The article analyzes Harness Engineering by breaking down the five layers of Agent systems—Model, Tool, Skill, Sub‑agent, and Harness—showing how to design a workspace that not only runs agents but also enables verification, hand‑off, correction, and the disciplined removal of outdated constraints.
This article clarifies the core concepts of AI agents, distinguishing models from agents, defining scaffolding and harness, and detailing the roles of context engineering, policy, tools, skills, sub‑agents, and training components such as environment, rollout, reward, and trainer.
This guide explains all 14+ metadata fields available in a SKILL.md file, distinguishes the six standard Agent Skills fields from Claude Code extensions, and provides concrete examples and best‑practice recommendations for naming, descriptions, licensing, compatibility, allowed tools, and advanced options such as model selection and sub‑agent configuration.
This article dissects Claude Code's AgentTool, explaining how it spawns full‑featured sub‑agents, routes execution through three distinct paths, shares Anthropic Prompt Cache via Fork, and protects against infinite recursion with a dual‑layer safeguard while isolating worktrees for safe parallel file operations.
The article argues that an agent harness’s context window should be treated as a bounded workset rather than an ever‑growing transcript, and explains how pagination, compression, tool‑output limits, session isolation, and sub‑agent design together determine whether long‑running agents remain reliable and efficient.
The article explains how to choose between Sub‑Agent and Agent Team structures for multi‑agent systems by evaluating whether sub‑tasks share context, need isolation, compression, parallelism, or continuous collaboration, and provides practical guidelines, pitfalls, and a decision framework to avoid over‑engineering.
The article analyzes why many AI projects misuse multi‑agent setups, explains the fundamental differences between Sub‑Agent (isolated parallel executors) and Agent Team (collaborative teams with shared state), and provides concrete guidelines, code examples, and design principles to select the appropriate architecture for a given task.
This guide walks developers through six powerful Claude Code features—including CLAUDE.md memory, Plan Mode planning, fine‑grained permission controls, Sub‑Agents, Model Context Protocol integration, and automated Hooks—showing how to boost productivity, ensure code quality, and avoid common pitfalls.
This article explains how OpenClaw functions as an AI Agent framework that connects chat applications to large language models, manages multi‑turn dialogues, executes tool commands, handles memory and security, and demonstrates advanced features such as sub‑agents, cron jobs, and context compression.
The article explains how to define, abstract, and evaluate reusable AI Skills, integrate them into collaborative workflows, and evolve them into Sub‑Agents that own continuous responsibilities, providing concrete examples, design principles, metrics, and a step‑by‑step rollout plan for product development teams.
This guide explains the Sub‑Agent concept used in AI coding tools, shows why it solves context‑loss problems, and walks through a concrete PHP security review example with Claude Code, including agent configuration, execution steps, and a detailed vulnerability report.
