All writing

Guided series · 6 parts

Claude Code in practice

Six parts on what actually changes how a session goes: context, commands, MCP, hooks, sub-agents, and skills.

Filed under AI Engineering

Reading order

Explore the series

Part 01 – 06

Part 1

Boluwaji Joshua AdedigbaAI Engineering

AI Engineering

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.

10 min readRead article

Part 2

Boluwaji Joshua AdedigbaAI Engineering

AI Engineering

Custom commands for work that repeats

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.

9 min readRead article

Part 3

Boluwaji Joshua AdedigbaAI Engineering

AI Engineering

MCP servers are capabilities, not knowledge

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.

10 min readRead article

Part 4

Boluwaji Joshua AdedigbaAI Engineering

AI Engineering

Hooks run whether the model agrees or not

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.

10 min readRead article

Part 5

Boluwaji Joshua AdedigbaAI Engineering

AI Engineering

Sub-agents are a context decision

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.

10 min readRead article

Part 6

Boluwaji Joshua AdedigbaAI Engineering

AI Engineering

A skill is a loading strategy with some knowledge attached

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.

9 min readRead article