From claude-council
Executes council queries by running the query pipeline across selected AI providers (Gemini, OpenAI, Grok, Perplexity), displays formatted responses verbatim, and generates a synthesis of consensus, divergence, and recommendations.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-council:council-executionThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
```bash
bash ${CLAUDE_PLUGIN_ROOT}/scripts/run-council.sh --providers=gemini,openai -- "Your question"
This outputs the path to the saved file (e.g., .claude/council-cache/council-1734567890.md).
Flag syntax: Use = with no spaces: --providers=gemini,openai
CRITICAL: Always place -- before the prompt to prevent prompt text containing dashes from being parsed as flags.
Use the Read tool to read the output file path returned by Step 1.
CRITICAL: Display the file content EXACTLY as written. Do NOT:
---)Simply copy-paste the entire file content into your response.
The file ends with a ## Synthesis header. Read
${CLAUDE_PLUGIN_ROOT}/prompts/synthesis.md and write your synthesis UNDER
that header following its structure (Consensus / Divergence / Recommendation)
and calibration rules.
After displaying the synthesis, tell the user:
(use this emoji 💾) Full output saved to
.claude/council-cache/council-TIMESTAMP.md(use the actual filename)
This lets them review the complete responses later.
The output file uses emoji prefixes to visually distinguish providers. Preserve this format when displaying results:
| Provider | Prefix |
|---|---|
| Gemini | 🟦 Gemini |
| OpenAI | 🔳 OpenAI |
| Grok | 🟥 Grok |
| Perplexity | 🟩 Perplexity |
npx claudepluginhub hex/claude-marketplace --plugin claude-councilSpawns parallel Claude subagents to query providers, evaluate response quality, and return structured insights with confidence ratings and blind spot analysis. For complex architectural decisions or with --agents flag.
Collects opinions from multiple AI agents via bash scripts and synthesizes a unified response. Activates on multi-perspective requests or via /agent-council.
Runs a configurable multi-LLM council with personas, budget caps, synthesis, veto gates, and optional implementation handoff via the orchestrate.sh runner.