sub-agents

Name: sub-agents
Author: webdevtodayjason

Warning

Claude Code Sub Agent Manager. A simple Manager for adding Claude Code Sub Agents with hooks and custom slash commands.

198stars

35forks

JavaScript

Installation

# Add to your Claude Code skills
git clone https://github.com/webdevtodayjason/sub-agents

Getting Started

Guides for using ai agents skills like sub-agents.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

Security ReportWarning

Last scanned: 5/30/2026

{
  "issues": [
    {
      "type": "npm-audit",
      "message": "ajv: ajv has ReDoS when using `$data` option",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "brace-expansion: brace-expansion: Zero-step sequence causes process hang and memory exhaustion",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "external-editor: Vulnerability found",
      "severity": "low"
    },
    {
      "type": "npm-audit",
      "message": "flatted: flatted vulnerable to unbounded recursion DoS in parse() revive phase",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "inquirer: Vulnerability found",
      "severity": "low"
    },
    {
      "type": "npm-audit",
      "message": "js-yaml: js-yaml has prototype pollution in merge (<<)",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "minimatch: minimatch has a ReDoS via repeated wildcards with non-matching literal in pattern",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "tmp: tmp allows arbitrary temporary file / directory write via symbolic link `dir` parameter",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "yaml: yaml is vulnerable to Stack Overflow via deeply nested YAML collections",
      "severity": "medium"
    }
  ],
  "status": "WARNING",
  "scannedAt": "2026-05-30T15:42:40.852Z",
  "npmAuditRan": true,
  "pipAuditRan": true
}

README.md

Frequently Asked Questions

What is sub-agents?

sub-agents is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by webdevtodayjason. Claude Code Sub Agent Manager. A simple Manager for adding Claude Code Sub Agents with hooks and custom slash commands. It has 198 GitHub stars.

Is sub-agents safe to use?

sub-agents returned warnings in SkillsLLM's automated security scan. It has no critical vulnerabilities, but review the flagged issues in the Security Report section before adding it to your workflow.

How do I install sub-agents?

Clone the repository with "git clone https://github.com/webdevtodayjason/sub-agents" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is sub-agents written in?

sub-agents is primarily written in JavaScript. It is open-source under webdevtodayjason on GitHub, so you can review or fork the full source.

Are there alternatives to sub-agents?

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 sub-agents against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

superpowers

by obra

An agentic skills framework & software development methodology that works.

234,966

omem writing-dna-skill

[!IMPORTANT]

🗄️ This project is archived (June 2026)

@webdevtoday/claude-agents is no longer maintained. When it was built (mid-2025) it filled a real gap: there was no first-class way to install and manage a pack of subagents, slash commands, and hooks in Claude Code. Claude Code now provides all of that natively — so a framework that copies these files into your project is no longer needed.

Use the built-in primitives instead:

Subagents — specialized workers with their own context, auto-delegated by description → https://code.claude.com/docs/en/sub-agents

Skills — reusable workflows/knowledge invoked with /name or auto-loaded (custom slash commands have been merged into skills) → https://code.claude.com/docs/en/skills

Hooks — event-driven automation → https://code.claude.com/docs/en/hooks

Plugins + marketplaces — the modern way to package and share a bundle of agents/skills/hooks/MCP across projects and teams → https://code.claude.com/docs/en/plugins

Memory — CLAUDE.md plus native auto-memory replace the in-process "memory" store this tool simulated → https://code.claude.com/docs/en/memory

The final release (v1.5.5) is left intact for reference. Thanks to everyone who used or contributed to it. The content below is preserved as historical documentation.

Claude Sub-Agents Manager - AI-Powered Development Assistants for Claude Code

🚀 Supercharge Claude Code with Specialized AI Sub-Agents for Code Review, Testing, Debugging & More

Transform your development workflow with intelligent AI assistants that excel at specific programming tasks

Installation • Quick Start • Available Agents • Documentation • Contributing

🎯 What is Claude Sub-Agents Manager?

Claude Sub-Agents Manager is a powerful CLI tool that enhances Claude Code with specialized AI assistants designed for specific development tasks. Each sub-agent is an expert in its domain - from automated code reviews and test fixing to intelligent debugging and documentation generation. Install production-ready agents instantly or create custom agents tailored to your unique workflow needs.

✨ Why Claude Sub-Agents?

🧠 Specialized Intelligence: Each agent is an expert in its domain
⚡ Zero Configuration: Pre-built agents work out of the box
🎨 Fully Customizable: Create agents that match your workflow
🔄 Smart Context Management: Agents operate in isolated contexts
🛠️ Developer First: Built by developers, for developers
🔗 Context-Forge Integration: Seamlessly works with context-forge projects and PRPs

🎉 New in v1.5.1 - Enhanced Voice Integration & Hook Improvements

🔊 Voice Announcements: Real-time audio feedback when agents complete tasks
🎙️ ElevenLabs Integration: High-quality voice synthesis with Sarah voice
🪝 Improved Hook System: Better settings.json merging during updates
🔧 Voice Setup Wizard: Interactive configuration with claude-agents voice --setup
📢 Auto-Announcements: Hear when sub-agents complete tasks in Claude Code
🎯 FFmpeg Detection: Automatic detection and installation guidance

