StackMap
Subscribe
Explore / council-of-high-intelligence
0xNyk

council-of-high-intelligence

/council: 18 AI personas deliberate your hardest decisions across multiple LLM providers — structured multi-round disagreement, confidence-weighted verdicts, one slash command.

3,571 320 Shell MITupdated yesterday
agentsskills
View on GitHubDispute this mapping →
Curator's take

Structured disagreement as a product: 18 personas with genuinely different priors argue your decision across providers (real model diversity, not one model roleplaying), through quick/standard/deep deliberation modes, ending in a confidence-weighted verdict. Its own README has a 'When Not to Use It' section — our kind of project. Best for irreversible, ambiguous calls where you'd otherwise ask three friends. NOT for anything with a checkable answer (deliberation theater costs real tokens), and a council is still only as wise as its training data — it widens perspective, it doesn't add ground truth.

Mapped by ShipWithAI editors · links verified
README.md

Council of High Intelligence

Council of High Intelligence

nyk.dev/oss · Brand kit

18 AI personas deliberate hard decisions. Structured disagreement, one command.

Lint Release License

Claude Code · Codex · Gemini CLI

Deliberation protocol: restate, analyze, attack, verdict

Table of Contents

Quickstart

Claude Code (plugin, recommended)

/plugin marketplace add 0xNyk/council-of-high-intelligence
/plugin install council@council-of-high-intelligence

Or via installer:

git clone https://github.com/0xNyk/council-of-high-intelligence.git
cd council-of-high-intelligence
./install.sh

Then in Claude Code:

/council Should we open-source our agent framework?
/council --quick Should we add caching here?
/council --duo Should we use microservices or monolith?

Codex

git clone https://github.com/0xNyk/council-of-high-intelligence.git
cd council-of-high-intelligence
./install.sh --codex

Gemini CLI

git clone https://github.com/0xNyk/council-of-high-intelligence.git
cd council-of-high-intelligence
./install.sh --gemini

The same /council commands work in all three hosts.

Why This Works

A single LLM gives you one reasoning path dressed up as confidence. Ask it a hard question and you get a fluent, structured, wrong answer. The council gives you structured disagreement instead.

  • Genuinely different perspectives. Polarity pairs force real tension: Socrates destroys assumptions, Feynman rebuilds from first principles. Multi-provider routing spreads members across Claude, OpenAI, Gemini, and Ollama, so the reasoning actually differs rather than putting one model in eighteen costumes.
  • Wrong questions caught early. The Problem Restate Gate makes every member reframe the question before analysis begins. When three members restate your question three different ways, the question was the problem.
  • An honest map of the gaps. Verdicts lead with Unresolved Questions and Recommended Next Steps rather than confident-sounding consensus. What the council cannot settle matters more than where it happens to agree.
  • Groupthink actively suppressed. Dissent quotas, novelty gates, and counterfactual prompts enforce disagreement. If agreement passes 70% too early, two members are conscripted to steelman the opposing view.

Why not just ask Claude directly? One prompt buys one model's confident best guess. The council runs 3 to 18 independent analyses from different intellectual traditions, forces them to attack each other's claims, and synthesizes a verdict that surfaces the disagreement instead of smoothing it

Continue your stack

What teams reach for next — and why each earns a place beside council-of-high-intelligence. Ranked by curator confidence.