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.
npx skills add saski/arnesto --skill llm-councilgit clone --depth 1 https://github.com/saski/arnestoWrote 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.
[](https://agentmods.dev/skills/saski/arnesto/llm-council)<a href="https://agentmods.dev/skills/saski/arnesto/llm-council"><img src="https://agentmods.dev/badge/skills/saski/arnesto/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.
<a href="https://agentmods.dev/skills/saski/arnesto/llm-council"><img src="https://agentmods.dev/badge/skills/saski/arnesto/llm-council.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00218 | $0.03621 |
| Opus 5 | $0.00109 | $0.01810 |
| Sonnet 5 | $0.00044 | $0.00724 |
| Haiku 4.5 | $0.00022 | $0.00362 |
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 5d 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.
This is a copy
98% identical to llm-council-v2 — 311 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Council
STARTER_CHARACTER = ⚖️
You ask one AI a question, you get one answer. That answer might be great. It might be mid. You have no way to tell because you only saw one perspective. The council fixes this. It runs your question through 5 independent advisors, each thinking from a fundamentally different angle. Then they review each other's work. Then a chairman synthesizes everything into a final recommendation that tells you where the advisors agree, where they clash, and what you should actually do. This is adapted from Andrej Karpathy's LLM Council. He dispatches queries to multiple models, has them peer-review each other anonymously, then a chairman produces the final answer. We do the same thing inside Claude using sub-agents with different thinking lenses instead of different models.
when to run the council
The council is for questions where being wrong is expensive. Good council questions:
- "Should I launch a $97 workshop or a $497 course?"
- "Which of these 3 positioning angles is strongest?"
- "I'm thinking of pivoting from X to Y. Am I crazy?"
- "Here's my landing page copy. What's weak?"
- "Should I hire a VA or build an automation first?" Bad council questions:
- "What's the capital of France?" (one right answer, no need for perspectives)
- "Write me a tweet" (creation task, not a decision)
- "Summarize this article" (processing task, not judgment) The council shines when there's genuine uncertainty and the cost of a bad call is high. If you already know the answer and just want validation, the council will likely tell you things you don't want to hear. That's the point.
the five advisors
Each advisor thinks from a different angle. They're not job titles or personas. They're thinking styles that naturally create tension with each other.
1. The Contrarian
Actively looks for what's wrong, what's missing, what will fail. Assumes the idea has a fatal flaw and tries to find it. If everything looks solid, digs deeper. The Contrarian is not a pessimist. They're the friend who saves you from a bad deal by asking the questions you're avoiding.
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.
- 5d ago First seen · 197 lines · 218 tokens per session scan A d9e6f34a9050
llm-council is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed 2d ago), licensed Unlicense. It adds 218 tokens to every session and 3,621 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to llm-council-v2, differing in 311 lines, and is treated as a copy.
Other skills, from other repositories
readonly-review
Run a no-network read-only review practice with two explorer steps and one synthesis step.
repo-contracts-and-boundaries
Use when turning architecture, layering, ownership, dependency direction, schemas, structural metrics, quality thresholds, baselines, allowlists, or generated quality snapshots into repository checks.
repo-harness-assessment
Use when evaluating repository agent-readiness, mapping harness roles, choosing the next smallest improvement, or designing and reconciling agent entrypoints such as AGENTS.md, CLAUDE.md, GEMINI.md, Cursor rules, or GitHub instructions.
work-state-and-delivery
Use when designing or reconciling design docs, task boards, external trackers, execution plans, delivery records, handoffs, review evidence, task-to-change traceability, or repository commit-coupling policy.
runtime-evidence-and-tracing
Use when connecting observed behavior, logs, metrics, request IDs, run IDs, screenshots, traces, external dependency results, or artifacts into a runtime evidence loop.
validation-harness-design
Use when designing repository validation commands, doctor scripts, test matrices, JSON or JUnit outputs, CI gates, smoke checks, or harness command surfaces.