Claude Code from zero: an agentic coding workflow, step by step

Agentic coding tools reward workflow discipline far more than prompt cleverness. This tutorial sets up Claude Code and then focuses on the habits that separate “autocomplete with extra steps” from an agent that does real work while you review it.

Step 1 — Install and authenticate

npm install -g @anthropic-ai/claude-code
cd your-project
claude

First run walks you through login. Verify with /status inside the session.

Step 2 — Give the agent a memory: CLAUDE.md

Claude Code reads CLAUDE.md from your project root at the start of every session. This is the highest-leverage file in the whole workflow. A good one is short and factual:

# CLAUDE.md

## Project
Payment reconciliation service. Python 3.12, FastAPI, PostgreSQL.

## Commands
- Test: `pytest -q`
- Lint: `ruff check .`
- Run locally: `make dev`

## Conventions
- Type hints everywhere; mypy must pass.
- Never touch `migrations/` by hand.

Rule of thumb: anything you’d tell a new teammate on day one belongs here. Anything you’d tell them once, in one specific situation, does not.

Step 3 — The core loop: plan first, then execute

For any non-trivial task, don’t let the agent code immediately. Press Shift+Tab to cycle into plan mode, describe the task, and read the plan it produces. You are reviewing the approach while it’s still cheap to change. Then approve, and let it execute against the plan.

The habit that matters: review at the plan level and the diff level, not keystroke level. You’re a tech lead now, not a typist.

Step 4 — Let it verify its own work

An agent that can run your tests can check itself. End tasks with an explicit verification instruction:

Implement the fix, then run pytest -q and iterate until green.

This single habit converts “plausible-looking code” into “code that passed the suite before you ever read it.”

Step 5 — Extend it with an MCP server

Claude Code speaks MCP natively. Connect any server:

claude mcp add my-server -- python /path/to/server.py
claude mcp list

Now the tools your server exposes are available in-session — the same mechanism from our first MCP server tutorial.

Troubleshooting

The agent keeps “fixing” things you didn’t ask about

Scope creep is a prompting problem. Add “Do not change anything outside src/billing/” style constraints to the task, and put standing boundaries (“never edit generated files”) in CLAUDE.md.

Long session starts giving worse answers

Context windows fill up. Use /compact at natural breakpoints, or /clear between unrelated tasks — a fresh session with a good CLAUDE.md beats a bloated one.

Next in this learning path Multi-agent orchestration explained: build an orchestrator and sub-agents from scratch →