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 refaelach/gmba-class-19-skills --skill llm-councilgit clone --depth 1 https://github.com/refaelach/gmba-class-19-skillsWrote 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/refaelach/gmba-class-19-skills/llm-council)<a href="https://agentmods.dev/skills/refaelach/gmba-class-19-skills/llm-council"><img src="https://agentmods.dev/badge/skills/refaelach/gmba-class-19-skills/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/refaelach/gmba-class-19-skills/llm-council"><img src="https://agentmods.dev/badge/skills/refaelach/gmba-class-19-skills/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 | $0.03857 |
| Opus 5 | $0.00109 | $0.01929 |
| Sonnet 5 | $0.00044 | $0.00771 |
| Haiku 4.5 | $0.00022 | $0.00386 |
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 11d 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
88% identical to llm-council-v2 — 203 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 — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Council
Compatibility
The skill follows the open Agent Skills standard, so it loads natively in Claude Code, Codex, Gemini CLI, Cursor, and any other tool that supports the spec. The full experience differs based on which features the tool exposes:
- Full experience (Claude Code, Codex): Spawns 5 advisors and 5 reviewers as parallel sub-agents, generates an HTML report and saved transcript using filesystem tools.
- Strong experience (Cursor, Gemini CLI, Antigravity): Sub-agent support varies; advisors may run sequentially. File outputs work where the tool has filesystem access.
- Partial experience (ChatGPT Custom GPTs, Gemini Gems, prompt-only setups): The methodology works the same, but advisors run sequentially in one chat. The HTML report step is skipped (or output as a single Markdown document instead). Paste the body of this
SKILL.mdinto a Custom GPT, Gem, or system prompt, then ask your question with one of the trigger phrases.
The core insight (5 thinking styles + anonymous peer review + chairman synthesis) is what matters, and that pattern is portable. The parallelism and file outputs are nice-to-haves.
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.
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.
- 11d ago First seen · 325 lines · 218 tokens per session scan A 1ac5923df719
llm-council is a skill published in the GitHub repository refaelach/gmba-class-19-skills (1 stars, last pushed 4mo ago), licensed MIT. It adds 218 tokens to every session and 3,857 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to llm-council-v2, differing in 203 lines, and is treated as a copy.
Other skills, from other repositories
lead-discovery
Orchestrator that runs first for lead generation requests. Gathers business context via website analysis or questions, identifies competitors, builds ICP, and routes to signal skills with pre-filled inputs.
email-finder-hunter
Email finder and verifier - find emails, verify deliverability, discover companies.
review-scraper
Scrape product reviews from G2, Capterra, and Trustpilot using Apify. Single script with platform dispatch. Use when you need to monitor competitor reviews, track product sentiment, or gather customer feedback from review sites.
company-domain-lookup-logodev
Logo.dev - search for company domains by brand name.
layout-skill
Layer A layout-mechanics reference. Stacks on any style skill when the screen is an app shell, dashboard, settings, list-detail, mail/inbox, or any layout with fixed regions plus a scrolling body — or when a layout breaks under long, empty, or unbroken content. Owns spatial structure and scroll ownership; owns zero…
who-owns-this-domain
Establish who registered and who operates a domain using WHOIS, RDAP and DNS. Use when running a whois lookup, querying RDAP, digging A, AAAA, MX, NS, TXT, SOA or CAA records, reading SPF includes, DKIM selectors or DMARC rua addresses, finding the registrar, registrant or nameservers, doing reverse DNS, PTR, ASN or…