Interesting read! I might replicate with my two whippets. What’s their inter-rater reliability?

You also should continue with a swap of the hands; randomize which one is in the left and record the results to see if the left bias is real

Sequential code review with fresh agent contexts. Each pass runs in an independent subagent, ensuring unbiased analysis that catches issues other passes might miss. A single code review pass catches ~60-70% of issues. Running multiple independent passes with fresh contexts significantly increases coverage. This plugin automates that workflow. Build for Claude Code.

Great point - I wrote a docker wrapper for convenience ultimately but you’re right, I’ll rewrite the readme with that in mind.

CLI tool that generates ML-KEM-768 + X25519 hybrid age keys and produces single-page printable HTML backups with QR codes. Designed for SOPS disaster recovery. Runs in a hardened Docker container (no network, read-only fs, no capabilities, distroless image). Written in Go.