by jtgsystems
🚀 Custom modes for Roo Code VS Code extension - Enhanced AI coding assistance configurations
# Add to your Claude Code skills
git clone https://github.com/jtgsystems/Custom-Modes-Roo-CodeGuides for using ai agents skills like Custom-Modes-Roo-Code.
Last scanned: 5/30/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-30T15:49:15.735Z",
"npmAuditRan": true,
"pipAuditRan": true
}Custom-Modes-Roo-Code is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by jtgsystems. 🚀 Custom modes for Roo Code VS Code extension - Enhanced AI coding assistance configurations. It has 177 GitHub stars.
Yes. Custom-Modes-Roo-Code passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/jtgsystems/Custom-Modes-Roo-Code" and add it to your Claude Code skills directory (see the Installation section above).
Custom-Modes-Roo-Code is primarily written in Python. It is open-source under jtgsystems on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh Custom-Modes-Roo-Code against similar tools.
No comments yet. Be the first to share your thoughts!
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.

Professional AI Agent Configuration Library for Roo Code — 2026 Edition
A comprehensive collection of 225 specialized AI agents designed for modern software development, following 2026 security-first principles and best practices. Includes 11 SOTA reasoning personas for advanced cognitive workflows.
# Clone the repository
git clone https://github.com/jtgsystems/Custom-Modes-Roo-Code.git
# Navigate to agent categories
cd Custom-Modes-Roo-Code/agents
# Convert YAML agents to VS Code format
cd vs-code/
python3 convert_modes.py
This repository contains a meticulously curated collection of AI agent configurations for Roo Code, designed to accelerate development workflows across multiple domains. Each agent is optimized for 2026 development standards with emphasis on:
All agents are updated to reference the latest 2026 technology stack:
| Technology | Version |
|---|---|
| React | 19+ |
| Node.js | 22+ |
| Python | 3.13+ |
| TypeScript | 5.7+ |
| Go | 1.24+ |
| Java | 24 |
| Next.js | 16 |
| .NET | 9 |
| Kubernetes | 1.32 |
| Terraform | 1.11 |
Specialized AI/ML development and deployment
Business strategy and product development
Foundation development roles and architectures
Modern infrastructure and deployment
Programming language experts
Regulatory and legal expertise
System coordination and workflow management
Security-first development and quality assurance
Industry-specific expertise
State-of-the-art reasoning and cognitive personas
See SOTA 2026 Personas section below for details.
Advanced cognitive personas implementing cutting-edge reasoning patterns from the Agent Personas SOTA 2026 specification.
| Persona | Level | Description |
|---|---|---|
| 🏛️ Core Reasoning Architect | L1 Root | Immutable reasoning foundation, RSC guard |
| 🔮 Formula Cascade Oracle | L2 | Fractal formula notation master |
| 🔬 Fractal Elaborator | L3-L6 | Infinite zoom specialist |
| Persona | Level | Description |
|---|---|---|
| ⚡ High-Performance Engineer | L2-L3 | Gallie-optimized hardware sympathizer |
| 🚀 SOTA Stack Master | L2 | Next-Gen Web & Language Virtuoso |
| 🎨 UI/UX Vibe Master | L2 | Aesthetic Intelligence + Layout Enforcer |
| Persona | Level | Description |
|---|---|---|
| 🛡️ Anti-Fiction Sentinel | L1 | Truth Enforcer & Neuro-Symbolic Verifier |
| 📡 DevOps Observability Sentinel | L3 | Production Guardian & Incident Commander |
| Persona | Level | Description |
|---|---|---|
| 🧩 Problem Solving Maestro | L2-L3 | Master of All Heuristics |
| 🧠 Cognitive Multi-Thinker | L2 | Parallel Thought Stream + Six Hats |
| 🕸️ Agentic Swarm Conductor | L2-L3 | Hive-Mind Orchestrator |
See agents/sota-personas/README.md for the inter-persona handoff matrix and swarm usage guide.
# Clone the complete repository
git clone https://github.com/jtgsystems/Custom-Modes-Roo-Code.git
cd Custom-Modes-Roo-Code
# Convert YAML agents to VS Code format
cd vs-code/
python3 convert_modes.py
# Copy converted modes to Roo Code settings
cp -r converted_modes/.roo/ ~/.config/Antigravity/User/globalStorage/rooveterinaryinc.roo-cline/settings/.roo/
# Install specific category
cp agents/core-development ~/.roo-code/agents/ -r
# Install SOTA personas only
cp agents/sota-personas ~/.roo-code/agents/ -r
Each agent YAML file can be used directly with Roo Code's custom mode system:
# Example: Loading an agent
slug: python-developer
name: 🐍 Python Developer
roleDefinition: ...
customInstructions: ...
groups: [read, edit, browser, command, mcp]
slug: agent-name # Unique identifier (kebab-case)
name: 🏷️ Agent Display Name # Display name with emoji
category: category-name # Primary category
subcategory: subcategory-name # Subcategory
roleDefinition: >- # Agent's role description
You are a specialist in...
customInstructions: >- # Detailed instructions
## 2026 Standards Compliance
...
groups: # Permission groups
- read
- edit
- browser
- command
- mcp
version: '2026.1' # Schema version
lastUpdated: '2026-05-12' # Last update date
agents/
├── ai-ml/ # AI & Machine Learning
│ ├── computer-vision/
│ ├── data-science/
│ ├── general/
│ ├── llm/
│ ├── mlops/
│ └── nlp/
├── business-product/ # Business & Product
│ ├── business-analysis/
│ ├── marketing/
│ ├── product-analytics/
│ ├── product-management/
│ ├── sales/
│ └── general/
├── core-development/ # Core Development
│ ├── architecture/
│ ├── backend/
│ ├── frontend/
│ ├── fullstack/
│ └── general/
├── infrastructure-devops/ # Infrastructure & DevOps
│ ├── cloud/
│ ├── general/
│ ├── kubernetes/
│ └── networking/
├── language-specialists/ # Language Specialists
│ ├── csharp/
│ ├── golang/
│ ├── java/
│ ├── javascript/
│ ├── python/
│ ├── rust/
│ └── general/
├── legal-compliance/ # Legal & Compliance
│ ├── compliance/
│ ├── corporate/
│ ├── criminal/
│ ├── employment/
│ ├── ip/
│ └── litigation/
├── meta-orchestration/ # Meta-Orchestration
│ └── general/
├── security-quality/ # Security & Quality
│ ├── general/
│ ├── secu