# 0xNyk/council-of-high-intelligence

Structured multi-perspective deliberation for hard decisions. Run full councils, focused triads, or duo debates across Claude Code, Codex, Gemini CLI, and OpenCode.

Repository: https://github.com/0xNyk/council-of-high-intelligence
Canonical: https://ross.abutalabs.com/products/council-of-high-intelligence
Homepage: https://www.nyk.dev/oss/council-of-high-intelligence
Language: Shell
License: MIT
License Family: permissive
Topics: ai-agents, claude-code, decision-making, deliberation, multi-llm, prompt-engineering, agent-skill, codex, gemini-cli, llm-routing, multi-agent-systems, open-source, opencode, structured-debate
Last push: 2026-08-24T05:53:54+00:00

## Health v2 (maintenance only)
Score: 75/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 79, longevity 13
- inputs: {"age_days": 184, "days_push": 9, "days_rel": 60, "gap_med": 47.5, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4162, forks 78 (observed 2026-08-28T04:08:36.589027+00:00)

## What it is
A shell-based skill/plugin that runs structured multi-persona deliberation for hard decisions across AI coding agents like Claude Code, Codex, Gemini CLI, and OpenCode. It assigns questions to distinct analytical personas, forces independent positions and direct disagreement, and synthesizes a verdict preserving dissent and next actions.

## Use cases
- run a structured debate between multiple AI personas on a hard decision
- get multi-perspective analysis before an irreversible technical choice
- compare microservices vs monolith with independent AI viewpoints
- install a deliberation skill for Claude Code
- force AI agents to disagree and cross-examine each other
- surface dissent and kill criteria for a high-stakes decision
- run multi-LLM deliberation across Codex and Gemini CLI

## When to choose
- you face a high-stakes, hard-to-reverse decision with competing values or incomplete evidence
- you already use Claude Code, Codex, Gemini CLI, or OpenCode and want structured deliberation inside them
- you want dissent, unresolved questions, and kill criteria preserved rather than a single confident answer

## When to avoid
- you need a quick factual lookup or a cheap, reversible choice
- you want validation for a decision you have already made
- you need a production multi-agent orchestration framework rather than a deliberation skill

## Facets
- artifact type: plugin
- maturity: active
- function: agent-framework, prompt-engineering, llm-inference, cli
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: cli, cross-platform
- tags: multi-agent-systems, structured-debate, claude-code-plugin, decision-making, multi-llm, deliberation, agent-skill, ai-agents, shell

## Member repositories
- 0xNyk/council-of-high-intelligence (main) score 75

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:36.589027+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:22:48.313299+00:00, confidence not recorded.
  - readme: https://github.com/0xNyk/council-of-high-intelligence (fetched 2026-08-28T04:08:36.589027+00:00, sha c5e0748c680b)
  - homepage: https://www.nyk.dev/oss/council-of-high-intelligence (fetched 2026-08-29T09:13:29.422661+00:00, sha 2846ffb6516f)
  - site_page: https://www.nyk.dev/about (fetched 2026-08-29T09:13:29.434699+00:00, sha 148c0f5ce7c4)
  - site_page: https://www.nyk.dev/oss/awesome-hermes-agent (fetched 2026-08-29T09:13:29.432469+00:00, sha 8a107f89d04a)
- Data as of 2026-08-30T08:39:29.467469+00:00.