the current directory:

rainbow init .
# or use the --here flag
rainbow init --here
# Skip confirmation when the directory already has files
rainbow init . --force
# or
rainbow init --here --force

rainbow init <project_name> --ai claude
rainbow init <project_name> --ai gemini
rainbow init <project_name> --ai copilot

# Or in current directory:
rainbow init . --ai claude
rainbow init . --ai codex

# or use --here flag
rainbow init --here --ai claude
rainbow init --here --ai codex

# Force merge into a non-empty current directory
rainbow init . --force --ai claude

# or
rainbow init --here --force --ai claude

The CLI will check if you have Claude Code, Gemini CLI, Cursor CLI, Qwen CLI, opencode, Codex CLI, or Amazon Q Developer CLI installed. If you do not, or you prefer to get the templates without checking for the right tools, use --ignore-agent-tools with your command:

rainbow init <project_name> --ai claude --ignore-agent-tools

🌱 Greenfield Workflow (New Projects)

For new projects starting from scratch, follow these steps:

STEP 1: Establish project principles

Go to the project folder and run your AI agent. In our example, we're using claude.

You will know that things are configured correctly if you see the /rainbow.regulate, /rainbow.specify, /rainbow.design, /rainbow.taskify, and /rainbow.implement commands available.

The first step should be establishing your project's governing principles using the /rainbow.regulate command. This helps ensure consistent decision-making throughout all subsequent development phases:

/rainbow.regulate Create principles focused on code quality, testing standards, user experience consistency, and performance requirements. Include governance for how these principles should guide technical decisions and implementation choices.

This step creates or updates the memory/ground-rules.md file with your project's foundational guidelines that the AI agent will reference during specification, planning, and implementation phases.

STEP 2: Create project specifications

With your project principles established, you can now create the functional specifications. Use the /rainbow.specify command and then provide the concrete requirements for the project you want to develop.

[!IMPORTANT]
Be as explicit as possible about what you are trying to build and why. Do not focus on the tech stack at this point.

An example prompt:

Develop Taskify, a team productivity platform. It should allow users to create projects, add team members,
assign tasks, comment and move tasks between boards in Kanban style. In this initial phase for this feature,
let's call it "Create Taskify," let's have multiple users but the users will be declared ahead of time, predefined.
I want five users in two different categories, one product manager and four engineers. Let's create three
different sample projects. Let's have the standard Kanban columns for the status of each task, such as "To Do,"
"In Progress," "In Review," and "Done." There will be no login for this application as this is just the very
first testing thing to ensure that our basic features are set up. For each task in the UI for a task card,
you should be able to change the current status of the task between the different columns in the Kanban work board.
You should be able to leave an unlimited number of comments for a particular card. You should be able to, from that task
card, assign one of the valid users. When you first launch Taskify, it's going to give you a list of the five users to pick
from. There will be no password required. When you click on a user, you go into the main view, which displays the list of
projects. When you click on a project, you open the Kanban board for that project. You're going to see the columns.
You'll be able to drag and drop cards back and forth between different columns. You will see any cards that are
assigned to you, the currently logged in user, in a different color from all the other ones, so you can quickly
see yours. You can edit any comments that you make, but you can't edit comments that other people made. You can
delete any comments that you made, but you can't delete comments anybody else made.

After this prompt is entered, you should see Claude Code kick off the planning and spec drafting process. Claude Code will also trigger some of the built-in scripts to set up the repository.

Once this step is completed, you should have a new branch created (e.g., 001-create-taskify), as well as a new specification in the specs/001-create-taskify directory.

The produced specification should contain a set of user stories and functional requirements, as defined in the template.

At this stage, your project folder contents should resemble the following:

└── .rainbow
    ├── memory
    │  └── ground-rules.md
    ├── scripts
    │  ├── check-prerequisites.sh
    │  ├── common.sh
    │  ├── create-new-feature.sh
    │  ├── setup-plan.sh
    │  └── update-claude-md.sh
    ├── specs
    │  └── 001-create-taskify
    │      └── spec.md
    └── templates
        ├── plan-template.md
        ├── spec-template.md
        └── tasks-template.md

STEP 3: Functional specification clarification (required before planning)

With the baseline specification created, you can go ahead and clarify any of the requirements that were not captured properly within the first shot attempt.

You should run the structured clarification workflow before creating a technical plan to reduce rework downstream.

Preferred order:

1. Use /rainbow.clarify (structured) – sequential, coverage-based questioning that records answers in a Clarifications section.
2. Optionally follow up with ad-hoc free-form refinement if something still feels vague.

If you intentionally want to skip clarification (e.g., spike or exploratory prototype), explicitly state that so the agent doesn't block on missing clarifications.

