deep-execution
Executes agent-enhanced council queries as one Workflow of parallel Claude analyst agents that each query a provider, evaluate response quality, ask follow-up…
Executes council queries by running the query pipeline across selected AI providers (Gemini, OpenAI, Grok, Perplexity), displaying formatted responses verbatim, and generating a synthesis of consensus, divergence, and recommendations. Invoked by the ask command during standard
$ npx -y skills add hex/claude-council --skill council-execution --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/council-executionContext preview
The summary Claude sees to decide when to auto-load this skill.
Executes council queries by running the query pipeline across selected AI providers (Gemini, OpenAI, Grok, Perplexity), displaying formatted responses verbatim, and generating a synthesis of consensus, divergence, and recommendations. Invoked by the ask command during standard
name: council-execution description: Executes council queries by running the query pipeline across selected AI providers (Gemini, OpenAI, Grok, Perplexity), displaying formatted responses verbatim, and generating a synthesis of consensus, divergence, and recommendations. Invoked by the ask command during standard (non-agent) council queries.
bash ${CLAUDE_PLUGIN_ROOT}/scripts/run-council.sh --providers=gemini,openai -- "Your question"This outputs the path to the saved file (e.g., `.claude/council-cache/council-1734567890.md`).
**Flag syntax**: Use `=` with no spaces: `--providers=gemini,openai`
**CRITICAL**: Always place `--` before the prompt to prevent prompt text containing dashes from being parsed as flags.
**Run this Bash call with `timeout: 600000`** (ten minutes). The Bash tool's two-minute default is shorter than a slow council round, and inside tmux a provider failure makes the streaming pane offer the user a retry for `COUNCIL_RETRY_WAIT` seconds (default 45) and then runs another provider round if accepted. A call cut off mid-run loses the whole transcript, the answers that did arrive included.
Use the **Read tool** to read the output file path returned by Step 1.
**CRITICAL**: Display the file content EXACTLY as written. Do NOT:
Simply copy-paste the entire file content into your response.
The file ends with a `## Synthesis` header. Read `${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 |
A Claude Code plugin that consults multiple AI coding agents in parallel and shows you their answers side-by-side.
Repo: hex/claude-council
Executes agent-enhanced council queries as one Workflow of parallel Claude analyst agents that each query a provider, evaluate response quality, ask follow-up…
Runs a local council when no external AI providers are configured. Spawns N independent Claude subagents (one per role, blind to each other) that each answer…
Adds new AI providers to claude-council, configures provider API settings, troubleshoots provider connections, and documents the provider script interface.…