Skip to content

sentry01/agentcouncil

v2.0.0MIT

Multi-model council for Copilot CLI. Three subagents on different model families (Anthropic, OpenAI, Google) answer independently, then build on each other or attack the leading answer before an orchestrator writes the final result. Ships the agentcouncil skill and the AgentCouncil agent.

GitHubOpen Website
agentcouncil

Use when the user asks for a council, debate, brainstorm, stress-test, or second opinions from multiple AI models, or when a high-stakes decision, architecture choice, security review, or comparison of competing approaches should be checked by more than one model family. Trigger prefixes: "council:", "debate:", "brainstorm:", "stress-test:", "adversarial council:", "collaborative council:", "quick council:", "full council:".