learn-claude-code

[English](./README.md) | [中文](./README-zh.md) | [日本語](./README-ja.md)
# Learn Claude Code -- Harness Engineering for Real Agents

## The Model IS the Agent

Before we talk about code, let's get one thing absolutely straight.

**An agent is a model. Not a framework. Not a prompt chain. Not a drag-and-drop workflow.**

### What an Agent IS

An agent is a neural network -- a Transformer, an RNN, a learned function -- that has been trained, through billions of gradient updates on action-sequence data, to perceive an environment, reason about goals, and take actions to achieve them. The word "agent" in AI has always meant this. Always.

A human is an agent. A biological neural network, shaped by millions of years of evolutionary training, perceiving the world through senses, reasoning through a brain, acting through a body. When DeepMind, OpenAI, or Anthropic say "agent," they mean the same thing the field has meant since its inception: **a model that has learned to act.**

The proof is written in history:

- **2013 -- DeepMind DQN plays Atari.** A single neural network, receiving only raw pixels and game scores, learned to play 7 Atari 2600 games -- surpassing all prior algorithms and beating human experts on 3 of them. By 2015, the same architecture scaled to [49 games and matched professional human testers](https://www.nature.com/articles/nature14236), published in *Nature*. No game-specific rules. No decision trees. One model, learning from experience. That model was the agent.

- **2019 -- OpenAI Five conquers Dota 2.** Five neural networks, having played [45,000 years of Dota 2](https://openai.com/index/openai-five-defeats-dota-2-world-champions/) against themselves in 10 months, defeated **OG** -- the reigning TI8 world champions -- 2-0 on a San Francisco livestream. In a subsequent public arena, the AI won 99.4% of 42,729 games against all comers. No scripted strategies. No meta-programmed team coordination. The models learned teamwork, tactics, and real-time adaptation entirely through self-play.

- **2019 -- DeepMind AlphaStar masters StarCraft II.** AlphaStar [beat professional players 10-1](https://deepmind.google/blog/alphastar-mastering-the-real-time-strategy-game-starcraft-ii/) in a closed-door match, and later achieved [Grandmaster status](https://www.nature.com/articles/d41586-019-03298-6) on European servers -- top 0.15% of 90,000 players. A game with imperfect information, real-time decisions, and a combinatorial action space that dwarfs chess and Go. The agent? A model. Trained. Not scripted.

- **2019 -- Tencent Jueyu dominates Honor of Kings.** Tencent AI Lab's "Jueyu" [defeated KPL professional players](https://www.jiemian.com/article/3371171.html) in a full 5v5 match at the World Champion Cup. In 1v1 mode, pros won only [1 out of 15 games and never survived past 8 minutes](https://developer.aliyun.com/article/851058). Training intensity: one day equaled 440 human years. By 2021, Jueyu surpassed KPL pros across the full hero pool. No handcrafted matchup tables. No scripted compositions. A model that learned the entire game from scratch through self-play.

- **2024-2025 -- LLM agents reshape software engineering.** Claude, GPT, Gemini -- large language models trained on the entirety of human code and reasoning -- are deployed as coding agents. They read codebases, write implementations, debug failures, coordinate in teams. The architecture is identical to every agent before them: a trained model, placed in an environment, given tools to perceive and act. The only difference is the scale of what they've learned and the generality of the tasks they solve.

Every one of these milestones shares the same truth: **the "agent" is never the surrounding code. The agent is always the model.**

### What an Agent Is NOT

The word "agent" has been hijacked by an entire cottage industry of prompt plumbing.

Drag-and-drop workflow builders. No-code "AI agent" platforms. Prompt-chain orchestration libraries. They all share the same delusion: that wiring together LLM API calls with if-else branches, node graphs, and hardcoded routing logic constitutes "building an agent."

It doesn't. What they build is a Rube Goldberg machine -- an over-engineered, brittle pipeline of procedural rules, with an LLM wedged in as a glorified text-completion node. That is not an agent. That is a shell script with delusions of grandeur.

**Prompt plumbing "agents" are the fantasy of programmers who don't train models.** They attempt to brute-force intelligence by stacking procedural logic -- massive rule trees, node graphs, chain-of-prompt waterfalls -- and praying that enough glue code will somehow emergently produce autonomous behavior. It won't. You cannot engineer your way to agency. Agency is learned, not programmed.

