A skill that convenes a panel of CLI-based AI agents (Claude Code, Codex, Gemini CLI) to deliberate on engineering problems through structured multi-stage discussion, peer review, and synthesis
This repository also configures its own agents. See what agent-council tells them →
Skill Claude Code
Convene a panel of CLI-based AI agents (Codex, Gemini) to deliberate on a question. Each agent answers independently, then you synthesize the council's verdict as chairman. Use for architecture decisions, code review, debugging hypotheses, or any question where diverse perspectives add value.
Skill Claude Code
Ambient awareness for Agent Council. Detects moments where convening a multi-model council would genuinely help and suggests the right command. Never interrupts. Never nags. Just a quiet tip at the right moment.
Skill Claude Code
List all past Agent Council sessions for the current project. Shows session ID, mode, agent count, and question for each.
Skill Claude Code
Nudge a specific agent to reconsider its opinion based on a corrected assumption. Sends the original question + response + correction to one agent and saves the updated opinion alongside the original for comparison.
Skill Claude Code
Record the outcome of a past Agent Council decision. Was the council right? Builds calibration data over time to learn which models are best at what.
Skill Claude Code
Replay a past Agent Council session in the terminal. Shows the full deliberation: question, each agent's opinion, and the chairman's synthesis.
Skill Claude Code
Revisit a past Agent Council decision with current codebase context. Re-runs the same question through the council and shows a side-by-side comparison of what changed. Use for living decisions.
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: