Council of High Intelligence

The council assigns a hard question to deliberately different analytical personas, keeps their first positions independent, forces direct disagreement, and returns a verdict that preserves unresolved questions, dissent, kill criteria, and the next concrete action.

Try a council

Claude Code users can install the plugin directly:

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

Then convene the full council, a faster panel, or a two-member dialectic:

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

For Codex, Gemini CLI, or OpenCode, clone once and use the matching installer flag:

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

./install.sh --codex-only
./install.sh --gemini-only
./install.sh --opencode-only

Restart the target client after installation. The command remains /council on every supported host.

Use it for the decision boundary

Good council questions have material downside, competing values, incomplete evidence, or an irreversible choice. Write down the decision, constraints, evidence, reversibility, and deadline before adding personas.

The field notes distinguish facts from inference, assumptions, and unknowns. They also make it harder to use a long deliberation as decoration for a decision already made.

When to use something smaller

• Use a direct answer or primary documentation for factual lookups.
• Run an experiment when the choice is cheap and reversible.
• Use --quick when cross-examination will not change the outcome.
• Use --duo when one tension matters more than broad coverage.
• Do not convene a council to manufacture support for a preferred answer.

Choose a mode

Mode	Shape	Use it when
Full	Independent analysis, cross-examination, final stance, synthesis	Stakes are high and competing frames need contact
Quick	Restate, rapid analysis, final positions	The decision needs breadth but not a full adversarial round
Duo	Opening positions, direct response, final statements	One polarity defines the decision

/council --full What is the right pricing model?
/council --quick --triad shipping Should we release today?
/council --duo --members torvalds,ada Is this abstraction worth it?

Named triads select three relevant lenses without assembling the whole council:

/council --triad strategy Where is our defensible advantage?
/council --triad risk What could make this launch irreversible?
/council --triad ai-product Which capability belongs in the product?

Available domains include architecture, strategy, ethics, debugging, risk, shipping, product, founder, ai, ai-product, ai-safety, decision, systems, uncertainty, design, economics, and bias. The canonical routing table lives in SKILL.md.

What the protocol protects

The full protocol has a fixed round budget. Members first restate the problem, analyze blind, cross-examine other positions, declare a final stance, and then enter synthesis. Enforcement checks look for premature agreement, repeated claims, missing dissent, and unsupported confidence.

Verdicts lead with what remains unresolved. A recommendation is paired with acceptable compromises, kill criteria, and one concrete next step. When the weighted tally remains split, the result returns that split to the user instead of turning it into prose consensus.

Evidence labels separate:

• FACT: directly supported by supplied or retrieved evidence;
• INFERENCE: follows from evidence but is not directly observed;
• ASSUMPTION: required for the argument and still unverified;
• UNKNOWN: missing information that could change the decision.

Track the outcome

A verdict is useful only if it can be checked later. Before acting, record the prediction, owner, review date, and evidence that would change the recommendation. At the checkpoint, mark the result confirmed, revised, reversed, or inconclusive instead of rewriting the original rationale.

The 18 lenses

Members are analytical instruments, not impersonation claims. Each persona has a grounding protocol, a method, known blind spots, and a structured response contract.

This is the beginning of the README. Read the rest at the original. Read the full README ↗