multi-agents operating system layer on top of Claude Cod: multi-agent engineering team for Claude Code, with hook-enforced protocol, adversarial review, Bayesian trust calibration, dynamic specialist hiring, an optional parallel cognitive layer, and a self-improving meta-cognitive loop
1 file for Claude Code: claude-nexus-hyper-agent-team CLAUDE.md — 9,311 tokens loaded in every session.
CLAUDE.md C 9,311 tok These files are asiflow/claude-nexus-hyper-agent-team's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.