dangerouslyskip
← Glossary
Definition

Claude Code Harness

A Claude Code harness is the scaffolding around the model — the tools, memory, context management, permissions and feedback loops — that turns Claude Code from a chat window into a reliable engineering agent. In practice it is the harness, not the model, that decides whether an agent ships working code.

The model is not the harness

It is tempting to think capability lives in the model. Most of the time, the difference between an agent that flails and an agent that ships is the harness: what tools it can call, what it can see, what it remembers, and how its work gets checked.

Two teams pointing the same model at the same task get wildly different results, and the delta is almost always harness design.

What a good harness gives the model

A well-designed Claude Code harness supplies the things a raw model lacks:

  • Tools — the ability to read files, run commands, search, and observe real results instead of guessing.
  • Context — the right slice of the codebase in the window at the right time, and not the whole thing.
  • Memory — durable state across runs, so the agent isn’t starting from zero every session.
  • Feedback loops — tests, typechecks and reviews that let the agent see when it’s wrong and correct itself.
  • Guardrails — permissions and boundaries so a capable agent stays a safe one.

Why it’s worth getting right

Harness design compounds. Every improvement to how the agent sees, remembers and verifies its work pays off on every task afterwards. It is the highest-leverage engineering in applied AI, and it is still mostly unwritten.

See also: Meta-Harness

So,… you want to be friends.

Want to go on picnics together? Take our families away on holidays together? Build cool things and make magic together?

Let’s start by connecting…

Connect on LinkedIn →
Subscribe

New essays, build logs and experiments — in your inbox, occasionally. No spam, leave whenever.