ml-developer — Claude Code subagent: what it does, how to install
ml-developer — a dedicated subagent for training machine learning models, exploring hyperparameter spaces, and editing Jupyter notebooks.
no license ★ 850 updated 2026-10-26
.claude/agents/data-ml-model.mdWhat ml-developer does
This subagent manages end-to-end machine learning workflows directly inside code repositories. It reads and edits files within directories like data/, models/, and src/ml/, executing training scripts and updating Jupyter notebooks. Through claude-flow@alpha, it caches experiment metrics, compares parameter configurations, and records successful optimization runs.
Its toolchain remains intentionally restricted. The agent cannot search the public web or run open-ended planning tasks, forcing it to rely exclusively on local training data. Datasets are capped at 100 MB, execution runs time out at 1800 seconds, and process memory cannot exceed 2 GB.
Deploying a model to production, launching large training jobs, or removing dataset files strictly requires explicit manual user approval.
What it helps with
- train classification and regression pipelines on local datasets
- tune model hyperparameters while logging optimization history
- edit and execute workflows in Jupyter notebooks and Python scripts
- hand off data preparation routines to a data-etl subagent
Example prompts for the agent
- Build a churn classification pipeline using data/churn.csv
- Tune hyperparameters for the estimator configured in src/ml/train.py
- Run the training procedure inside notebooks/forecast.ipynb
How to install ml-developer
Manually: put the files in place
.claude/agents/data-ml-model.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.codex/agents/data-ml-model.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.cursor/agents/data-ml-model.mdCursor also reads .claude/agents/
Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean
Questions about ml-developer
How to install ml-developer in Claude Code?
Add the agent definition to your project at .claude/agents/data-ml-model.md.
What does ml-developer do?
It prepares model architectures, runs local training routines, preserves saved artifacts such as .pkl or .joblib files, and tracks experiment metrics across runs.
What boundaries are enforced during execution?
Web browsing is disabled, datasets cannot exceed 100 MB, and production releases must wait for manual sign-off.