Module 01 — Models & CLI overview

Name: Harness Engineering — Claude Code Mastery
Price: 89 EUR
Availability: InStock

In this module

You'll know how to pick the right model for the right task (Claude, GPT-5.4, Gemini 3.1 Pro, open-source), you'll know the strengths and limits of every agentic CLI on the market, and you'll understand why Claude Code offers the deepest harness engineering.

Contents

1.1 — The Claude family: reasoning and long context The three tiers Picking the model in Claude Code Key takeaways

1.2 — The GPT family: the versatile giant The current lineup The ecosystem Key takeaways 1.3 — The Gemini family: natively multimodal The key models Google integration Key takeaways 1.4 — Open-source models: freedom and self-hosting The main players Upsides and limits Key takeaways 1.5 — Model comparison: decision grid Summary table Decision tree Key takeaways 1.6 — Claude Code: the terminal-first agentic tool Harness architecture Launching Claude Code Key takeaways 1.7 — Codex CLI: OpenAI's answer The three autonomy levels Strengths and limits Key takeaways 1.8 — Gemini CLI: Google's free entry Usage Key takeaways 1.9 — Aider, Cline, Continue: the model-agnostic alternatives Quick comparison Key takeaways 1.10 — GitHub Copilot: the autocompletion pioneer Copilot modes Multi-model and GitHub integration Key takeaways 1.11 — Cursor: the AI-first IDE Key features Multi-model Key takeaways 1.12 — Windsurf, Augment and the rest: the expanding ecosystem Overview Key takeaways 1.13 — Why this course focuses on Claude Code The five reasons Key takeaways

1.1 — The Claude family: reasoning and long context The three tiers Picking the model in Claude Code Key takeaways

1.1 — The Claude family: reasoning and long context

Anthropic ships three models in the Claude 4.6 family. Each targets a specific segment of the development workflow, and you'll find them directly in Claude Code via the --model flag or the /model command.

The three tiers

Model	Target	Context	Typical use case
Opus 4.6	Deep reasoning	1M tokens	Architecture, multi-file refactoring, complex decisions
Sonnet 4.6	Perf/cost ratio	1M tokens	Daily development, code review, test generation
Haiku 4.5	Speed and minimal cost	200K tokens	Classification, reformatting, lightweight subagent tasks

Picking the model in Claude Code

```bash

claude --mod

Locked content

Unlock the full course to access this module.

Unlock

Already purchased? Recover access