Where are my sub-agent configurations saved?

Project-specific agents are stored in `.claude/agents/`, while your global user-level agents are stored in `~/.claude/agents/`.

What is a Claude Code sub-agent?

A sub-agent is a specialized AI assistant that Claude Code can delegate specific tasks to, operating with its own unique context, system prompt, and toolset.

Do sub-agents share the main conversation history?

No, each sub-agent operates in its own isolated context window, which prevents the main conversation from becoming polluted with technical side-tasks.

Can I restrict what a sub-agent is allowed to do?

Yes. You can grant specific tool access (like Bash, Edit, or WebSearch) in the agent's configuration file to ensure it only performs authorized actions.

How do I create a new sub-agent?

Run the `/agents` command in your terminal and select 'Create New Agent' to configure its purpose, scope, and permissions.

AI Sub-Agents Manager

Name: AI Sub-Agents Manager
Author: reggiechan74

byreggiechan74

Productividad y Flujo de Trabajo

Delegates complex tasks to specialized AI assistants with isolated contexts and granular tool permissions within the Claude Code CLI.

Acerca de

The Sub-Agents skill empowers developers to build and orchestrate a team of specialized AI assistants directly within Claude Code. By creating agents with distinct system prompts and specific tool access, users can isolate complex tasks like debugging, code reviews, or data analysis into separate context windows. This prevents main conversation bloat and significantly improves the accuracy of autonomous workflows. Sub-agents can be scoped to individual projects or shared globally, allowing for a highly customizable and reusable AI-driven development environment.

Características Principales

0 GitHub stars
Standardized YAML-based agent configuration
Isolated context windows for specialized task execution
Project and user-level configuration scopes
Automatic task delegation based on agent descriptions
Granular tool permission control per agent

Casos de Uso

Automating multi-step code reviews with a dedicated expert reviewer agent
Isolating root-cause analysis for complex bugs to keep the main chat history clean
Creating a read-only documentation assistant to fetch and analyze external APIs

Acerca de

Características Principales

0 GitHub stars
Standardized YAML-based agent configuration
Isolated context windows for specialized task execution
Project and user-level configuration scopes
Automatic task delegation based on agent descriptions
Granular tool permission control per agent

Casos de Uso

Automating multi-step code reviews with a dedicated expert reviewer agent
Isolating root-cause analysis for complex bugs to keep the main chat history clean
Creating a read-only documentation assistant to fetch and analyze external APIs