Home / ai-business-tools / claude-code · GitHub

ai-council SKILL.md skillA

ai-council from ai-business-tools/claude-code is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add ai-business-tools/claude-code/ai-council@git:20260830.80a4dcd

Pins git:20260830.80a4dcd in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: ai-business-tools/claude-code
Path: skills/ai-council/SKILL.md
Versions recorded: 3
Latest version: git:20260830.80a4dcd, committed Aug 30, 2026
First version recorded: Apr 15, 2026
Size: 18,267 bytes
Repository stars: 5
License: MIT

Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Adapted from Andrej Karpathy's LLM Council methodology. Triggers on council, council this, run the council, war room this, pressure-test this, stress-test this, and debate this.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

<!-- Credit: Original LLM Council skill by John Graff, Assistant Professor of Instruction, UT Austin McCombs School of Business. Adapted from Andrej Karpathy's LLM Council methodology. -->

# AI Council

You ask one AI a question, you get one answer. That answer might be great, or mid, and you have no way to tell because you only saw one perspective. The council fixes this by running the question through 5 independent advisors, each thinking from a fundamentally different angle. Then they peer-review each other's work anonymously. Then a chairman synthesizes everything into a final recommendation showing where advisors agree, where they clash, and what you should actually do.

This is adapted from Andrej Karpathy's LLM Council: dispatch queries to multiple models, have them peer-review each other anonymously, then a chairman produces the final answer. Here we use sub-agents with different thinking lenses instead of different models.

---

## When to switch to the deep variant
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add ai-business-tools/claude-code/ai-council@sha256:42f1d6029b37400d

The line at the top of this page pins the label git:20260830.80a4dcd, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_frijayc4qpaomp3d.svg)](https://markdownregistry.com/a/art_frijayc4qpaomp3d)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Apr 15, 2026 and Aug 30, 2026, about one every 69 days.

version	committed	commit	size	audit
git:20260830.80a4dcd latest	2026-08-30	80a4dcd	18,267 B	A	view · diff
git:20260426.1de814c	2026-04-26	1de814c	17,818 B	A	view · diff
git:20260415.7acb3e8	2026-04-15	7acb3e8	16,904 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (18267 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

ai-business-tools/claude-code · 5 stars · license MIT · pushed 2026-09-25 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_frijayc4qpaomp3d
GET https://markdownregistry.com/api/v1/resolve?ref=ai-business-tools/claude-code/ai-council
GET https://markdownregistry.com/api/v1/blob/42f1d6029b37400dd02b144c7ca07f217d7e1775dd4a2cc03333e3c0eeb96956

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from ai-business-tools/claude-code

CLAUDE.md@CLAUDE-template CLAUDE.md file

ai-business-tools/claude-code · CLAUDE-template/CLAUDE.md

git:20260428.9493702 · audit A · 5 stars

ai-council-deep SKILL.md skill

ai-business-tools/claude-code · skills/ai-council-deep/SKILL.md · Deep, interactive variant of ai-council with three user-in-the-loop checkpoints (clarify, surface assumptions…