Upgrading DSH to version 0.1.0‑rc.8 shows that Codex and Claude Code can be invoked as subagents, exposing the internal Harness execution system and prompting a discussion of whether agents are forming a new runtime layer in software architecture.
The article explains why using a flagship LLM for end‑to‑end coding tasks is slow and costly, then presents a SubAgent orchestration framework that assigns planning to the expensive model and execution to cheaper models, detailing seven universal rules, three concrete model combos, a full test workflow, and common pitfalls to halve token bills.
The article explains that parallelizing a task across five Claude Code subagents often yields no speedup—or even slowdown—because true parallel gains depend on independent task parts, while four overheads (re‑learning context, dependency chains, shared file conflicts, and single‑point aggregation) can dominate the runtime.
Claude Code’s v2.1.212 overhaul turns /fork into a one‑click “clone” that spawns an independent background session with full conversation memory, letting you fix bugs or run long jobs while your primary work continues uninterrupted.
The article analyzes why Claude Code often ignores constraints in CLAUDE.md, identifies four root causes—including incomplete rule loading, vague descriptions, context overload, and lack of hard enforcement—and proposes a five‑layer governance architecture with concrete migration and troubleshooting steps.
The article explains the technical differences between CLAUDE.md and Skill files, when to use each, their loading strategies, file structures, front‑matter fields, dynamic context, security considerations, and how Skills interact with Subagents, Plugins and Agent Teams in Claude Code.
This article explains how Harness Skills let you package repeatable instructions into reusable directories, distinguishes Reference and Action Skills, shows dynamic shell‑command injection, details front‑matter controls, and provides concrete PR‑summary and pre‑commit examples for Claude agents.
This lesson explains how Harness uses Subagents—isolated execution units created via the Task tool—to offload heavy, multi‑step operations into separate context windows, custom prompts, and limited toolsets, and how to configure built‑in and custom Subagents with the Claude Code SDK.
This tutorial shows how to transform the previously built Vercel Eve agents into a full‑featured content creation team by defining reusable skills for topic planning, article writing, and review, and by splitting responsibilities into dedicated subagents for researcher, writer, and reviewer, with detailed code examples and workflow guidance.
The article explains AgentScope 2.0’s “agent‑as‑tool” philosophy, showing how a Router agent can dynamically delegate tasks to specialist ReActAgents via @Tool methods, and how HarnessAgent’s Subagent feature enables long‑running, user‑direct interactions, with concrete Java code illustrating both patterns.
Claude Code often hallucinates by inventing functions, imports, or test results, which wastes time; this article explains a four‑layer engineering setup—honesty rules, pre‑write verification, post‑write hooks, and a dedicated fact‑checking sub‑agent—to force the model to provide evidence before claiming code works.
This article details how we used a three‑layer AI architecture—Skill for stable execution, SubAgent for context‑aware scheduling, and Agent Team for parallel collaboration—to reliably migrate a large Android codebase to a Kotlin Multiplatform project, addressing instability, context inflation, and efficiency challenges.
This article analyzes why token waste in Claude Code stems mainly from bloated context rather than verbose prompts and presents seven concrete techniques—including model selection, CLAUDE.md management, Subagent usage, precise file targeting, early compacting, context diagnostics, and restrained tool integration—to reduce token consumption by up to 80% while preserving workflow efficiency.
The article explains how Deep Agents’ task tool splits complex responsibilities into a main agent that schedules and sub‑agents that execute specialized roles, detailing the tool’s placement, SubAgent definition, predefined versus dynamic agents, context isolation, AsyncSubAgent use cases, and practical criteria for when to decompose tasks.
An in‑depth walkthrough of a Spring AI‑based AI Agent demo showcases its core modules—including AgentCore orchestration, multi‑layer conversation memory compression, function‑calling tool registration, RAG retrieval pipelines, markdown‑driven Commands and Skills, Sub‑Agent isolation, and MCP integration—complete with code snippets, design rationale, and runtime configuration details.
This article analyzes Anthropic's Claude Code session‑management features, explaining how context rot limits effective token usage, what the 1 M‑token window actually stores, and when to use the five built‑in actions—Continue, /rewind, /clear, Compact and Subagent—to keep long‑running AI tasks reliable and efficient.
Drawing from 18 months of hands‑on experience, this guide presents seven concrete practices—ranging from precise task framing and lean CLAUDE.md files to reusable skills, memory repositories, reliable hooks, a structured Design‑Plan‑Build workflow, and Subagents—that help developers use Claude Code efficiently and avoid costly rework.
In this detailed lecture, Prof. Li Hongyi of National Taiwan University dissects the OpenClaw AI Agent, explaining its system prompts, tool usage, memory handling, sub‑agents, security risks like prompt injection, and practical safeguards for deploying autonomous agents on personal computers.
This article explains DeepAgents SubAgent mechanisms, showing how context isolation and task division improve complex agent workflows, details two creation methods (dictionary‑based and compiled), demonstrates a search‑and‑report demo, and outlines suitable and unsuitable scenarios with practical code examples.
The article walks through a new OpenClaw scenario where users attempt to create a sub‑agent as cheap labor, explains the required /spawn parameters (runtime, agentId, task, label), shows a concrete example command, and discusses why the resulting agent fails to act as intended, offering guidance for non‑IT users.
The article explains how organizing the prompt, tool schemas, dialogue history, and retrieved documents—collectively the context window—affects an AI agent’s decisions, introduces the concepts of Lost‑in‑the‑Middle, Thinking Tokens, tool‑response caching, compaction versus SubAgent strategies, and shows a step‑by‑step evolution that raised accuracy from 60 % to over 95 %.
This article outlines a practical, step‑by‑step workflow for Claude Code that starts with defining acceptance criteria, correctly layering context, selecting the right execution channel, enforcing system‑level constraints, and actively managing long sessions, turning experimental AI agents into reliable engineering tools.
The article shares a hands‑on review of Claude Code, a terminal‑based AI coding assistant, covering setup with custom API endpoints, the use of Claude.md for project context, subagent parallel development, comparisons with GeminiCLI and Cursor, and practical tips for effective use.
