Plugin Claude Code
William Zujkowski's Claude Code plugin marketplace — hosts nexus-agents.
Plugin Claude Code
William Zujkowski's Claude Code plugin marketplace — hosts nexus-agents.
Plugin Claude Code
Intelligent orchestration platform for AI coding tools — routes tasks to the best model, learns from outcomes, and enforces quality through multi-model consensus. 47 MCP tools for agent management, research, memory, consensus voting, codebase intelligence, and a full dev pipeline.
Agent Claude Code
Human-facing review personas for the Agent tool's subagenttype parameter (Claude Code) or any equivalent subagent invocation surface. These are not the same as the voter-pipeline experts in agents/ at the repo root.
Agent Claude Code
Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.
Agent Claude Code
Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.
Agent Claude Code
QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.
Cursor rule Cursor
Federated to AGENTS.md — this repo authors all agent-facing rules in a single canonical surface.
Instructions file CodexOpenCode
AGENTS.md instructions for nexus-substrate/nexus-agents, covering agents.md — nexus-agents, mission, prime directive, development disciplines and default working mode.
Instructions file
Claude Code instructions, protocols, agent behavior, governance rules, and canonical paths.
Instructions file Gemini CLI
Gemini CLI instructions for nexus-substrate/nexus-agents: This repo follows the AGENTS.md federation (#2764 / #3446): AGENTS.md is the single source of truth for project conventions, rules, and agent guidance. It's the canonical, harness-neutral superset; harness-specific entry points redirect to it rather than…
Agent
Architecture expert for system design, design patterns, and architectural trade-offs.
Agent
Code expert for code review, refactoring, and multi-language best practices.
Agent
Data visualization expert for chart selection, interactive dashboards, WCAG-AA color palettes, and ECharts/D3 code.
Agent
DevOps/SRE expert for CI/CD pipelines, infrastructure-as-code, observability, and reliability engineering.
Agent
Documentation expert for technical writing, API docs, README authoring, and docs-content governance.
Agent
Infrastructure expert for bare-metal, out-of-band (iDRAC/iLO), networking, and physical-server operations.
Agent
Product management expert for requirements gathering, user stories, acceptance criteria, and scope decisions.
Agent
Quality assurance expert for code review, requirements verification, regression analysis, and standards compliance.
Agent
Research expert for literature review, prior-art analysis, and evidence-based recommendations.
Agent
Security expert for OWASP-aware code review, threat modeling, and vulnerability analysis.
Agent
Testing expert for TDD, test strategy, coverage analysis, and edge-case identification.
Agent
UX design expert for interaction design, usability analysis, accessibility, and user-journey mapping.
Hook
Runs before the agent uses a tool for [object Object] and [object Object] tool calls, executing fitness-gate.sh and secret-scan.sh (2 commands). From nexus-substrate/nexus-agents.
Skill Claude CodeCodex
Design stable, hard-to-misuse interfaces — REST endpoints, MCP tool schemas, module boundaries, type contracts. Apply when defining new surfaces or evolving public ones. Triggers on "API design", "interface", "schema", "contract", "module boundary", "type design".