SkillAgentSearch skills...

RooFlow

RooFlow - Enhanced Memory Bank System with ☢️Footgun Power☢️ Next-gen Memory Bank system with five integrated modes and system-level customization. Uses Roo Code's experimental "Footgun" feature for deep AI assistant customization while maintaining efficient token usage!

Install / Use

/learn @GreatScottyMac/RooFlow
About this skill

Quality Score

0/100

Supported Platforms

Universal

README

<div align="center">

⚠️ Alternate System Prompt Format for Roo Code ⚠️

RooFlow provides an experimental set of modes and system prompts designed as an alternative way to interact with the Roo Code VS Code extension. It uses YAML-based system prompts aiming for improved efficiency and token usage compared to the standard Markdown prompts. RooFlow is NOT officially endorsed or supported by the Roo Code project. Use with caution.

✨Now with optional installation for use with the new Context Portal MCP!!✨

<br>

RooFlow

<img src="https://raw.githubusercontent.com/GreatScottyMac/RooFlow/main/images/rooflow_logo.png" alt="RooFlow Logo" width="300"/>

Persistent Project Context and Streamlined AI-Assisted Development

Roo Code RooFlow

</div>

🎯 Overview

RooFlow offers an experimental alternative approach to AI-assisted development within the Roo Code VS Code extension. It utilizes YAML-based system prompts for its specialized "Flow" modes, potentially offering improved efficiency and reduced token consumption compared to standard modes. RooFlow provides persistent project context through its Memory Bank system (adapted from the concepts in roo-code-memory-bank), ensuring the AI assistant maintains project understanding across sessions.

Key Improvements over Roo Code Memory Bank:

  • Reduced Token Consumption: Optimized prompts and instructions minimize token usage.
  • Five Integrated Modes: Flow-Architect, Flow-Code, Flow-Debug, Flow-Ask, and Flow-Orchestrator modes work together seamlessly.
  • Simplified Setup: Easier installation and configuration.
  • Streamlined Real-time Updates: More efficient and targeted Memory Bank updates.
  • Clearer Instructions: Improved YAML-based rule files for better readability and maintainability.

Key Components

%%{init: {'themeVariables': { 'fontSize': '14px'}}}%%
graph LR
    subgraph Workspace
        U[User]
        MB[(Memory Bank)]
    end

    subgraph VSCode
        RC[Roo Code Extension]
    end

    subgraph RooFlow ["RooFlow (Experimental Alternative)"]
        subgraph FlowModes ["Flow Modes (YAML Prompts)"]
            direction TB
            FO[Flow-Orchestrator]
            subgraph ExecutionModes ["Direct/Delegated Modes"]
               direction LR
               FA[Flow-Architect]
               FC[Flow-Code]
               FD[Flow-Debug]
               FK[Flow-Ask]
            end
             %% Link Orchestrator to the group it delegates to
             FO -- Delegates --> ExecutionModes
        end
    end

    %% Core Flow
    U -- Interacts with --> RC
    RC -- Uses --> RooFlow

    %% User Task Paths
    U -- Complex Task --> FO
    U -- Direct Task --> ExecutionModes


    %% Memory Bank Interactions
    FA <--> MB
    FC <--> MB
    FD <--> MB
    FK --> MB

    %% Styling
    style MB fill:#f9f,stroke:#333,stroke-width:2px,color:#000
    style FO fill:#ccf,stroke:#333,stroke-width:2px,color:#000

Memory Bank Access Legend:

  • <--> (Read/Write): Flow-Architect, Flow-Code, Flow-Debug
  • --> (Read-Only): Flow-Ask
  • 🧠 Memory Bank: Persistent storage for project knowledge (automatically managed).
  • 💻 System Prompts: YAML-based core instructions for each mode (.roo/system-prompt-[mode]).
  • 🔧 VS Code Integration: Seamless development experience within VS Code.
  • Real-time Updates: Automatic Memory Bank updates triggered by significant events.

