Council Execution logo

Council Execution

Community
hex
council-execution

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.

Overview

Publisherhex
Repositoryclaude-council
Skill namecouncil-execution
Stars
866
Forks
106
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by hex on GitHub. Read the source before you install it.

Installation

Install the Council Execution AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/hex/claude-council/tree/main/skills/council-execution
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/hex/claude-council.git /tmp/claude-council
mkdir -p .claude/skills
cp -r /tmp/claude-council/skills/council-execution .claude/skills/council-execution
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Council Execution in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Council Execution on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Council Execution is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Council Query Execution

Step 1: Run Query and Save to File

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

Pass only the flags the user asked for. Never add --no-pane, --quiet, --no-cache or --no-auto-context on your own judgment; they are the user's to choose, and the script already skips a pane that cannot open.

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.

Step 2: Read and Display the Output VERBATIM

Use the Read tool to read the output file path returned by Step 1.

If the file's first line is <!-- council: round 1 was shown in the pane -->, the user already read every round-1 answer in the streaming pane. Do not reprint them. Instead, output one line per provider in round 1, taken from its ## header (name, role, model, and any fallback note) followed by answered or the Error: line under it. When the header says the seat fell back, add the > <provider>: <reason> line printed under it. Then display VERBATIM the rest of the file from its ## Round 2 heading, or from ## Synthesis when there is no round 2 (debate rebuttals never reach the pane), and continue with Step 3 under the ## Synthesis header. Without that first line, display the whole file as below.

CRITICAL: Display the file content EXACTLY as written. Do NOT:

  • Reformat or reinterpret any text
  • Add your own headers or structure
  • Summarize or abbreviate responses
  • Skip any lines including separator lines (---)

Simply copy-paste the entire file content into your response.

Step 3: Complete the Synthesis Section

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.

Step 4: Notify User of Saved Output

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.

Output Format: Provider Names

Each provider section opens with a ## ● <Provider> (<role>) - <model> header, where the dot is the provider's colour swatch. Display the header as written.

Frequently asked questions

What does the Council Execution AI skill do?

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.

Why use Council Execution on TypingMind?

Because you install it once and use it with any model. Council Execution is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Council Execution in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hex/claude-council/tree/main/skills/council-execution. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Council Execution?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Council Execution?

As many as you like. As long as a model supports skills, you can use Council Execution with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Council Execution AI skill free?

Yes. It is published on GitHub by hex under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