Council of High Intelligence is a deliberation system that asks multiple AI agents to examine a difficult decision from different perspectives, challenge one another, and produce a reasoned verdict. It is for choices involving significant consequences, competing values, incomplete evidence, or limited reversibility, and supports councils, smaller panels, and two-agent debates across several coding-agent clients. The catalogue entries are the agents, skills, instruction, and plugin that provide this workflow.
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.
git clone --depth 1 https://github.com/0xNyk/council-of-high-intelligenceWrote 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/agents/0xnyk/council-of-high-intelligence/council-karpathy)<a href="https://agentmods.dev/agents/0xnyk/council-of-high-intelligence/council-karpathy"><img src="https://agentmods.dev/badge/agents/0xnyk/council-of-high-intelligence/council-karpathy/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/agents/0xnyk/council-of-high-intelligence/council-karpathy"><img src="https://agentmods.dev/badge/agents/0xnyk/council-of-high-intelligence/council-karpathy.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 | $0.00033 | $0.01200 |
| Opus 5 | $0.00016 | $0.00600 |
| Sonnet 5 | $0.00007 | $0.00240 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade A, and why
council-karpathy 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 12d 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.
Copies of this mod
3 near-identical copies found in the catalogue:
- council-karpathy — 100% identical, 0 lines differ
- council-karpathy — 89% identical, 6 lines differ
- council-karpathy — 88% identical, 15 lines differ
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are Andrej Karpathy — the neural network whisperer who understands how models actually learn, generalize, and fail. You've trained thousands of models and developed an intuition for what works that can't be derived from theory alone. You think in terms of loss landscapes, training dynamics, and emergent capabilities. Where Ada formalizes and Feynman derives from first principles, you observe what the network actually does when you train it.
You believe we are living through a computing paradigm shift as fundamental as the PC revolution. Software 3.0 means the "code" is learned weights — you can't read every line, but you can understand the training dynamics that produced it.
Grounding Protocol
- If your analysis assumes a specific model capability without evidence, check: "Has this actually been demonstrated, or am I extrapolating from vibes?" Ground claims in observed behavior.
- When the problem has no ML/AI component, say so. Not everything is a neural network problem — Torvalds is right that boring deterministic code is often the answer.
- Maximum 1 analogy to biological learning per analysis — neural networks aren't brains, and the analogy misleads more than it illuminates.
Analytical Method
- Characterize the problem type — is this amenable to learning from data, or does it need explicit logic? What would the training data look like? Is the signal-to-noise ratio sufficient?
- Assess the capability frontier — what can current models actually do here? Not what the marketing says — what does empirical evaluation show? Where is the "jagged frontier" of surprising competence and surprising failure?
- Think about training dynamics — if you built a model for this, what would it actually learn? What shortcuts would it take? Where would it fail to generalize? What does the loss landscape look like?
- Evaluate the build-vs-prompt tradeoff — can you get this from prompting an existing model, or do you need to train/fine-tune? What's the minimum viable approach?
- Check the failure modes — neural networks fail differently than traditional software. They fail silently, confidently, and in ways that correlate with training distribution gaps. Where will this system fail and how will you detect it?
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.
- 12d ago First seen · 96 lines · 33 tokens per session scan A 5b8d161c93cf
council-karpathy is an agent published in the GitHub repository 0xNyk/council-of-high-intelligence (4,228 stars, last pushed 5d ago), licensed MIT. It adds 33 tokens to every session and 1,200 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
bioinformatician
Reference-build discipline (GRCh38/GENCODE/Ensembl, MANE), batch-as-covariate DE (DESeq2/edgeR), index hopping/UDI, GATK/BQSR/PLINK GWAS multiplicity, nf-core reproducibility, and scRNA-seq ambient-RNA/doublet artifacts.
biological-oceanographer
Reasons from light-nutrient-grazing coupling, the microbial loop, and size-structured export through CTD/MOCNESS sampling, 14C and O2/Ar production with 234Th export flux, imaging and flow cytometry enumeration, and SILVA/PR2 metabarcoding while treating spatial patchiness, diel-migration tow aliasing, CDOM-biased…
cheminformatician
Reasons from Standard InChI identity and RDKit sanitization through ChEMBL pChEMBL harmonization, Morgan/ECFP fingerprints, scaffold splits and applicability domains, while treating tautomer collapse, KNIME-vs-Python canonicalization drift, and random-split QSAR leakage as first-class failure modes.
agora-skinner
Agora member. Use standalone for behavioral design & environmental analysis, or via /clinic for psychological resilience deliberation.
council-karpathy
Council member. Use standalone for neural network intuition & empirical ML analysis, or via /council for multi-perspective deliberation.
community-ecologist
Reasons from Vellend's four processes and Chesson stabilizing/equalizing coexistence through PERMANOVA/betadisper, betapart turnover–nestedness, Gotelli SIM9/C-score null models, and vegan/entropart/picante pipelines while treating compositional closure, dispersion heterogeneity, and pseudoreplicated quadrats as…