Claude Code Harness & Graph Engineering: Advanced Claude Code CLI Harness Engineering in Practice

Claude Code can be fun in a GUI.

However, in CLI harness design, Claude Code pays off.

This course does not introduce Claude Code CLI as a simple AI coding tool. Instead, it covers how to establish Claude Code within real-world backend and DevOps workflows through the lenses of Context, Permission, Verification, Tool, Subagent, and Debugging Harness. By connecting log analysis, bug fixes, test recovery, CLAUDE.md design, session management, and parallel worktree operations, you will learn how to design a work system that enables Claude to operate safely in real-world projects.

Recommended for developers who…

After completing the course,

After taking this course, you’ll no longer see Claude Code as merely a “tool for writing good prompts.” Instead, you’ll be able to determine what Claude needs to see, how far it can act, how to verify its results, when to use clear/compact/restart if a session becomes polluted, and how to manage worktrees and parallel sessions.

Specifically, you will be able to structurally codify project rules and prohibitions in CLAUDE.md, organize log, environment variable, and configuration scope issues into a form that Claude can solve, and review Claude’s proposed changes through a testing, diff, and counterexample verification loop. In other words, you will take Claude Code beyond being a GUI-based assistant and bring it to a level where it can be integrated into actual backend and DevOps workflows.

Features of this course

1. Rather than merely explaining features, this course teaches from a “harness engineering” perspective grounded in academic papers.

This course does not list Claude Code’s features like official documentation. Instead, it explains how to design Context, Permission, Verification, Tool, Subagent, and Debugging Harnesses so that Claude Code can work safely on real projects. As a result, you are less affected by rapidly changing version information and are left with principles that can be applied to real projects.

2. It covers large codebases and real-world work problems

Rather than simply building demo apps, this course covers how to keep Claude from getting lost in large codebases, reduce session contamination, safely manage worktrees and parallel sessions, and connect the GitHub Issue → PR workflow with Claude. It starts with the points where people actually get stuck in practice.

What you'll learn

Getting Started with Claude Code CLI in Practice /

Architecture / Memory / CLAUDE.md / Plan Mode / Skills

In the first section, we clearly lay out the differences between GUI-based Claude and the CLI. Rather than simply comparing interface differences, we explain why GUI use tends to stop at “asking a question and receiving an answer,” while the CLI can connect all the way to actual logs, tests, Git, and deployment preparation. We then use Claude Code architecture to understand why the harness is more important than the model, and explore the roles of memory across sessions and CLAUDE.md, as well as the differences between Plan/Thinking Mode and Subagents, and between Skills and Tool use.

Harness configuration files you can copy and use right away

We provide all the harness configurations you create in the course as completed files.
After taking the course, you can copy them into your own project and apply them right away without having to rewrite them from scratch.

The provided settings are as follows.

• CLAUDE.md
  Defines the working rules Claude must follow in the project.

• codecraft-harness/SKILL.md
  Transforms a short, ambiguous one-sentence request into a concrete design and implementation plan.

• solid-review/SKILL.md
  Before starting implementation, check whether responsibilities are properly separated and whether the design is unnecessarily complex.

• block-sensitive-paths.sh
  .env, SSH keys, and sensitive files and paths such as the parent folder of the project are blocked from access.

• run-tests-after-edit.sh
  Automatically runs the relevant tests every time Claude modifies a file.

• block-stop-without-tests.sh
  It prevents you from reporting a task as complete when tests have not been run or have failed.

• guard.sh
  It blocks even unauthorized external network requests, creating a safe execution environment.

The Hooks included in the course are not merely sample code.
We ran them all in real-world environments and verified that they work.

Once you register the configuration file, tests run automatically every time Claude modifies the code, and it cannot arbitrarily end by saying “I’ve completed the task” when the tests are failing.

In other words, you will learn how to go beyond asking Claude to perform verification through prompts and make the system forcibly execute the verification process.

3. Model-Specific Prompt Playbook

Even when using the same harness, each model differs in which instructions it follows well and which ones it is likely to miss.

In this course, instead of using the same prompt for every model, we provide five copy-ready prompt blocks that outline which instructions to remove and which to add based on each model’s characteristics.

• Opus 5
  Reduce instructions for validations the model performs on its own to prevent unnecessary duplicate work.

• Opus 4.8
  Specify tool execution conditions more clearly so that the necessary tools are used at exactly the right time.

