onnx-minimal-network-design

onnx-minimal-network-design is a skill for Claude Code, Codex from topprismdata/cultivating-ml-agent. It costs 144 tokens per session (982 once invoked), scanned A, original, MIT.

A method for designing very small neural networks directly as ONNX graphs. ONNX is a portable format for representing machine-learning models, and the approach focuses on reducing intermediate memory and parameter counts.

In plain words
What is it for?
Use it to build compact ONNX solutions, choose minimal operators, design convolution-based local rules, and optimize memory and parameter costs.
Why use it?
In network-size competitions, extra intermediate data can cost more than model parameters, so a smaller graph can score better even when it has more weights.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to build compact ONNX solutions, choose minimal operators, design convolution-based local rules, and optimize memory and parameter costs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/topprismdata/cultivating-ml-agent/onnx-minimal-network-design
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 topprismdata/cultivating-ml-agent --skill onnx-minimal-network-design
Clone the repo
git clone --depth 1 https://github.com/topprismdata/cultivating-ml-agent

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 onnx-minimal-network-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/topprismdata/cultivating-ml-agent/onnx-minimal-network-design/github.svg)](https://agentmods.dev/skills/topprismdata/cultivating-ml-agent/onnx-minimal-network-design)
Your own site
<a href="https://agentmods.dev/skills/topprismdata/cultivating-ml-agent/onnx-minimal-network-design"><img src="https://agentmods.dev/badge/skills/topprismdata/cultivating-ml-agent/onnx-minimal-network-design/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 onnx-minimal-network-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/topprismdata/cultivating-ml-agent/onnx-minimal-network-design"><img src="https://agentmods.dev/badge/skills/topprismdata/cultivating-ml-agent/onnx-minimal-network-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 144 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 982 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 $0.00144 $0.00982
Opus 5 $0.00072 $0.00491
Sonnet 5 $0.00029 $0.00196
Haiku 4.5 $0.00014 $0.00098

Measured 12d ago against content hash 1c45f9c64651, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

onnx-minimal-network-design 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.

skills/examples/onnx-minimal-network-design/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ONNX Minimal Network Design

Problem

Neural network golf competitions require the smallest possible ONNX network that correctly implements a transformation. Score = max(1, 25 - ln(memory + params)).

Smaller networks → exponentially higher scores. The key insight: memory dominates cost (intermediate tensor bytes), not parameters.

Solution

Core Scoring Formula

memory = Σ(bytes of all intermediate tensors)  # input/output are FREE
params = Σ(initializer element counts)
score  = max(1, 25 - ln(memory + params))

Design Principle 1: Single-Node = Zero Memory

A single-node graph (1 Conv/Gather/Transpose) has zero intermediate memory (output tensor is free). Only params count.

Implication: A 1-node Conv with 900 params (cost=900, score=18.2) beats a 4-node net with 200 params + 5000 memory (cost=5200, score=16.3).

Design Principle 2: Conv is a Linear Classifier

A Conv node maps 3×3 one-hot neighborhoods → output channels. This is a linear classifier on 90-dim features (9 positions × 10 colors).

To find Conv weights for a local rule:

  1. Collect all (3×3 neighborhood, output color) pairs from training data
  2. Verify the rule is deterministic (same neighborhood → same output)
  3. Train LogisticRegression (multi-class, C=1e4, solver='newton-cg') on the pairs
  4. Extract coef_ as Conv W[10,10,3,3], intercept_ as B[10]
  5. Verify ONNX runtime output matches ground truth on ALL examples

Limitation: If LogReg accuracy < 100%, the rule is NOT linearly separable. Need nonlinear ops (Cast/Equal/Where) — a single Conv cannot implement it.

Design Principle 3: Gather for Color Permutations

A pixel-wise color map (e.g., swap color 3↔4) is a 1-node Gather:

  • idx = [0,5,6,4,3,1,2,7,9,8] (10-element lookup table)
  • Gather(input, idx, axis=1) maps each one-hot vector to the permuted one
  • Cost: 10 params, 0 memory → score ≈ 22.7

Design Principle 4: Sparse Initializers REJECTED

Converting dense sparse weights to sparse_initializer reduces params but onnx.checker.check_model(full_check=True) rejects sparse Conv weights:

W typestr: T, has unsupported type: sparse_tensor(float)

Read the full file on GitHub · 95 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. 12d ago First seen · 95 lines · 144 tokens per session scan A 1c45f9c64651

Subscribe to this mod's changes

onnx-minimal-network-design is a skill published in the GitHub repository topprismdata/cultivating-ml-agent (5 stars, last pushed 14d ago), licensed MIT. It adds 144 tokens to every session and 982 once invoked, about $0.0007 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

huggingface-hub

Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.

braxtonROSE4/zorro-agent · 43 tokens

tensorboard

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit.

davila7/claude-code-templates · 32 tokens

mlflow

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform.

davila7/claude-code-templates · 33 tokens

datachain-knowledge

Use whenever datasets, cloud storage buckets, or data pipelines are mentioned — creating, saving, querying, listing, exploring, deleting, or processing data in S3, GCS, Azure Blob, or local storage. Also use when running any script that may create datasets as a side effect. Maintains a knowledge base at dc-knowledge/…

datachain-ai/datachain · 104 tokens

prompt-scanner

A scanner for text sent to an AI agent, looking for prompt injection and jailbreak attempts. Prompt injection is text that tries to override an agent's instructions; a jailbreak tries to bypass its safety limits.

alibaba/anolisa · 103 tokens

install-openviking-memory

Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin…

volcengine/OpenViking · 191 tokens