BLD-201 · Personal Development

Claude Code Power User — From Interactive to Autonomous Agent Development

Personal development track →

Most people use 10% of Claude Code’s capability. This course fixes that. You’ll master the full stack — hooks, CLAUDE.md architecture, custom subagents, multi-agent workflows, the Agent SDK, and production hardening — all in your real codebase, not toy examples. Every session builds toward a capstone architecture document and a production-hardened agent you can actually deploy.

30 Hours
10 Learning objectives
Create Bloom's ceiling (?)
6 Competencies

Learning Objectives

Objectives

Depth
  • Explain the difference between prompting (ask → answer) and agentic development (goal → plan → tools → actions → verify), and identify agent loops in your own workflows Understand
  • Master Claude Code’s advanced features — /effort levels, /loop automation, multi-instance patterns, and model routing — to maximize output quality and minimize cost Apply
  • Design CLAUDE.md architecture using instruction budgets (~150–200 lines), @import hierarchy, skills budgets (2% context), and auto-memory configuration Create
  • Evaluate the plugin and skill ecosystem — assess SKILL.md quality, security risks (including the plugin signing gap), and cross-platform compatibility Evaluate
  • Configure custom subagents with YAML frontmatter, model overrides, and tool restrictions for specialized workflows like multi-agent code review Apply
  • Implement event-driven hook pipelines using all 22 hook events, HTTP hooks, and CI/CD integration for production automation Apply
  • Build standalone agents using the Agent SDK with tool execution, session persistence, compaction handling, and the initializer/coder pattern Create
  • Evaluate autonomous loop patterns — /loop, Ralph Loop, Claude-Mem Endless Mode — and their cost, quality, and reliability tradeoffs Evaluate
  • Design multi-agent orchestration using Agent Teams, cross-device workflows (Dispatch, Codex Cloud), and the WebMCP standard Analyze
  • Apply production hardening: MCP security posture (30+ CVEs), cost management via /effort + prompt caching, Enterprise Analytics API monitoring, and Claude Code Security scanning Apply

Levels: Remember · Understand · Apply · Analyze · Evaluate · Create — highest demands most original thinking.

10 sessions. Here’s what you’ll do.

  1. 01

    What Makes an Agent — From Prompting to Orchestration

    Free trial

    Build the mental model: prompting (ask→answer) vs agentic (goal→plan→tools→verify). Map the three paradigms — interactive, autonomous, hybrid.

    Exercise: Your Agent Baseline
  2. 02

    Claude Code Power User Masterclass

    Free trial

    Gap-filling for daily CC users: /effort levels, /voice, /loop automation, multi-instance patterns, Agent Teams, and breaking changes.

    Exercise: CC Power User Playbook
  3. 03

    The .claude Folder — Your Agent’s Operating System

    Configuration deep dive: CLAUDE.md cascade, settings.json levels, instruction budgets, skills budgets, auto-memory, and @import syntax.

    Exercise: CLAUDE.md Refactor
  4. 04

    The Plugin & Skill Ecosystem

    Extension types: plugins, skills, hooks, agents, MCP servers, desktop extensions. Evaluate the ecosystem and assess supply chain security risks.

    Exercise: Plugin Ecosystem Audit
  5. 05

    Subagents, Custom Agents, and Multi-Agent Code Review

    Configure custom subagents with tool restrictions and model routing. Build a 3-agent code review system.

    Exercise: 3-Agent Code Review System
  6. 06

    Hooks, Pipelines, and Event-Driven Architecture

    22 hook events with decision control types. HTTP hooks, security context (real CVEs), and pipeline architecture patterns.

    Exercise: Production Hooks + Pipeline Design
  7. 07

    The Agent SDK — Building Standalone Agents

    Agent SDK deep dive: agent loop, tool execution, compaction API, session persistence. Build agents you can deploy outside Claude Code.

    Exercise: Two Standalone Agents
  8. 08

    Autonomous Loops and Long-Running Agents

    /loop cost model and compaction between iterations. Evaluate Ralph Loop, Claude-Mem Endless Mode, and when autonomous loops are worth it.

    Exercise: Autonomous Loop Trial Run
  9. 09

    Multi-Agent Orchestration and Cross-Tool Workflows

    Agent Teams, WebMCP W3C Draft, cross-device orchestration with Dispatch and Codex Cloud. Cost reality: 3–5x tokens.

    Exercise: Multi-Agent Course Builder
  10. 10

    Capstone — Production Deployment + AI Uni Agent Architecture

    Harden agents for production: MCP security posture, cost management with /effort and prompt caching, testing, and monitoring.

    Exercise: AI Uni Agent Architecture + Production Agent

What You'll Master

Agent Architecture

Understanding agent loops, the three paradigms (interactive, autonomous, hybrid), human-in-the-loop models, and how Claude Code fits in the agentic landscape.

Configuration & Instruction Design

CLAUDE.md hierarchy, settings.json load order, instruction budgets, skills budgets, @import syntax, auto-memory, and the WHY/WHAT/HOW pattern.

Plugin & Extension Ecosystem

Evaluating plugins and skills, reading SKILL.md, cross-platform compatibility, supply chain security assessment, and building custom skills.

Subagent & Multi-Agent Design

Custom subagents with YAML frontmatter, model routing strategies, Agent Teams with shared task boards, Dispatch orchestration, and the WebMCP standard.

Hooks & Automation

All 22 hook events, HTTP hooks, pipeline architecture (sequential, DAG, event-driven, swarm), autonomous loops, CI/CD integration, and cost tracking.

Production Hardening

MCP threat landscape (30+ CVEs), permission modes, Claude Code Security scanning, cost management via /effort and prompt caching, Enterprise Analytics API monitoring.

What You'll Build

AI Uni Agent Architecture — A comprehensive architecture document covering every repeatable process mapped to agents, skills, and automations. Includes .claude folder architecture, MCP servers, hooks, cost projections with /effort routing, security posture informed by real CVE data, and cross-tool strategy. Plus one production-hardened agent with cost controls, security audit, verification hooks, error recovery, and monitoring. Assembled across all sessions, finalized in Session 10.

Industry Tools, Not Toy Projects

Claude Code

Anthropic’s agentic coding tool. The primary environment for every session — hooks, subagents, skills, and configuration all happen here.

Agent SDK

TypeScript SDK for building standalone agents with tool execution, session persistence, compaction handling, and model routing.

MCP

Model Context Protocol for tool connectivity. Build MCP servers, evaluate security, and understand the protocol that connects the ecosystem.

Dispatch

Anthropic’s desktop orchestration layer for cross-device agent workflows, background task monitoring, and multi-agent coordination.

Claude Code Security

Enterprise/Team vulnerability scanning feature. Deep reasoning analysis that traces data flows, maps dependencies, and simulates attack paths.

Community Tools

Superpowers, Claude-Mem, Ralph Loop, Ruflo — ecosystem plugins you’ll evaluate, compare, and integrate into your workflows.

Prerequisites & What's Next

Prerequisites

This Course Unlocks

  • Coming soon — advanced agent development tracks

Ready to start learning?

Most people use 10% of Claude Code. Session 1 shows you the other 90%.

Join the waitlist
Free when we open — join the waitlist and you’re first in.