📦 New in v1.5.0 - Voice Features, Chaining & Meta-Agent

🔗 Agent Chaining: Run multiple agents in powerful sequences with data handoffs
🤖 Meta-Agent: Automatically generate new specialized agents from descriptions
🎙️ Multiple TTS Providers: ElevenLabs (via MCP), OpenAI, and local system TTS
⚙️ Voice Configuration: Easy setup with claude-agents voice command
🎯 Enhanced Orchestration: Context-preserving handoffs between agents

📦 New in v1.4.0 - Context-Forge Integration

🛠️ Full Context-Forge Support: Automatic detection and smart integration
📦 Init Command: claude-agents init for one-command project setup
🧹 Uninstall Command: Bulk removal with cleanup options
📁 Smart Command Organization: No conflicts with existing context-forge commands
⚡ Concurrent Execution Rules: Enforces best practices for maximum performance
📝 CLAUDE.md Integration: Appends configuration without overwriting
🎯 PRP Awareness: Agents understand and work with your existing PRPs

🚀 Installation

NPM (Recommended)

# Install latest version
npm install -g @webdevtoday/claude-agents@latest

# Or install without @latest (gets latest by default)
npm install -g @webdevtoday/claude-agents

Yarn

# Install latest version
yarn global add @webdevtoday/claude-agents@latest

From Source

git clone https://github.com/webdevtodayjason/sub-agents.git
cd sub-agents
npm install
npm link

🔄 Updating Existing Installation

If you already have claude-agents installed:

# Update to latest version
npm update -g @webdevtoday/claude-agents@latest

# Or with yarn
yarn global upgrade @webdevtoday/claude-agents@latest

After updating the package, update your projects to get the latest features:

# In your project directory, run init to update hooks and configurations
claude-agents init

# This will:
# - Update Claude Code hooks to latest versions
# - Merge new hook configurations into existing settings.json
# - Add any new agent features
# - Preserve your existing configurations

⚡ Quick Start

For New Projects

# Initialize all agents in your project
claude-agents init

# List available agents
claude-agents list

For Context-Forge Projects

# Initialize with context-forge awareness
claude-agents init --respect-context-forge

# Agents will:
# - Detect existing PRPs and CLAUDE.md
# - Place commands in .claude/commands/agents/
# - Append to CLAUDE.md without overwriting
# - Work alongside your existing setup

🔊 Voice Setup (Optional)

Voice announcements provide real-time audio feedback when agents complete tasks in Claude Code.

Quick Setup

# Run the interactive setup wizard
claude-agents voice --setup

# Or configure manually
claude-agents voice --enable
claude-agents voice --provider mcp  # or openai, local

Voice Requirements

Basic Voice (Local TTS)

No additional requirements - works out of the box
Uses system text-to-speech (macOS/Windows/Linux)

High-Quality Voice (ElevenLabs/OpenAI)

FFmpeg: Required for audio playback
- macOS: brew install ffmpeg
- Windows: choco install ffmpeg or download from ffmpeg.org
- Linux: sudo apt-get install ffmpeg
API Keys:
- ElevenLabs: Get from elevenlabs.io
- OpenAI: Get from platform.openai.com

Voice Features

Auto-Announcements: Hear when sub-agents complete tasks
AI Summaries: OpenAI/Anthropic generates contextual completion messages
Multiple Providers: ElevenLabs (best quality), OpenAI, or local TTS
Claude Code Integration: Works seamlessly with hooks system

Testing Voice

# Test with default message
claude-agents voice --test

# Test with custom message
claude-agents voice --test "Hello from Claude Agents"

# Check voice status
claude-agents voice --status

Example Agent Tasks

# Project Planning - Reads and understands your PRPs
claude-agents run project-planner --task "Create implementation roadmap from existing PRPs"
claude-agents run project-planner --task "Break down auth-prp into sprint tasks"

# API Development - PRP-aware implementation
claude-agents run api-developer --task "Implement user endpoints from feature-auth-prp.md"
claude-agents run api-developer --task "Create REST API following our conventions"

# Frontend Development
claude-agents run frontend-developer --task "Build login UI matching dark-theme-ui-prp"
claude-agents run frontend-developer --task "Create dashboard from feature-dashboard-prp.md"

# Testing & Quality
claude-agents run tdd-specialist --task "Create tests for authentication flow"
claude-agents run code-reviewer --task "Review API endpoints for security"
claude-agents run security-scanner --task "Scan authentication implementation"

# Documentation
claude-agents run api-documenter --task "Generate OpenAPI spec from implemented endpoints"
claude-agents run doc-writer --task "Update Implementation.md with progress"

# Debugging & Refactoring
claude-agents run debugger --task "Analyze login timeout issue"
claude-agents run refactor --task "Improve error handling in auth module"

# DevOps & Deployment
claude-agents run devops-engineer --task "Setup CI/CD for main branch"
claude-agents run devops-engineer --task "Create Docker configuration"

# Product & Marketing
claude-agents run product-manager --task "Create user stories from PRPs"
claude-agents run marketing-writer --task "Write feature announcement for auth system"

# Agent Chaining - NEW!
claude-agents chain feature-development  # Full development pipeline