Use Explanatory and Learning Modes to Understand Your Codebase
Claude Code isn't just for getting things done. Two built-in output styles turn it into a coding tutor that explains its decisions as it works.
Switch styles via /config and select Output style, or set it directly in .claude/settings.local.json:
{
"outputStyle": "Explanatory"
}
The two teaching modes are:
Explanatory: Claude completes your engineering tasks normally but adds "Insights" between steps, explaining implementation choices and codebase patterns it noticed. Great for onboarding to an unfamiliar repo or learning why certain patterns exist.
Learning: Collaborative, learn-by-doing mode. Claude adds insights like Explanatory mode, but also places TODO(human) markers in the code for you to fill in. You implement small, strategic pieces yourself while Claude handles the rest.
The default style is the standard engineering-focused prompt, and these modes completely replace the parts of the system prompt specific to efficient output and coding. Changes take effect at the start of the next session (not mid-conversation) so that prompt caching stays effective.
Output styles sit above CLAUDE.md in the hierarchy: they modify the system prompt itself, whereas CLAUDE.md content arrives as a user message after it.
# Check or change your current output style
/config
Use Explanatory when you want to ship and learn; use Learning when you want to build the skill yourself.
Log in to leave a comment.
Set up Claude Code as an automated reviewer in your CI pipeline — on every pull request, it reads the diff, checks for bugs, security issues, missing tests, and convention violations, then posts its findings as a PR comment. Your human reviewers get a head start because the obvious issues are already flagged before they look.
Before deploying, tell Claude to read your project — migrations, environment variables, queue workers, scheduled tasks, caching, third-party integrations — and generate a deployment checklist that's specific to your app. Not a generic "did you run migrations?" list, but one that knows YOUR infrastructure and catches the things YOUR deploy can break.
Instead of writing a README from memory or copying a template, tell Claude to read your project and generate one that's actually accurate — real setup instructions from your config, real architecture from your directory structure, real API examples from your routes, and real prerequisites from your dependency files.