Plugins

Compare des agents de codage dans des worktrees Git isolés avec validation déterministe, notation et application explicite du gagnant.

Run the same prompt through every model you have, and see the difference without squinting.

Evidence-first multi-model coding comparison workbench for DeepSeek Harness

Evidence-backed Skill self-evolution for DeepSeek Harness: redacted trajectory learning, quarantined proposals, arena validation, canary monitoring, automatic rollback.