AI Agents

Claude Code · Cursor · MCP and other AI agent setups.

• Running AI Agents in the Background — cron · launchd · Task Scheduler

  Scheduling patterns to run AI agents like Claude Code periodically without a human at the keyboard. macOS launchd · Linux cron · Windows Task Scheduler compared.

• Claude Code Hooks — Auto-run Shell Commands on Session and Tool Events

  settings.json hooks insert shell commands at session start / pre & post tool use / stop. Five examples: security block, auto-format, logging, external alerts.

• Claude Code setup — install, permissions, hooks, MCP in the first hour

  Single-path setup for Claude Code: install → auth → project guidance → permissions → hooks → MCP. The state you want to reach before using it daily.

• Cursor setup — install, .cursorrules, MCP, and how to split work with Claude Code

  First hour with the AI editor Cursor: model choice, four core shortcuts, project rules, and how to combine it with Claude Code.

• MCP Servers — Connect External Tools to Claude Code / Cursor

  Expose filesystem, GitHub, DB, Slack to AI agents via Model Context Protocol. Setup, debugging, security.

• Multi-Agent Workflow — Claude Code + Codex CLI Collaboration

  Patterns that break when you move from one AI agent to two — role split, handoff document, verification gates, real failure cases.

• Prompt Templates — Reuse AI Tasks You Do Daily

  Stop briefing the AI from scratch — code review, debugging, refactor, test, doc templates.

• Claude Code Subagents — Role Splitting via the Task Tool

  Spawn Explorer/Plan/Reviewer subagents to protect the parent's context and boost throughput in parallel.