Explore Code

When you want to try a risky architecture change in a research codebase without polluting your main branch, this handles the isolated exploratory work. It transplants modules, swaps backbones, adds LoRA layers, or stitches together low-risk migration ideas while keeping rollback records in explore_outputs/. The key constraint is that the researcher must explicitly authorize the exploration and accept that results are candidates, not verified contributions. It won't touch your trusted baseline or handle conservative debugging. Honest take: the discipline of treating exploratory code as explicitly provisional is rare and worth enforcing, especially in research repos where "just trying something" can erase weeks of careful provenance.

Install to Claude Code

npx -y skills add lllllllama/rigorpilot-skills --skill explore-code --agent claude-code