Organic pattern

What Claude Code
Actually Is

The architecture behind the agent runtime, revealed by the source code leak

Execution Pipeline

01
Your Input
02
CLI Parser
03
Query Engine
04
LLM API
05
Tool Loop
06
Output

Six Core Systems

01

Tool System

File operations, code execution, search, and external tool integration via MCP protocol.

02

Command System

85+ slash commands for planning, reviewing, compacting, resuming, and managing sessions.

03

Memory System

CLAUDE.md at the center. User-level, project-level, and extracted memories across sessions.

04

Permission Engine

Granular control with wildcard rules. Allow, deny, or ask for any action at any scope.

05

Multi-Agent Coordinator

Task decomposition, parallel execution, and background work across multiple agents.

06

MCP Client + Server

Both consumes and provides tools. The integration layer for external systems and plugins.

The Commands
That Matter

Essential slash commands for designers using Claude Code

Command What it does Category
/init Sets up project context. Generates the CLAUDE.md file that shapes every future interaction. Setup
/plan Planning mode. Maps out the full approach before touching any files. Essential for complex builds. Strategy
/compact Compresses conversation history. Keeps important context, drops noise. Accepts optional focus prompt. Tokens
/review Runs a structured code review workflow. First-class command, not an afterthought. Quality
/context Manages what files Claude Code is paying attention to. Every file in context costs tokens. Tokens
/cost Shows what you've actually spent in the current session. Run this early and often. Tokens
/resume Pick up where you left off between sessions without re-explaining everything. Workflow
/summary Generates a session summary. Pairs with /resume for multi-day projects. Workflow
Hexagonal bokeh pattern

7 Habits of Top 1%
Claude Code Users

Based on what the source code reveals about how the tool was designed to be used

1

Treat CLAUDE.md like a force multiplier

Keep it short, opinionated, and operational. Update it regularly. Route to other files. This single file shapes every interaction.

2

Learn the command surface

You don't need all 85 commands. But /plan, /compact, /context, /review, /cost, and /resume will change your daily workflow.

3

Configure permissions for recurring workflows

Stop babysitting every action. Set wildcard rules for the stuff you do every day. Let it operate like an agent.

4

Think in decomposition, not monolithic prompts

Break complex work into phases: research, plan, execute, verify. Let Claude Code use its multi-agent architecture the way it was designed.

5

Manage context like it's money

Because it literally is. Use /compact when conversations get long. Use /context to control what's loaded. Every unnecessary file is tokens you're paying for.

6

Connect everything to it

MCP servers, CLIs, plugins, skills. The more tools Claude Code can access, the more valuable it becomes. Build an ecosystem, not a silo.

7

Treat it like infrastructure, not an app

Model routing, sub-agent overrides, shell behavior, privacy controls. There's real leverage in tuning the environment to fit your workflow.