bench-repro
01Skill Claude CodeCodex
How to reproduce and grade a bench task or A/B arm for moss capability work.
not rated 143 5d ago A 20 tokens
original MIT
This repository also configures its own agents. See what moss tells them →
Skill Claude CodeCodex
How to reproduce and grade a bench task or A/B arm for moss capability work.
Skill Claude CodeCodex
How to make code changes in the moss repo — read-before-edit, minimal diffs, verify with real runs.
Skill Claude CodeCodex
How to run writable sub-agents in isolated git worktrees and merge their lease patches.