Module 05 — Hooks & automation

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

In this module

You'll understand why CLAUDE.md is not enough and how hooks deliver deterministic guarantees. You'll know how to wire in security guardrails, automate linting after each edit, and force checks before the agent considers its work done.

Contents

5.1 — Stochastic vs Deterministic: why hooks exist Key takeaways 5.2 — Lifecycle events: where to wire your hooks Key takeaways

5.3 — Anatomy of a hook: JSON structure, matcher, timeout Key takeaways 5.4 — PreToolUse: the main gatekeeper Key takeaways 5.5 — PostToolUse: the automatic feedback loop Key takeaways 5.6 — Stop and SubagentStop: enforce quality before closing Key takeaways 5.7 — SessionStart, UserPromptSubmit, PreCompact: enriching context Key takeaways 5.8 — Security hooks: block, audit, validate Key takeaways 5.9 — Productivity hooks: linting, formatting, pre-commit Key takeaways 5.10 — Assembling a complete hooks configuration Key takeaways

5.1 — Stochastic vs Deterministic: why hooks exist Key takeaways 5.2 — Lifecycle events: where to wire your hooks Key takeaways

5.1 — Stochastic vs Deterministic: why hooks exist

Since the start of this training, you've been configuring Claude Code with CLAUDE.md files, project instructions, and team conventions. All of that works — most of the time. The fundamental problem: CLAUDE.md is advisory. Claude reads it, interprets it, and does its best. But "its best" is not a guarantee. An LLM can forget an instruction, misinterpret it, or decide it doesn't apply in a given context.

Hooks solve this problem. They are shell commands or LLM prompts that run automatically at precise points in the Claude Code lifecycle. They aren't "suggested" — they are executed. When you configure a hook that blocks file deletions, that hook will run on every attempt, no exceptions.

Locked content

Unlock the full course to access this module.

Unlock

Already purchased? Recover access