Field Guide · Learning Roadmap

Claude Code: from copilot to shipping features.

An agentic coding tool that lives in the terminal — reads, writes, and runs code with you. Goes beyond autocomplete: understands your full codebase and executes multi-step tasks. Built on Claude's reasoning, designed for engineers who want a collaborator, not a copilot.

01

What is Claude Code

Foundation

Definition

Agentic coding tool in the terminal — reads, writes & runs code with you.

Beyond Autocomplete

Understands your full codebase and executes multi-step tasks autonomously.

Designed For

Engineers who want a collaborator — not just suggestions.

Copilot Suggests code Claude Code Ships features Modes: Plan · Investigate · Verify
02

Core Primitives

6 building blocks
md

CLAUDE.md

Project Memory
  • Project memory layer
  • Persistent instructions
  • Coding conventions
  • Tech stack notes
SK

Skills

Reusable Workflows
  • SKILL.md format
  • Loaded on demand
  • Reusable workflows
  • Composable expertise
HK

Hooks

Lifecycle Automation
  • PreToolUse / PostToolUse
  • Lifecycle automation
  • Auto-formatting
  • Custom guardrails
SA

Subagents

Specialized Roles
  • Specialized roles
  • Parallel tasks
  • Context isolation
  • Delegated reasoning
PL

Plugins

Bundled Capabilities
  • Bundled capabilities
  • Shareable packages
  • Community extensions
  • Org-wide standards
MCP

MCP

Model Context Protocol
  • Open standard for tools
  • External tool servers
  • Standardized integrations
  • Plug-in any system
03

Installation & Setup

5 steps · ~3 min
01 · INSTALL
Install CLI
npm install -g @anthropic-ai/claude-code
02 · AUTH
Authenticate
claude login
03 · CD
Enter Project
cd ./your-project
04 · RUN
Launch Claude
claude
05 · MEMORY
Create CLAUDE.md
/init
04

The Claude Code Stack

4 layers
Interface Layer
Terminal CLI · VS Code extension · JetBrains plugin · Slack integration
Reasoning Layer
Claude Opus / Sonnet / Haiku · Extended thinking · Tool-use loop
Context Layer
CLAUDE.md memory · Skills directory · File-system awareness · Codebase indexing
Execution Layer
Bash tool · File-edit tools · Web search/fetch · MCP servers
05

Agentic Patterns

6 patterns
01

Plan-and-Execute

Break the task. Execute step by step.

02

Explore-then-Edit

Read the codebase before changing it.

03

Test-Driven

Write the test. Make it pass.

04

Parallel Subagents

Delegate isolated tasks. Synthesize results.

05

Self-Critique

Review own output. Catch its own bugs.

06

Tool-Orchestrated

Bash, edit, search, fetch — composed in sequence.

06

Building with Claude Code

8-step workflow
01
Define the goal in plain English

State a clear outcome — not a technical pseudo-spec.

02
Write a CLAUDE.md with conventions

Coding standards, tech stack, boundaries as project memory.

03
Let Claude explore the codebase

Read-first: understand before changing.

04
Approve the plan before execution

Plan mode as a gate — review before write access.

05
Add Skills for repeated workflows

Encapsulate recurrence — composable expertise.

06
Add Hooks for automation

Lifecycle automation: format, lint, guardrails.

07
Run, verify, iterate

Feedback loop: test → critique → fix.

08
Commit with co-author tag

Auditable trail: Co-authored-by: Claude.

Security & Trust
  • Permission prompts
  • Sandboxed execution
  • Audit trail
  • Read-before-write
Observability
  • Session transcripts
  • Tool-call logs
  • Cost tracking
  • Token usage per session
07

Skills — the SKILL.md Standard

Anatomy
SKILL.md
---
name:        pdf-extractor
description: Extract text and tables from PDF files
---
# Body markdown — instructions for Claude
When the user uploads a PDF, follow these steps:
1. Inspect the PDF structure
2. Choose the right extraction tool
3. Validate output schema
4. Return clean, structured data
# Optional scripts & resources
# Loaded only when relevant
Anatomy of a Skill
  • YAML frontmatter (name + description)
  • Body markdown (instructions for Claude)
  • Optional scripts and resources
  • Loaded only when relevant
PDF Excel Document Frontend Design Custom Team
08

Multi-Agent Workflows

Patterns & use cases
P

Patterns

Coordination Models
  • Orchestrator — Worker
  • Specialist Subagents
  • Parallel Exploration
  • Critic — Editor pair
  • Researcher — Builder
U

Use Cases

When It Pays Off
  • Large refactors
  • Codebase migrations
  • Test-suite generation
  • Documentation passes
  • Multi-repo coordination
09

Evaluating Claude Code Sessions

Metrics & tooling

Quality

Task success rate%
PR merge rate%
Test pass rate%
Code-review feedbackqual

Efficiency

Tokens per tasktok
Wall-clock timesec
Tool calls per taskn
Cost per shipped featureEUR
log
Session logs
$
/cost command
tx
Telemetry hooks
ok
Custom evals
10

Learning Resources

Verified · Official + ecosystem
MEMBER · FREE

Read the full article or download as PDF

The full article and the PDF are member content. Magic-link login, no credit card, no risk — both available immediately.