tags
Click a filter to scope results to projects or posts.
Claude Code remembers. Between sessions, across days, across machines — through `CLAUDE.md` files and the auto-memory system. Used well, it stops asking the same questions and starts knowing your project. Used poorly, it bloats context and drifts. This post covers the mental model and the practical patterns.
MCP — the Model Context Protocol — is the standard interface for plugging external tools and data sources into AI agents. In Claude Code, MCP servers turn the CLI into a hub that can query your database, search your Notion, browse your Linear, control your browser, and run any tool you can wrap in a process.
Subagents in Claude Code are independent AI workers spawned by the main agent to handle scoped tasks — code search, planning, security review, status-line setup. They run with their own context window, their own tool allowlist, and return a single summary. This post explains when to use them, how to author your own, and the patterns that work.
Hooks let you run shell commands automatically at specific points in Claude Code's lifecycle — before a tool runs, after an edit, when a session starts, when Claude stops. They are the harness's escape hatch for enforcing conventions, running formatters, sending notifications, and gating risky actions.
Claude Code is keyboard-first. Knowing the shortcuts cuts friction dramatically — interrupt a runaway agent, paste multi-line prompts, scroll diffs, switch modes, and queue messages without ever reaching for the mouse. This is the cheat sheet.
Slash commands are Claude Code's control surface — typed commands that change session state, run skills, manage memory, and trigger custom workflows. This post walks through every built-in slash command and shows how to author your own project- or user-level commands.
Claude Code is Anthropic's official command-line agent — a terminal-native AI pair programmer that reads your repo, edits files, runs tests, and ships PRs. This guide walks through installation, first-run authentication, project setup with CLAUDE.md, and the day-to-day workflow that makes it stick.