Question 1

How do I let Claude take notes about my project without writing CLAUDE.md myself?

Accepted Answer

Auto memory is the second persistence mechanism alongside CLAUDE.md — but you don't write it, Claude does. Here's how to find it, audit it, and decide which mechanism a given fact belongs in.

Question 2

How do I let Claude work autonomously without approving every command?

Accepted Answer

Auto mode replaces permission prompts with a background classifier that blocks anything dangerous and lets routine work through. It's narrower than bypassPermissions, available on Max/Team/Enterprise/API only, and quietly drops some of your existing allow rules on entry.

Question 3

How do I get Claude to react to a Sentry alert while I sleep?

Accepted Answer

Channels are MCP servers that push events into your already-running Claude Code session — webhooks from CI or Sentry, DMs from your phone, anything that can speak HTTP. Here's the webhook-receiver pattern end to end, plus the sender-gating footgun that bites people.

Question 4

How do I connect Claude Code to my database via MCP?

Accepted Answer

Wire up the official Postgres MCP server in read-only mode so Claude can query schemas and inspect rows without risking writes.

Question 5

How do I run my first Claude Code session?

Accepted Answer

Install Claude Code, open it inside an existing repo, and walk through the loop you'll use every day after.

Question 6

How do I run my formatter automatically after Claude edits a file?

Accepted Answer

A PostToolUse hook on Edit and Write runs prettier (or any formatter) so Claude's output matches your house style.

Question 7

When should I delegate work to a subagent instead of doing it inline?

Accepted Answer

Subagents are good for noisy lookups and for protecting your main context window. They are bad for anything where you'd want to ask follow-ups.

Question 8

Which Claude model and effort level should I use in Claude Code?

Accepted Answer

Default to Opus 4.7 at xhigh effort. Drop to Sonnet for routine work, raise to max only when xhigh hits a wall, and never switch mid-session unless you mean to pay for it.

Question 9

Which Claude code review tool should I actually use?

Accepted Answer

Three reviewers ship inside Claude: a single-pass local /review, a cloud-sandbox multi-agent /ultrareview, and a GitHub App that runs on every PR. They cost different amounts, run in different places, and answer different questions. Here's the picking guide and the per-tool footguns.

Question 10

How do I make Claude plan before it edits code?

Accepted Answer

Use planning mode (or just ask) so Claude writes the plan, you approve it, and only then does it touch files.

AI

Getting started

Coworking patterns

Slash commands

Hooks

Subagents

MCP servers

Real session walkthroughs