Your AI coding agent is running at 30% capacity. This course installs Everything Claude Code — 28 agents, 125 skills, 60 commands — and teaches you to use rules, hooks, subagents, MCPs, and token optimization to ship 10x faster.
What You Build
A fully tuned AI agent harness with rules, hooks, skills, MCPs, and a feature built end-to-end using the full system
Sections
Lessons
Estimated
Concepts
Spec-Driven Development
Stop writing code and start writing specs. Learn to describe exactly what you want in a structured format that AI agents execute perfectly — frontend, backend, and tests in parallel. Ship features the same day you think of them.
Building Skills, Agents & Rules
Skills are the Cambrian explosion of software engineering. Learn to build SKILL.md files, custom subagents, rules, hooks, and slash commands that make your AI harness uniquely powerful. Auto-generate skills from git history and evolve them with instinct-based learning.
Dev Jordan
walkthrough · casual
First 5 lessons are free (36% of the course). No login required.
AI Coding Agents
Autonomous software agents (Claude Code, Stripe Minions, Gas Town Polecats) that read codebases, write code, run tests, and open pull requests with minimal human interaction during execution.
Skills
Markdown files that tell AI models how to perform specific tasks, optionally accompanied by extra documents and pre-written scripts. Skills extend what agents can do.
Backpressure
Automated feedback systems (type checkers, linters, test suites, build systems) that keep agents on track. Without backpressure, you review trivial mistakes. With it, agents self-correct.
Self-Improving Factory
A closed-loop system where agents monitor user feedback, analytics, A/B tests, error logs, and production data to populate the backlog without human curation.
Blueprint Architecture
Hybrid systems combining deterministic code nodes (run linters, push changes) with agentic subtasks (implement feature, fix CI). A pipeline with guardrails, not full autonomy.
MCP (Model Context Protocol)
A standard protocol connecting AI systems with external tools and data sources. Enables agents to access specialized functions and services through a unified interface.