What Claude Code stores on your machine (and how to see it)

#ai #typescript #opensource #devtools

Claude Code keeps a lot of data in ~/.claude/ that most people never look at. I wanted to know what was there, so I built a scanner.

On my machine it found:

76 persistent memory files across 10 projects
4,445 session transcripts totaling 1.8GB
2.2GB total data footprint

The memory files are markdown with frontmatter, organized by type: what Claude thinks your role is, feedback you've given, project context, reference links. It remembers more than you'd expect.

The tool

npx agentlens scan

No API keys, no accounts. Reads local files only.

Scan commands

agentlens memory — what Claude remembers about you
agentlens costs — token usage by model and project
agentlens features — active feature flags on your account
agentlens sessions — transcript stats and tool usage
agentlens privacy — total data footprint

Action commands

agentlens clean --dry-run — preview which memories would be deleted
agentlens redact — find secrets that leaked into memory files
agentlens diff save — snapshot current state, then diff show to compare later
agentlens export — dump everything to portable JSON

What surprised me

The sensitivity scanner flagged 13 potential secrets in my memory files. Most were false positives (the word "token" in pricing discussions), but some were file paths and references I wouldn't want in a shared context.

Session transcripts contain everything: every file you read, every bash command you ran, every edit you made. If you've ever read a .env file during a Claude Code session, it's in there.