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
This repository also configures its own agents. See what claude-nexus-hyper-agent-team tells them →
asiflow/claude-nexus-hyper-agent-team
Agent Claude Code
Use this agent as a distinguished Python/FastAPI language authority and domain expert for peer-review-level code review. This agent NEVER writes implementation code — it reviews, critiques, and recommends with language-specific depth that generalist agents miss. Covers async mastery, FastAPI deep patterns, Pydantic…
asiflow/claude-nexus-hyper-agent-team
Agent Claude Code needs its repo
Use this agent as the team's Deep Domain Research + Prompt Synthesis + Validated Hiring Execution engine — it takes a YAML requisition from talent-scout, conducts evidence-grade domain research (WebSearch + WebFetch with citation trail), mines inherited scar-tissue from adjacent existing agents' memory, synthesizes a…
asiflow/claude-nexus-hyper-agent-team
Agent Claude Code
Use this agent as the team protocol enforcer and session auditor — dispatched at SESSION START and SESSION END to ensure the 32-agent team follows its own protocols. Audits CTO delegation compliance, gate completion, memory utilization, orchestrator usage, and Pattern F closure. Produces session health metrics and…
asiflow/claude-nexus-hyper-agent-team
Agent Claude Code
Use this agent for continuous team-coverage gap detection and structured hiring-requisition drafting — it senses when the user's active work is drifting into a domain the team does not specialize in, composes a 5-signal weighted confidence score, and (only with session-sentinel co-sign at ≥90% confidence) drafts a…
asiflow/claude-nexus-hyper-agent-team
Agent Claude Code
Use this agent as a distinguished Test Architecture and Engineering authority. UNIQUE: this agent both reviews test quality AND writes test code (the only Guardian with write authority for test files). Covers test strategy design, unit/integration/contract/E2E test creation, performance testing, chaos engineering…
asiflow/claude-nexus-hyper-agent-team
Agent Claude Code
Use this agent as a distinguished TypeScript/React/Next.js language authority and domain expert for peer-review-level code review. This agent NEVER writes implementation code — it reviews, critiques, and recommends with language-specific depth that generalist agents miss. Covers type system mastery, React 19+…
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: