vardoger
dstrupl/vardogerPlugin
vardoger personalizes Claude Code by analyzing your own conversation history and turning recurring patterns into tailored rules. How it works: the plugin's `analyze` skill calls the `vardoger` CLI, which reads your local `~/.claude/projects/` session files in batches. Claude summarizes each batch for behavioral signals (tools you prefer, libraries you use, coding conventions you follow, mistakes you don't want repeated), then synthesizes the summaries into a single personalization that lands in your rules file. Re-running refreshes the personalization as your history grows. Everything runs on your machine — conversations never leave your disk, there is no server or account, and the output is plain Markdown you can edit or delete. The same CLI also supports Cursor, Codex, and OpenClaw, so the personalization stays consistent across assistants if you use more than one.
Why this score
Popularity score: 50/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
Security
Scanned Nov 4, 2026 at commit f813e9ca00a3, with Cisco's open-source skill-scanner.
None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Nothing from another maker does quite the same job yet.