Part 1
Context is the budget
Claude Code spends a fixed slice of the window before you type a word. Most sessions that go badly are budget failures, not model failures.
Guided series · 6 parts
Six parts on what actually changes how a session goes: context, commands, MCP, hooks, sub-agents, and skills.
Filed under AI EngineeringReading order
Part 01 – 06
Part 1
Claude Code spends a fixed slice of the window before you type a word. Most sessions that go badly are budget failures, not model failures.
Part 2
A slash command is a prompt you got tired of retyping. What changes when it becomes a file is that it can be reviewed, shared, and wrong in only one place.
Part 3
A server gives Claude something new to do, not something new to know. Which is why adding one never fixes a model that keeps forgetting your conventions.
Part 4
A CLAUDE.md rule is a request. A hook is shell the harness runs regardless, which makes it the only place to put a rule you cannot afford to have ignored.
Part 5
Delegating does not make the model smarter. It buys a clean context window and charges you visibility, and every good use of a sub-agent follows from that.
Part 6
A skill that is always in context is a memory file with extra steps. The engineering is in the description field and in everything you keep out of SKILL.md.