Those systems are dead on arrival: fragile, unscalable, fundamentally incapable of generalization. They are the modern resurrection of GOFAI (Good Old-Fashioned AI) -- the symbolic rule systems the field abandoned decades ago, now spray-painted with an LLM veneer. Different packaging, same dead end.

### The Mind Shift: From "Developing Agents" to Developing Harness

When someone says "I'm developing an agent," they can only mean one of two things:

**1. Training the model.** Adjusting weights through reinforcement learning, fine-tuning, RLHF, or other gradient-based methods. Collecting task-process data -- the actual sequences of perception, reasoning, and action in real domains -- and using it to shape the model's behavior. This is what DeepMind, OpenAI, Tencent AI Lab, and Anthropic do. This is agent development in the truest sense.

**2. Building the harness.** Writing the code that gives the model an environment to operate in. This is what most of us do, and it is the focus of this repository.

A harness is everything the agent needs to function in a specific domain:

```
Harness = Tools + Knowledge + Observation + Action Interfaces + Permissions

    Tools:          file I/O, shell, network, database, browser
    Knowledge:      product docs, domain references, API specs, style guides
    Observation:    git diff, error logs, browser state, sensor data
    Action:         CLI commands, API calls, UI interactions
    Permissions:    sandboxing, approval workflows, trust boundaries
```

The model decides. The harness executes. The model reasons. The harness provides context. The model is the driver. The harness is the vehicle.

**A coding agent's harness is its IDE, terminal, and filesystem access.** A farm agent's harness is its sensor array, irrigation controls, and weather data feeds. A hotel agent's harness is its booking system, guest communication channels, and facility management APIs. The agent -- the intelligence, the decision-maker -- is always the model. The harness changes per domain. The agent generalizes across them.

This repo teaches you to build vehicles. Vehicles for coding. But the design patterns generalize to any domain: farm management, hotel operations, manufacturing, logistics, healthcare, education, scientific research. Anywhere a task needs to be perceived, reasoned about, and acted upon -- an agent needs a harness.

### What Harness Engineers Actually Do

If you are reading this repository, you are likely a harness engineer -- and that is a powerful thing to be. Here is your real job:

- **Implement tools.** Give the agent hands. File read/write, shell execution, API calls, browser control, database queries. Each tool is an action the agent can take in its environment. Design them to be atomic, composable, and well-described.

- **Curate knowledge.** Give the agent domain expertise. Product documentation, architectural decision records, style guides, regulatory requirements. Load them on-demand (s05), not upfront. The agent should know what's available and pull what it needs.

- **Manage context.** Give the agent clean memory. Subagent isolation (s04) prevents noise from leaking. Context compression (s06) prevents history from overwhelming. Task systems (s07) persist goals beyond any single conversation.

- **Control permissions.** Give the agent boundaries. Sandbox file access. Require approval for destructive operations. Enforce trust boundaries between the agent and external systems. This is where safety engineering meets harness engineering.

- **Collect task-process data.** Every action sequence the agent executes in your harness is training signal. The perception-reasoning-action traces from real deployments are the raw material for fine-tuning the next generation of agent models. Your harness doesn't just serve the agent -- it can help improve the agent.

You are not writing the intelligence. You are building the world the intelligence inhabits. The quality of that world -- how clearly the agent can perceive, how precisely it can act, how rich its available knowledge is -- directly determines how effectively the intelligence can express itself.

**Build great harnesses. The agent will do the rest.**

### Why Claude Code -- A Masterclass in Harness Engineering

Why does this repository dissect Claude Code specifically?

Because Claude Code is the most elegant and fully-realized agent harness we have seen. Not because of any single clever trick, but because of what it *doesn't* do: it doesn't try to be the agent. It doesn't impose rigid workflows. It doesn't second-guess the model with elaborate decision trees. It provides the model with tools, knowledge, context management, and permission boundaries -- then gets out of the way.

Look at what Claude Code actually is, stripped to its essence:

```
Claude Code = one agent loop
            + tools (bash, read, write, edit, glob, grep, browser...)
            + on-demand skill loading
            + context compression
            + subagent spawning
            + task system with dependency graph
            + team coordination with async mailboxes
            + worktree isolation for parallel execution
            + permission g