Claude Code history: onboarding an engineer

How does someone new find out why this code was written this way?

Why this is hard

A new engineer inherits decisions, not just code. When a large share of the codebase was written with AI, the reasoning lives in conversations rather than in commit messages — and those conversations are on other people's laptops, if they still exist.

What Claude Code specifically does to you here

Transcripts record the tool calls as well as the conversation, so a session shows which files were touched and why — genuinely good onboarding material. It is also the material most likely to be missing, because a new joiner arrives months after the sessions that shaped the code.

ls -lt ~/.claude/projects/*/*.jsonl | tail -3

Where Claude Code keeps this in the first place: ~/.claude/projects/<project>/<session>.jsonl. Transcripts older than 30 days are deleted by default, and nothing tells you it is happening.

What a working answer looks like

A working answer means the reasoning behind a file is reachable from the file, by someone who was not there when it was written.

Start by measuring what you have. npx promptwake doctor reports what every AI tool on the machine is holding and how much of it sits inside a deletion window — no account, writes nothing, sends nothing anywhere. If the conclusion is that the record should not depend on one laptop, that is what PromptWake captures: prompt, response and the resulting diff, local by default and synced into a shared timeline on the paid tiers.