Multi-agent framework for Claude Code: tier-aware acceptance, filesystem-isolated adversary review, cross-family second-opinion via Codex MCP, human as supreme judge
npx skills add ElPinus/agentic-workflowMulti-agent framework for Claude Code: tier-aware acceptance, filesystem-isolated adversary review, cross-family second-opinion via Codex MCP, human as supreme judge
Source: https://github.com/ElPinus/agentic-workflow
Discovered from GitHub repositories pushed in the last 24 hours for agent skills, Claude/Codex/Gemini workflows, MCP tooling, and adjacent AI-agent automation.
Provide community-built automation skills for OpenClaw agents to enhance task handling through browser and API integrations.
Tandem is the authority layer for AI-first work: runtime authority for agents, tools, memory, approvals, and audit trails.
AI-powered multi-agent orchestration and autonomous workflow architecture intelligence.
Autonomous agent system for long-running projects — mission-driven, multi-agent pipelines, self-evolving skills.
Custom ArkClaw/OpenClaw skills for lobster fitting and Feishu bitable workflows (v2: streamlined fields, voice ASR protocol, project-level binding config)
Meta-framework that scaffolds local-only Obsidian second-brain vaults driven by Claude Code skills