🚀 Quick Start

Installation

  1. Install Roo Code Extension: Ensure you have the Roo Code extension installed in VS Code.

  2. Prerequisites:

    • Git: The installation script requires git to be installed and accessible in your system's PATH. Download Git from https://git-scm.com/downloads.
    • Python 3: The script now uses Python directly. Ensure Python 3 is installed and accessible as python3 (Linux/macOS) or python (Windows) in your PATH. Download Python from https://www.python.org/downloads/.
    • PyYAML: The Python script requires the PyYAML library. Install it using pip:
      pip install pyyaml
      # or potentially pip3 install pyyaml
      
  3. Open your terminal and navigate (cd) to your project's root directory.

  4. Run the appropriate command for your operating system directly:

    • Windows (Command Prompt or PowerShell):
      1. Download the script

        For Use With File Based Memory Bank:

        curl -O https://raw.githubusercontent.com/GreatScottyMac/RooFlow/main/config/install_rooflow.cmd
        

        For Use With Context Portal MCP:

        curl -O https://raw.githubusercontent.com/GreatScottyMac/RooFlow/main/config/install_rooflow_conport.cmd
        
      2. Execute the downloaded script (⚠️If you have MCP servers connected, see Importing Connected MCP Server Tools prior to installation):

        ./install_rooflow.cmd
        

        or

        ./install_rooflow_conport.cmd
        
    • Linux / macOS (bash/zsh):
      1. Download the script

        For Use With File Based Memory Bank:

        curl -O https://raw.githubusercontent.com/GreatScottyMac/RooFlow/main/config/install_rooflow.sh
        

        For Use With Context Portal MCP:

        curl -O https://raw.githubusercontent.com/GreatScottyMac/RooFlow/main/config/install_rooflow_conport.sh
        
      2. Make the script executable:

        chmod +x install_rooflow.sh
        

        or

        chmod +x install_rooflow_conport.sh
        
      3. Execute the downloaded script (⚠️If you have MCP servers connected, see Importing Connected MCP Server Tools prior to installation):

        ./install_rooflow.sh
        

        or

        ./install_rooflow_conport.sh
        
  5. The command downloads and executes the script, which will check for prerequisites (git, python3/python, pyyaml), clone the repository, copy necessary files (including generate_mcp_yaml.py), clean up the clone, and run the Python script to process templates. Follow any on-screen prompts or error messages.

  6. Note: The installer script (install_rooflow.*) is designed to remain after execution for potential re-runs (e.g., for updates).

  7. Verify Installation: After the script runs successfully:

    • Check that the .roo/ directory, along with the .roomodesfile exist in your project root.
    • Optionally, inspect the .roo/system-prompt-* files to ensure placeholders like WORKSPACE_PLACEHOLDER have been replaced with your actual system paths.
  8. Coexistence with Standard Modes: The RooFlow installation adds the Flow-* modes alongside the standard Roo Code modes (Architect, Code, Debug, Ask). You can switch between Flow modes and standard modes at any time using the Roo Code interface. If you encounter issues with a Flow mode, you can easily switch back to its standard counterpart.

Importing Connected MCP Server Tools (Optional)

If you use MCP (Model Context Protocol) servers with Roo Code, RooFlow can automatically inject the details of your connected servers (their tools, resources, etc.) into the custom Flow mode prompts during installation. This ensures the Flow modes are aware of the same tools as the standard Roo Code modes.

To enable this during initial installation:

  1. Get Full System Prompt: Before running the RooFlow installer, you need the complete system prompt text that Roo Code generates dynamically after it connects to your MCP servers.

    • Navigate to Extensions -> Roo Code -> Prompts (as shown in illustration below). <br/>
    <img src="https://raw.githubusercontent.com/GreatScottyMac/RooFlow/main/images/copy_system_prompt.png" alt="Create Mode View" width="200"/>
    • Select any standard Roo Code mode (e.g., "Architect", "Code", "Ask", "Debug").
    • Click the "Copy system prompt to clipboard" button (as shown in illustration above).
    • This text includes the dynamically discovered information about your currently connected MCP servers.
  2. Save as system_prompt.md: Save this copied text into a new file named exactly system_prompt.md directly in your project's root directory.

  3. Run Installer: Now, run the install_rooflow.sh or install_rooflow.cmd script as described in the main Installation section above.

    • The installer copies the Python script generate_mcp_yaml.py.
    • It then runs this Python script (using python3 or python). The script automatically looks for `system
View on GitHub
GitHub Stars1.1k
CategoryDevelopment
Updated4h ago
Forks123

Languages

Python

Security Score

95/100

Audited on Mar 28, 2026

No findings