Coding

Claude Code

Anthropic's agentic CLI for working in a real codebase.

Knowledge cards
Best practice
Keep a CLAUDE.md That Actually Changes the Output
A discipline for the CLAUDE.md file that Claude Code reads at the start of every task: keep it to rules that actually change behaviour — real commands, real conventions, real boundaries — and ruthlessly cut anything the model would do correctly anyway.
L3 · Workflows
Knowledge card
Let Claude Code Run the Tests and Close the Loop
A Claude Code practice where you let the agent run the project's tests, type checker, or build itself after making a change, and require it to iterate until they pass before reporting the work done.
L3 · Workflows
Best practice
Let Claude Code Explore the Repo Before It Edits
Working with Claude Code — Anthropic's agentic CLI — by letting it read and understand the codebase first, agree a plan, then make edits and run the tests itself, rather than demanding a change blind.
L4 · Multi-AI systems
Workflow
Have Claude Code Plan First, Then Approve the Plan
A workflow where you ask Claude Code to produce a written plan — the files it will change and the approach — and get your sign-off before it edits anything. You review the intent, which is cheap, rather than the diff, which is expensive to unwind.
L3 · Workflows
Claude Code

An agent in your terminal

Claude Code is Anthropic's agentic coding tool that works directly in your terminal and codebase — reading files, running commands, planning changes, and editing across a project. Unlike pasting snippets into a chat, it operates on the real thing, which is what makes it useful for actual development rather than isolated questions. The trade-off is that an agent editing your code needs supervision and good habits, or it does confident work in the wrong direction. Set up correctly, it behaves like a fast, capable teammate.

Explore, plan, and keep a CLAUDE.md

Three habits make Claude Code reliable. Let it explore the codebase before it edits, so its changes are informed by how the project actually works. Make it plan and wait for your approval before applying anything significant, so you catch a wrong approach before it becomes a wrong diff. And keep a CLAUDE.md that earns its place — concise project conventions and context it reads every session, not a dumping ground. Together these turn an eager generator into a dependable collaborator.

Frequently asked
What is Claude Code?

Anthropic's agentic coding tool that works in your terminal and codebase — reading files, running commands, planning, and editing across a project rather than answering isolated questions.

How do I use Claude Code well?

Let it explore before editing, make it plan and wait for approval on significant changes, and keep a concise CLAUDE.md of project conventions it reads each session.

What is a CLAUDE.md file?

A project file of conventions and context that Claude Code reads every session. Keep it concise and useful — it should earn its place, not become a dumping ground.