• Sonnet 5
  This covers how to specify, literally and concretely, the files that need to be modified and the scope of the changes.

• Haiku 4.5
  Lay out the execution procedure step by step so you can work reliably even with models that do not have the effort option.

• Fable 5
  We provide a reference approach for leaving only the necessary prescriptions without giving the model excessive instructions.

Each playbook also includes the following content.

• Parameter combinations that cause a 400 Error when requested

• Default parameters and behavioral differences by model

• A record sheet for comparing results while changing the effort value

• Run the same prompt on multiple models and compare the results in the Lab 04 exercise

Rather than simply explaining “which model is better,” you will learn how to find the optimal settings for each model yourself by repeatedly running the same task and recording the results.

Graph Engineering Hands-on Materials — Lab 05

Directly compare the approach of processing complex tasks sequentially in one go with the Graph Engineering approach of dividing multiple tasks according to their dependencies.

Interactive Learning Sheet

You can use it by opening the HTML file in a browser, without any separate installation or server startup.

You can play back step by step how the same request is handled differently in the following two approaches.

• Repeating a single flow with loop-based execution

• Graph-based execution that divides a task into multiple nodes and dependencies

By selecting each step, you can also view the configuration file that created that action, allowing you to immediately understand the relationship between the execution result and the configuration.

Step-by-Step Learning Guide

We provide a learning guide totaling 645 lines.

Rather than explaining the theory at length from the outset, it is structured in the following order.

Check the conclusion → 30-minute practice → key concepts → advanced theory

There are also separate learning paths for non-majors and for students with development experience.

Even if you’re using Claude Code for the first time through vibe coding, you can start with hands-on practice, while developers can delve deeper into its internal workings and design principles.

Three demo projects you can run yourself

Rather than simply reading the configuration file and stopping there, you will run claude in an actual project folder and see firsthand how the Hook blocks and validates the work.

The following issues have been intentionally included in each project.

• Type error

• Test failure

• A logic bug that appears normal on the surface

Learners will directly experience the following flow.

Detect the issue → Block the task → Modify the code → Run the tests → Pass verification

Loop-based and graph-based projects use the same code, with only the harness configurations set up differently.

Therefore, you can accurately compare how results differ due not to code differences, but to differences in how the work is organized.

Reference documentation

We also provide practical documentation that you can refer to when setting up projects or solving problems even after completing the course.

• Environment Setup Guide
  A summary of how to prepare the execution environment, register Hooks, and resolve common errors.

• Distinguishing the Roles of Skills / Hooks / CLAUDE.md / Tests
  Explains what each component is responsible for and which tool to use for each problem.

• Harness Inspection Checklist
  You can verify that nothing is missing from the prompt, design, implementation, tests, and completion criteria.

• Question and test cards
  Provides questions to use when requirements are ambiguous, test design criteria, and a verification checklist template.

• A model-specific playbook document
  It organizes each model’s parameters, behavioral characteristics, and prompt-writing guidelines in one place.

• Model evaluation log
  You can run the same task with multiple models and configurations, then compare and record the results.

These materials are not merely course supplements; they are structured as a Claude Code harness operations manual that you can repeatedly use in real-world projects.

The person who created this course

• Silicon Valley Survivor | American Snail 

  Based on experience and expertise gained at the forefront of the Global Tech Scene, this presents a path for non-majors to overcome technical barriers and become the owners of their businesses.

  • Current) Founder of a Silicon Valley AI coding agent startup

    • Operating the in-house AI tool 'Snailer CLI' (18K+ downloads)

    • Selected for the Google for Startups Program

  • Former engineer at major U.S. tech companies and promising startups

    • Gave up Amazon’s final-stage offer to start a company

    • Silicon Valley AI fintech startup engineer

    • OpenAI / Meta / Apple / Adobe / Amazon Full-Stack Fellowship

    • Domestic search engine portal, fintech development

    • AI startup AR/B2B/SDK development

  • Proven educational expertise

    • Double major in Computer Science and Business Administration at a four-year university in Seoul, with extensive startup experience

    • Produced 1,900+ students in total, with 4.5K+ followers on the SNS Threads and 480+ Substack followers

    • Threads: https://www.threads.com/@rich_l_2024?igshid=NTc4MTIwNjQ2YQ==

    • Substack: https://open.substack.com/pub/1234373801

Do you have any questions?

Notes Before Taking the Course