Articles for people who
ship the stack
Original rewrites on React, Node.js, TypeScript and AI — practical notes from the same engineering practice behind our operator software. Article bodies are in English.
Tagged: subagents
How Subagents and Multi-Agent Systems Split Work and Cost Tokens
Subagents vs multi-agent systems: the orchestrator-worker design, four topologies, what each costs in tokens, and the cases where a single agent does better.
12 min readHow Claude Code Fits Together: Skills, Subagents, MCP, Hooks, Plugins
How Claude Code fits together: CLAUDE.md, skills, subagents, MCP, hooks, slash commands and plugins, what each building block does and when to reach for it.
10 min readFive Layers Inside Claude Code: Memory, Skills, Hooks, Subagents and Plugins
Claude Code seen as an agent runtime: CLAUDE.md memory, on-demand Skills, deterministic Hooks, isolated Subagents and Plugins that package it all for a team.
15 min readGemini CLI Subagents: Context Isolation, Tool Limits and a README Specialist
Gemini CLI subagents keep the main chat clean: hub and spokes, the agent definition file, the /agents command and a read-only README agent with tight limits.
9 min readSubagents in Practice: Roles, Budgets, Bans and Silent Failures
Claude Code subagents that last: roles, handoff files, run state, budgets, bans and silent-failure checks, plus how skills vs subagents differ in practice.
35 min readClaude Code Subagents Explained: What They Are and When to Use Them
How Claude Code subagents differ from skills and agent teams: context isolation, a first custom subagent, description and tool best practices, and when to skip them.
15 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.