AI Agents

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

• OpenAI Codex CLI setup — comparison with Claude Code and Cursor

  OpenAI's official coding-agent CLI. Install, auth, autonomy modes, and how it compares to Claude Code — all in 30 minutes.

• GitHub Copilot setup — splitting work between Copilot, Claude Code, and Cursor

  30-minute setup for Copilot in VS Code and JetBrains. Plus a decision table for which jobs go to Copilot vs Claude Code/Cursor.

• Local LLMs with Ollama — Open WebUI · Continue.dev integration

  Run Llama / Qwen / DeepSeek locally on Mac and Windows. Cost, privacy, offline — an alternative to cloud LLMs.

• Running Claude Code, Cursor, and Copilot together

  Practical workflow for using all three AI tools at once without conflicts — task-to-tool mapping, keybinding clashes, context isolation.

• 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.