#105105th of 149 in Skills, plugins and rules

council-of-high-intelligence

Multi-persona deliberation skill for coding agent CLIs

Stars: 4.6k
License: MIT
Last commit: Oct 2026
Last release: Jul 2026
Language: Shell

Missed the latest GitHub check; these facts may be older.

Overview

Adds a /council command that sends a decision to up to 18 analytical personas, such as Socrates, Torvalds and Taleb. Members analyze independently, cross-examine each other, then produce a verdict listing dissent, kill criteria and a next step. Seats can be spread across providers (native host, Codex, Gemini, Ollama, NVIDIA NIM, Cursor) so one model family does not argue both sides.

Who it is for: Coding-agent users who want structured review of high-stakes decisions

Strengths

Full, quick and duo modes plus named triads for narrower questions
Same /council command across Claude Code, Codex, Gemini CLI and OpenCode
Verdicts keep dissent and unresolved questions, with FACT/INFERENCE/ASSUMPTION/UNKNOWN labels
Provider routing with --dry-route preview and fallback to the native host

Weaknesses

No benchmarks or evals in the README; output quality depends on the underlying models
Full protocol runs several rounds across many personas, so token cost is likely high
Personas are prompt contracts, not verified expert models
Four host mirrors of SKILL.md must be kept aligned by hand

What it needs

no GPU
Needs Claude Code, Codex, Gemini CLI or OpenCode, Optional: codex, gemini, ollama, cursor-agent executables or NVIDIA_API_KEY
Models: Claude Code native subagents, OpenAI via codex, Google via gemini, Ollama, NVIDIA NIM

Also in Skills, plugins and rules

See all 149

Also in Skills, plugins and rules
Rank	Project	Score
1	cavemanCuts token use in coding agents with terse replies and compressed inputs Live demo ↗ (opens in a new tab)112.2k starsApache-2.0	95 out of 100
2	skillsAgent skills for planning, TDD, debugging and code review292.4k starsMIT	94 out of 100
3	eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses280k starsMIT	94 out of 100
#4	impeccableDesign skill with 24 commands and a detector for AI-generated frontends Live demo ↗ (opens in a new tab)81.5k starsApache-2.0	94 out of 100
#5	ponytailSkill prompt that makes coding agents write less code and add tests164.1k starsMIT	92 out of 100

How to choose

Check which agent it targets and whether it works with the version you run.
Read what it adds to every prompt; big rule sets cost tokens on each call.
Prefer add-ons you can turn off per project.

Health

Releases: Not checked
Top contributor: Not checked
Security advisories: Not checked
Package advisories: Not checked
OpenSSF Scorecard: Not checked

Not read for this project yet: each refresh reads the facts of a few projects. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check.

License in plain words

MIT Permissive

Use it at work: Yes
Change it and rebrand it: Yes
Sell it or host it for others: Yes

Your part: Keep the copyright and license notice in copies you ship.

A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)

#105 of 149 in Skills, plugins and rules on Archestack, as of 15 Oct 2026.

In your README

The badge updates twice a day.

[![Archestack](https://archestack.com/badge/0xnyk/council-of-high-intelligence.svg)](https://archestack.com/best-of-vibe-coding/projects/council-of-high-intelligence/)

How badges work

On your site or blog

A card with the rank, score and signals, in light or dark to match the reader.

<iframe src="https://archestack.com/embed/best-of-vibe-coding/council-of-high-intelligence/" title="council-of-high-intelligence on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>

Preview the card

Best of Vibe Coding on GitHub

Each review comes from the project's README and facts we check on GitHub. The fix form opens with council-of-high-intelligence filled in.