Example free-form refinement prompt (after /rainbow.clarify if still needed):

For each sample project or project that you create there should be a variable number of tasks between 5 and 15
tasks for each one randomly distributed into different states of completion. Make sure that there's at least
one task in each stage of completion.

You should also ask Claude Code to validate the Review & Acceptance Checklist, checking off the things that are validated/pass the requirements, and leave the ones that are not unchecked. The following prompt can be used:

Read the review and acceptance checklist, and check off each item in the checklist if the feature spec meets the criteria. Leave it empty if it does not.

It's important to use the interaction with Claude Code as an opportunity to clarify and ask questions around the specification - do not treat its first attempt as final.

STEP 4: Generate a plan

You can now be specific about the tech stack and other technical requirements. You can use the /rainbow.design command that is built into the project template with a prompt like this:

We are going to generate this using .NET Aspire, using Postgres as the database. The frontend should use
Blazor server with drag-and-drop task boards, real-time updates. There should be a REST API created with a projects API,
tasks API, and a notifications API.

The output of this step will include a number of implementation detail documents, with your directory tree resembling this:

.
├── CLAUDE.md
├── memory
│  └── ground-rules.md
├── specs
│  └── 001-create-taskify
│      ├── contracts
│      │  ├── api-spec.json
│      │  └── signalr-spec.md
│      ├── data-model.md
│      ├── plan.md
│      ├── quickstart.md
│      ├── research.md
│      └── spec.md
└── .rainbow/
    ├── memory/
    │   └── ground-rules.md
    ├── scripts/
    └── templates/
        └── templates-for-commands/
            ├── plan-template.md
            ├── spec-template.md
            └── tasks-template.md

Check the research.md document to ensure that the right tech stack is used, based on your instructions. You can ask Claude Code to refine it if any of the components stand out, or even have it check the locally-installed version of the platform/framework you want to use (e.g., .NET).

Additionally, you might want to ask Claude Code to research details about the chosen tech stack if it's something that is rapidly changing (e.g., .NET Aspire, JS frameworks), with a prompt like this:

I want you to go through the implementation plan and implementation details, looking for areas that could
benefit from additional research as .NET Aspire is a rapidly changing library. For those areas that you identify that
require further research, I want you to update the research document with additional details about the specific
versions that we are going to be using in this Taskify application and spawn parallel research tasks to clarify
any details using research from the web.

During this process, you might find that Claude Code gets stuck researching the wrong thing - you can help nudge it in the right direction with a prompt like this:

I think we need to break this down into a series of steps. First, identify a list of tasks
that you would need to do during implementation that you're not sure of or would benefit
from further research. Write down a list of those tasks. And then for each one of these tasks,
I want you to spin up a separate research task so that the net results is we are researching
all of those very specific tasks in parallel. What I saw you doing was it looks like you were
researching .NET Aspire in general and I don't think that's gonna do much for us in this case.
That's way too untargeted research. The research needs to help you solve a specific targeted question.

[!NOTE]
Claude Code might be over-eager and add components that you did not ask for. Ask it to clarify the rationale and the source of the change.

STEP 5: Have Claude Code validate the plan

With the plan in place, you should have Claude Code run through it to make sure that there are no missing pieces. You can use a prompt like this:

Now I want you to go and audit the implementation plan and the implementation detail files.
Read through it with an eye on determining whether or not there is a sequence of tasks that you need
to be doing that are obvious from reading this. Because I don't know if there's enough here. For example,
when I look at the core implementation, it would be useful to reference the appropriate places in the implementation
details where it can find the information as it walks through each step in the core implementation or in the refinement.

This helps refine the implementation plan and helps you avoid potential blind spots that Claude Code missed in its planning cycle. Once the initial refinement pass is complete, ask Claude Code to go through the checklist once more before you can get to the implementation.

You can also ask Claude Code (if you have the GitHub CLI installed) to go ahead and create a pull request from your current branch to main with a detailed description, to make sure that the effort is properly tracked.

[!NOTE]
Before you have the agent implement it, it's also worth prompting Claude Code to cross-check the details to see if there are any over-engineered pieces (remember - it can be over-eager). If over-engineered components or decisions exist, you can ask Claude Code to resolve them. Ensure that Claude Code follows the ground rules as the foundational piece that it must adhere to when establishing the plan.

STEP 6: Generate task breakdown with /rainbow.taskify

With the implementation plan validated, you can now break down the plan into specific, actionable tasks that can be executed in the correct order. Use the /rainbow.taskify command to automatically generate a detailed task breakdown from your implementation plan:

/rainbow.taskify

This step creates a tasks.md file in your feature specification directory that contains:

• Task breakdown organized by user story - Each user story becomes a separate implementation phase with its own set of tasks
• Dependency management - Tasks are ordered to respect dependencies between components (e.g., models before services, services before endpoints)
• Parallel execution markers - Tasks that can run in parallel are marked with [P] to optimize development workflow
• File path specifications - Each task includes the exact file paths where implementation should occur
• Test-driven development structure - If tests are requested, test tasks are included and ordered to be written before implementation
• Checkpoint validation - Each user story phase includes checkpoints to validate independent functionality

The generated tasks.md provides a clear roadmap for the /rainbow.implement command, ensuring systematic implementation that maintains code quality and allows for incremental delivery of user stories.

STEP 7: Implementation

Once ready, use the /rainbow.implement command to execute your implementation plan:

/rainbow.implement

The /rainbow.implement command will:

• Validate that all prerequisites are in place (ground-rules, spec, plan, and tasks)
• Parse the task breakdown from tasks.md
• Execute tasks in the correct order, respecting dependencies and parallel execution markers
• Follow the TDD approach defined in your task plan
• Provide progress updates and handle errors appropriately

[!IMPORTANT]
The AI agent will execute local CLI commands (such as dotnet, npm, etc.) - make sure you have the required tools installed on your machine.

Once the implementation is complete, test the application and resolve any runtime errors that may not be visible in CLI logs (e.g., browser console errors). You can copy and paste such errors back to your AI agent for resolution.

🏗️ Brownfield Workflow (Existing Projects)

For adding new features to existing codebases, follow this streamlined workflow:

STEP 1: Assess existing codebase

Start by analyzing the existing codebase to understand its architecture, patterns, and conventions:

/rainbow.assess-context

This command performs a comprehensive analysis of your codebase and creates docs/context-assessment.md that documents:

• Technology Stack - Languages, frameworks, libraries, and tools in use
• Project Structure - Directory organization and architectural layers
• Architecture Patterns - Design patterns, component relationships, and communication patterns
• Coding Conventions - Naming conventions, file organization, and code quality practices
• Data Layer - ORM/query patterns, schema design, and data access patterns
• API Patterns - Endpoint structure, authentication, and integration patterns
• Testing Strategy - Test organization, coverage, and testing patterns
• Build & Deployment - Build process, environment configuration, and deployment strategy
• Technical Health Score - Overall assessment with strengths and improvement areas
• Feature Integration Readiness - Guidance for adding new features consistently

[!NOTE]
The context assessment serves as the foundation for all subsequent steps. It helps ensure that new features integrate seamlessly with existing patterns and maintain codebase consistency.

STEP 2: Update project principles

With the codebase context understood, update or establish project principles that align with the existing architecture:

/rainbow.regulate Review the context assessment and update project principles to align with the existing codebase patterns. 
Ensure principles cover code quality standards found in the assessment, testing practices currently in use, 
and architectural decisions that should guide new feature development.

This step creates or updates .rainbow/memory/ground-rules.md to reflect:

• Coding standards and conventions discovered in the codebase
• Architectural patterns and design principles in use
• Testing practices and quality standards
• Integration guidelines for maintaining consistency

[!TIP]
The /rainbow.regulate command in brownfield projects should reference the context assessment to ensure principles align with existing practices rather than imposing new ones.

STEP 3: Create feature specification

With both the codebase context and updated principles established, specify the new feature you want to add:

/rainbow.specify Add a user notification system that sends email alerts when tasks are assigned. 
Users can configure notification preferences (immediate, daily digest, or disabled) in their profile settings.

The AI agent will reference the context assessment and updated principles to ensure the specification aligns with existing patterns and architecture.

STEP 4: Clarify requirements

Use the clarification workflow to refine the specification:

/rainbow.clarify

This ensures all edge cases and integration points with the existing system are properly defined.

STEP 5: Design integration plan

Create a technical plan that integrates with the existing architecture:

/rainbow.design Follow the existing email service pattern identified in the context assessment. 
Use the current user preference storage approach. Integrate with the existing task assignment workflow.

The plan will reference existing components, patterns, and conventions from the context assessment.

STEP 6: Generate task breakdown

Break down the implementation into specific tasks:

/rainbow.taskify

Tasks will be organized to integrate with existing code while maintaining consistency with established patterns.

STEP 7: Implement the feature

Execute the implementation plan:

/rainbow.implement

The AI agent will build the feature following existing coding conventions and integration patterns identified in the context assessment and established principles.

STEP 8: Test and validate

Test the new feature in the context of the existing application. Ensure it integrates properly with existing functionality and doesn't break existing workflows.