Command Claude CodeOpenCode
Adversarial debate with blind judges until convergence.
Research-first Agent Skill that runs long-horizon paper pipelines with evaluator gates, heartbeat watchdogs, resume controls, and manifest cleanup.
This repository also configures its own agents. See what autoresearch-paper tells them →
Command Claude CodeOpenCode
Adversarial debate with blind judges until convergence.
Command Claude CodeOpenCode
Layered regression stability gate: capture baseline behavior on the base ref, diff the candidate, verdict STABLE/UNSTABLE before you push.
Command Claude CodeOpenCode
Generate edge cases across 12 dimensions from a seed scenario.
Command Claude CodeOpenCode
STRIDE + OWASP security audit with red-team adversarial personas.
Command Claude CodeOpenCode
Ship anything through 8 phases: checklist, dry-run, deploy, verify.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: