base-agent

Community

Foundation for AI agents.

Authorteodorboev
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides the essential framework for all AI agents, ensuring consistent logging, confidence scoring, and error handling across the system.

Core Features & Use Cases

  • Base Agent Class: A robust abstract class that all agents must extend.
  • Standardized Logging: Automatically logs agent actions, inputs, outputs, and errors.
  • Confidence Scoring: Integrates a system for scoring the confidence of agent outputs, driving automation and review workflows.
  • Escalation Pipeline: Manages the process of escalating low-confidence or erroneous results for human review.
  • Cost Tracking: Estimates and logs the token costs associated with agent operations.
  • Use Case: When building any new AI agent, developers must inherit from this base class to ensure all operational requirements are met from the start.

Quick Start

Implement the execute() method in your new agent class, extending BaseAgent and passing the correct AgentName enum value.

Dependency Matrix

Required Modules

@anthropic-ai/sdk@prisma/clientzod

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: base-agent
Download link: https://github.com/teodorboev/socialai/archive/main.zip#base-agent

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.