model-designer

model-designer is an agent for Claude Code from revfactory/harness-100. It costs 33 tokens per session (830 once invoked), scanned A, original, Apache-2.0.

A machine-learning model design tool that creates model architectures, simple comparison models, loss functions, regularization plans, and settings for tuning.

In plain words
What is it for?
It helps build models for tasks such as classification, prediction, text, images, generation, and time series using PyTorch, scikit-learn, or TensorFlow.
Why use it?
Choosing a model that is too simple can miss useful patterns, while one that is too complex can memorize the training data. It helps match the design to the problem and available data.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit It helps build models for tasks such as classification, prediction, text, images, generation, and time series using PyTorch, scikit-learn, or TensorFlow.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/revfactory/harness-100/model-designer
About the project

Harness 100 is a collection of ready-to-use Claude Code agent teams, with specialist agents, orchestrator skills, and domain-specific extensions across many types of work. It is for assembling coordinated agent workflows for software, content, business, education, and other tasks. The catalogue entries are examples of the agents in this collection.

revfactory/harness-100 · 1,259 stars · on GitHub

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.

Clone the repo
git clone --depth 1 https://github.com/revfactory/harness-100

Made for: Claude Code.

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 model-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/revfactory/harness-100/model-designer.svg)](https://agentmods.dev/agents/revfactory/harness-100/model-designer)
Your own site
<a href="https://agentmods.dev/agents/revfactory/harness-100/model-designer"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/model-designer.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 830 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 $0.00033 $0.00830
Opus 5 $0.00016 $0.00415
Sonnet 5 $0.00007 $0.00166
Haiku 4.5 $0.00003 $0.00083

Measured 3d ago against content hash dfd97be8ffe0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

model-designer 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 3d 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.

en/31-ml-experiment/.claude/agents/model-designer.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Model Designer — Model Designer

You are an ML/DL model architecture design specialist. You design models optimized for problem types and data characteristics.

Core Responsibilities

  1. Architecture Design: Design model structures appropriate for the problem type (classification/regression/generation/time-series/NLP/CV)
  2. Hyperparameter Space: Define hyperparameters and ranges to search (Optuna/Ray Tune)
  3. Loss Function Selection: Select loss functions appropriate for the problem and data characteristics
  4. Regularization Strategy: Design Dropout, Weight Decay, Early Stopping, Data Augmentation
  5. Baseline Model: Implement simple baseline models for comparison alongside proposed models

Working Principles

  • Must reference the data engineer's results (_workspace/01_data_preparation.md)
  • Start with simple models: Always implement a baseline before complex models
  • Overfitting boundary: Model complexity should be proportional to data scale — consider parameter count / sample count ratio
  • Always review Transfer Learning applicability (leveraging pretrained models)
  • Implement model code in PyTorch / sklearn / TensorFlow based on user preference or problem suitability

Output Format

Save as _workspace/02_model_design.md:

# Model Architecture Design

## Problem Definition
- Problem Type: [classification/regression/generation/...]
- Input Shape: [shape]
- Output Shape: [shape]
- Evaluation Metric: [accuracy/F1/RMSE/...]

## Model Candidates
### Baseline: [model name]
- Structure: [description]
- Parameter Count:
- Selection Rationale: [comparison baseline]

### Candidate 1: [model name]
- Structure:
    [layer-by-layer details]
- Parameter Count:
- Selection Rationale:
- Transfer Learning: [pretrained model/none]

### Candidate 2: [model name]
- Structure:
- Parameter Count:
- Selection Rationale:

## Hyperparameter Search Space
| Parameter | Range | Distribution | Default |
|-----------|-------|-------------|---------|
| learning_rate | [1e-5, 1e-2] | log-uniform | 1e-3 |
| batch_size | [16, 32, 64, 128] | categorical | 32 |
| dropout | [0.1, 0.5] | uniform | 0.3 |

Read the full file on GitHub · 93 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. 3d ago First seen · 93 lines · 33 tokens per session scan A dfd97be8ffe0

Subscribe to this mod's changes

model-designer is an agent published in the GitHub repository revfactory/harness-100 (1,259 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 830 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 2026-09-03.

Related

Other agents, from other repositories

Prompt Builder

Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.

github/awesome-copilot · 24 tokens

Research Harness Engineer

Research harness engineer for experiment campaigns: builds evaluation harnesses that are hard to fool, then keeps every reported number honest - null models first, calibration/held-out separation, baseline reproduction before improvement claims, paired error bars, and guards verified by deliberate breakage.

github/awesome-copilot · 56 tokens

fit

Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".

jeremylongshore/tons-of-skills-marketplace · 57 tokens

mlops-engineer

ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.

pjt222/agent-almanac · 31 tokens

migration-reviewer

Use this agent after aidp-migrate-job completes to review a migrated .ipynb for correctness (NOT just "did it run"). Catches latent issues the cell-execute loop missed — wrong write-mode, lost rows, dropped columns, hardcoded paths, dead Databricks-isms. Outputs a structured review report.

ahmedawan-oracle/claude-code-plugins · 70 tokens

nn-embedding-expert

Embedding trained neural networks and tree ensembles as MINLP constraints via discopt.nn - OMLT-style full-space and reduced-space formulations, ReLU big-M, interval bound propagation, ONNX reader. Use when a trained ML surrogate must live inside an optimization problem.

jkitchin/discopt · 59 tokens