council-of-high-intelligence: Instructions file for Claude Code

CLAUDE.md

council-of-high-intelligence CLAUDE.md is an instructions file for Claude Code, Codex from 0xNyk/council-of-high-intelligence. It costs 626 tokens per session, scanned A, original, MIT.

Repository guidance for a multi-agent review system called Council of High Intelligence, including coordinator protocols, member personas, provider settings, demos, and validation scripts.

In plain words
What is it for?
Use it when modifying council behavior, agent persona files, installation settings, model routing, demonstrations, or validation checks.
Why use it?
It keeps the different coordinator versions and agent roles consistent when the council's deliberation process changes.

Instructions file for Claude CodeCodex

Written for Codex and Claude Code: reads ~/.codex or $CODEX_HOME, but also the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions Codex; mentions Gemini CLI.

This is 0xNyk/council-of-high-intelligence's own configuration. It tells Claude Code and Codex how to work on council-of-high-intelligence itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything council-of-high-intelligence configures →

About the project

Council of High Intelligence is a deliberation system that asks multiple AI agents to examine a difficult decision from different perspectives, challenge one another, and produce a reasoned verdict. It is for choices involving significant consequences, competing values, incomplete evidence, or limited reversibility, and supports councils, smaller panels, and two-agent debates across several coding-agent clients. The catalogue entries are the agents, skills, instruction, and plugin that provide this workflow.

0xNyk/council-of-high-intelligence · 4,228 stars · on GitHub · nyk.dev

Reuse

Borrowing it

Nothing to install: this file belongs to 0xNyk/council-of-high-intelligence. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/0xNyk/council-of-high-intelligence/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/0xNyk/council-of-high-intelligence

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for council-of-high-intelligence CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/0xnyk/council-of-high-intelligence/claude-md/github.svg)](https://agentmods.dev/instructions/0xnyk/council-of-high-intelligence/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/0xnyk/council-of-high-intelligence/claude-md"><img src="https://agentmods.dev/badge/instructions/0xnyk/council-of-high-intelligence/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for council-of-high-intelligence CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/0xnyk/council-of-high-intelligence/claude-md"><img src="https://agentmods.dev/badge/instructions/0xnyk/council-of-high-intelligence/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 626 This file is loaded in full into every session.
When invoked 626 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00626 $0.00626
Opus 5 $0.00313 $0.00313
Sonnet 5 $0.00125 $0.00125
Haiku 4.5 $0.00063 $0.00063

Measured 12d ago against content hash ead6bbf72867, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

council-of-high-intelligence CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Council of High Intelligence

Architecture

  • SKILL.md — coordinator protocol with execution sequence, modes, and verdict templates (canonical — feature changes land here first, then get mirrored)
  • SKILL.codex.md — Codex-specific council coordinator protocol (compressed mirror of SKILL.md)
  • SKILL.gemini.md — Gemini CLI-specific council coordinator protocol (compressed mirror of SKILL.md)
  • SKILL.opencode.md — opencode-specific council coordinator protocol (mirror of SKILL.md)
  • agents/council-*.md — 18 member personas with YAML frontmatter
  • install.sh — installs to ~/.claude/, optionally ~/.codex/skills/council/, ~/.gemini/extensions/council-of-high-intelligence/, and ~/.config/opencode/
  • configs/ — provider/model routing templates
  • demos/ — example prompts and scoring rubric
  • scripts/ — validation checklist

Conventions

Agent files

  • Section order: Identity → Grounding Protocol → Analytical Method → What You See → What You Miss → When Deliberating → Output Format (Council Round 2) → Output Format (Standalone)
  • Grounding Protocol appears immediately after Identity (LLMs weight earlier instructions more heavily)
  • "What You See" and "What You Miss" sections: ≤3 sentences each
  • Every agent gets a Council Round 2 output format with structured headers (Disagree, Strengthened by, Position Update, Evidence Label)

SKILL.md

  • Coordinator instructions are an execution sequence with numbered STEPs and [CHECKPOINT]/[VERIFY] markers
  • Three modes: full (3-round), quick (2-round), duo (dialectic)
  • Reference tables (triads, profiles, polarity pairs) are above the execution sequence, not mixed in

Testing

  • Always run ./scripts/council-simulation-checklist.sh after changes
  • Always run ./install.sh --dry-run to verify installation
  • When changing Codex installation, also run ./install.sh --dry-run --codex
  • When changing Gemini installation, also run ./install.sh --dry-run --gemini
  • When changing opencode installation, also run ./install.sh --dry-run --opencode
  • When changing protocol features in SKILL.md, mirror them in SKILL.codex.md, SKILL.gemini.md, and SKILL.opencode.md (or document why a host is exempt) — the checklist verifies parity
  • Test at least one mode (full/quick/duo) after protocol changes

Read the full file on GitHub · 41 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 41 lines · 626 tokens per session scan A ead6bbf72867

Subscribe to this mod's changes

council-of-high-intelligence CLAUDE.md is an instructions file published in the GitHub repository 0xNyk/council-of-high-intelligence (4,228 stars, last pushed 5d ago), licensed MIT. It adds 626 tokens to every session, about $0.0031 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens