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 merely an AI coding tool. Instead, it covers how to establish Claude Code within real 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 people who…

After completing the course,

After completing this course, you will no longer see Claude Code as merely a tool for “entering good prompts.” Instead, you will be able to determine what Claude needs to see, how far it is allowed to act, how to verify the 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 logs, environment variables, and configuration scope issues into a form that Claude can solve, and review Claude’s proposed changes through testing, diff, and counterexample verification loops. In other words, you will elevate Claude Code from a GUI-based assistant to a level where it can be integrated into actual backend and DevOps workflows.

Features of This Course

1. Rather than simply explaining features, this course teaches from a “harness engineering” perspective based on research 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’ll be less affected by rapidly changing version information and retain principles that can be applied to actual projects.

2. We address 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 operate worktrees and parallel sessions, and connect the GitHub Issue → PR workflow with Claude. It starts with the points where people actually get stuck in real-world work.

What you’ll learn

Getting Started with Claude Code CLI for Practical Work /

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

In the first section, we clearly organize the differences between the GUI-based Claude and the CLI, starting with the basics. Rather than simply comparing interface differences, we explain why the GUI tends to stop at “asking questions and receiving answers,” while the CLI can connect all the way to actual logs, tests, Git, and deployment preparation. We then use the 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 ready to copy and use immediately

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

The provided settings are as follows.

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

• codecraft-harness/SKILL.md
  Transforms short, ambiguous, one-sentence requests into concrete designs and implementation plans.

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

• block-sensitive-paths.sh
  Blocks access to sensitive files and paths such as .env, SSH keys, and parent project folders.

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

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

• guard.sh
  It blocks even unauthorized external network requests to create a secure execution environment.

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

Once you register the configuration file, tests will run automatically every time Claude modifies the code, and if the tests fail, it cannot arbitrarily end by saying, “The task is complete.”

In other words, you will learn how to go beyond asking Claude to validate through prompts and make the system enforce the execution of the validation 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 itself to prevent unnecessary duplicate work.

• Opus 4.8
  Makes the tool execution conditions more explicit so that the necessary tools are used at the right time.

• Sonnet 5
  Covers how to specify in literal detail which files 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 that avoids giving the model excessive instructions and retains only the necessary guidance.

Each playbook also includes the following content.

• Parameter combinations that cause a 400 Error when requested

• Default parameters and behavioral differences by model

• A log 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

You will directly compare handling a complex task sequentially in a single pass with the Graph Engineering approach, which divides 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 setup.

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 the corresponding 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 consisting of 645 lines in total.

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

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

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

Even those using Claude Code for the first time through vibe coding can start with hands-on practice, while developers can learn more deeply, down to its internal workings and design principles.

Three Demo Projects You Can Run Yourself

Rather than just reading configuration files and stopping there, you will run claude in an actual project folder and directly observe how Hooks block and validate tasks.

Each project intentionally includes the following issues.

• Type error

• Test failure

• Logic bugs that appear normal on the surface

Students will experience the following workflow firsthand.

Detect the problem → Block the task → Modify the code → Run the tests → Pass validation

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

Therefore, you can accurately compare how results differ due to the way the work is organized, rather than differences in the code.

Reference document

Practical documentation is also provided so that you can refer to it when setting up projects or solving problems even after completing the course.

• Environment Setup Guide
  This section covers preparing the execution environment, how to register Hooks, and common errors and their solutions.

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

• Harness Inspection Checklist
  Verify that nothing is missing from the prompt, design, implementation, testing, and completion criteria.

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

• Model-Specific Playbook Documentation
  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 just supplementary course materials; they are organized as a Claude Code harness operations manual that you can reuse repeatedly in real-world projects.

The person who created this course

• Silicon Valley Survivor | American Snail 

  Drawing on experience and expertise gained at the forefront of the global tech scene, this course shows non-majors how to overcome technical barriers and become the owners of their businesses.

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

    • Operating the self-developed AI tool 'Snailer CLI' (18K+ downloads)

    • Selected for the Google for Startups Program

  • Formerly an engineer at U.S. big tech companies and promising startups

    • Gave up at the final stage with Amazon 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 cumulatively, with 4.5K+ followers on the SNS platform 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