llm-council

llm-council is a skill for Claude Code, Codex from YonasValentin/llm-council. It costs 225 tokens per session (1,933 once invoked), scanned A, original, MIT.

A decision-review process in which five AI advisers analyze a question independently, review one another anonymously, and combine their conclusions into a recommendation.

In plain words
What is it for?
Use it to pressure-test important choices, compare competing ideas, and get a synthesized verdict with a recommended next step.
Why use it?
It reduces the risk of relying on one answer shaped by a single wording or point of view.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

Good fit Use it to pressure-test important choices, compare competing ideas, and get a synthesized verdict with a recommended next step.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yonasvalentin/llm-council/llm-council
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add YonasValentin/llm-council --skill llm-council
Clone the repo
git clone --depth 1 https://github.com/YonasValentin/llm-council

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 llm-council

README.md
[![agentmods](https://agentmods.dev/badge/skills/yonasvalentin/llm-council/llm-council/github.svg)](https://agentmods.dev/skills/yonasvalentin/llm-council/llm-council)
Your own site
<a href="https://agentmods.dev/skills/yonasvalentin/llm-council/llm-council"><img src="https://agentmods.dev/badge/skills/yonasvalentin/llm-council/llm-council/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 llm-council

Your own site · 80×15
<a href="https://agentmods.dev/skills/yonasvalentin/llm-council/llm-council"><img src="https://agentmods.dev/badge/skills/yonasvalentin/llm-council/llm-council.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 225 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,933 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00225 $0.01933
Opus 5 $0.00112 $0.00966
Sonnet 5 $0.00045 $0.00387
Haiku 4.5 $0.00022 $0.00193

Measured 10d ago against content hash 40406f06f74d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

llm-council 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 10d 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.

SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Council

One AI gives you one answer. That answer feels smart because it was shaped by how you asked. Ask the same question with different framing and you get a different answer, often opposite, equally confident.

The council breaks that loop. Five advisors with different thinking styles answer your question independently. They peer-review each other anonymously. A chairman synthesizes everything into a verdict with a clear recommendation and one concrete next step.

This skill runs the whole protocol inside a single Claude Code session.

When NOT to convene

If the question fits one of these, just answer directly instead of convening:

  • Factual lookup (one correct answer exists).
  • Creation task (write, summarize, translate, refactor).
  • Trivial choice (e.g. "should I use markdown or plaintext for this note").
  • The user has already decided and wants validation. Warn them the council may dissent, then proceed only if they confirm.

If you are unsure, ask the user once: "Is this a real tradeoff you want pressure-tested, or do you want a direct answer?"

The seven steps

This workflow is rigid. Execute in order. Do not skip, merge, or parallelize across steps.

Step 1. Scan workspace for context (30 seconds max)

Before framing the question, surface any workspace context the advisors will need. Use Glob and Read. Do not spend more than 30 seconds on this step.

Look for:

  • CLAUDE.md, AGENTS.md, GEMINI.md (user or project instructions).
  • memory/**/*.md (user profile, past decisions, voice).
  • Files the user referenced by name or @-mention.
  • Recent council/**/council-report.html artifacts so you avoid re-counciling ground already covered.

Pick at most 2 to 3 files that would move advisors from generic to grounded. Skip entirely if nothing relevant is present. Never read the whole workspace indiscriminately.

Step 2. Frame the question

Restate the user's raw question as a single neutral prompt with four parts:

  1. Core decision, stripped of emotional lean.
  2. User-provided context: facts, numbers, constraints.
  3. Workspace context: the 2 to 3 facts from Step 1 that matter here.
  4. Stakes: why being wrong is expensive.

Read the full file on GitHub · 169 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. 10d ago First seen · 169 lines · 225 tokens per session scan A 40406f06f74d

Subscribe to this mod's changes

llm-council is a skill published in the GitHub repository YonasValentin/llm-council (4 stars, last pushed 4mo ago), licensed MIT. It adds 225 tokens to every session and 1,933 once invoked, about $0.0011 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 2026-08-31.

Related

Other skills, from other repositories

thinking-theory-of-constraints

When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.

tjboudreaux/cc-thinking-skills · 37 tokens

Vizra ADK Memory System

Implement persistent memory, session context, and vector memory (RAG) for AI agents.

vizra-ai/vizra-adk · 24 tokens

foundation-models

On-device LLM integration using Apple's Foundation Models framework. Use when implementing AI text generation, structured output, or tool calling.

rshankras/claude-code-apple-skills · 29 tokens

analytics-interpretation

Interpret app metrics and make data-driven decisions. Covers DAU/MAU, retention, LTV, ARPU, App Store Connect analytics, AARRR funnel analysis, cohort analysis, and diagnostic decision trees. Use when user wants to understand their metrics, diagnose problems, or build a data-driven growth plan.

rshankras/claude-code-apple-skills · 68 tokens

app-namer

Turn an app idea into validated, App-Store-ready name candidates. Use when the user says "name my app", "what should I call it", "app name ideas", "help me name this app", "is this name available", or needs to pick a brandable, ownable name before reserving it in App Store Connect.

rshankras/claude-code-apple-skills · 73 tokens

animation-patterns

SwiftUI animation patterns including springs, transitions, PhaseAnimator, KeyframeAnimator, SF Symbol effects, scroll-driven effects, mesh gradients, text renderers, and shader effects. Use when implementing, reviewing, or fixing animation or visual-effect code on iOS/macOS.

rshankras/claude-code-apple-skills · 58 tokens