ml-pipeline — Claude Code plugin: what it does, how to install
The ml-pipeline plugin makes an agent follow a 16-step, data-first ML workflow before training. It fits tasks where premature .fit() calls could compromise the analysis.
Apache-2.0 ★ 1,596 updated 2026-10-29
/plugin marketplace add hashgraph-online/awesome-codex-plugins
/plugin install ml-pipeline@awesome-codex-pluginsWhat ml-pipeline does
ml-pipeline makes the agent inspect the raw data, define the prediction target, run profiling and EDA, then prepare splits before it trains anything. Each phase ends with a permission gate: the agent explains its findings, shows figures, and waits for an explicit approval. marimo notebooks provide the workspace, while matplotlib figures go to ml_pipeline/figures/.
Progress and approvals are recorded in ml_pipeline/PIPELINE.md, so another session can continue from the last completed step. In Claude Code, hooks inspect commands, file writes, and notebook edits. They block training before the required gates, prevent test-set misuse, and flag suspicious metrics. The runtime helpers guard.split() and guard.final_test() handle temporal or grouped data and allow the frozen test set to be scored once. Codex receives the same workflow as instructions, but it has no hook support. Training cannot proceed before Gate A is approved.
What it helps with
- inspect raw data before fitting a model
- surface missing values, duplicates, and leakage suspects
- split data before feature engineering and preprocessing
- stop early evaluation on the test split
- record ML workflow steps and approvals
Example prompts for the agent
- Run
/ml-pipelinefor a model-training task based ondata.csv. - Take this ML task through all 16 steps and pause at every approval gate.
- Check the dataset for leakage, invalid splits, and any premature
.fit()call.
How to install ml-pipeline
Plugin marketplace
/plugin marketplace add hashgraph-online/awesome-codex-plugins/plugin install ml-pipeline@awesome-codex-pluginsStep by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own
Questions about ml-pipeline
How do I install ml-pipeline in Claude Code?
Run /plugin marketplace add hashgraph-online/awesome-codex-plugins, then run /plugin install ml-pipeline@awesome-codex-plugins.
What does ml-pipeline do?
It guides an ML task through 16 ordered steps, including data inspection, EDA, target definition, dataset preparation, training, and evaluation. The agent must receive explicit approval between phases.
Does ml-pipeline use hooks in Codex?
Codex follows the same workflow through instructions, while hooks are available in Claude Code only.
Source text
ml-pipeline · Apache-2.0
# ml-pipeline **Stop your coding agent from jumping straight to model training.** Coding agents love to call `.fit()` five minutes into an ML task — before looking at the data, before there's a test set, before anyone agreed on what is being predicted. This plugin forces a strict, data-first 16-step pipeline with explicit user-permission gates — and, in Claude Code, a hook that makes skipping them impossible:  ## Install **Claude Code** ``` /plugin marketplace add jananthan30/ml-pipeline /plugin install ml-pipeline@ml-pipeline ``` The skill activates automatically on any ML training/tuning/evaluation task, or invoke it directly with `/ml-pipeline`. **Codex CLI** ``` codex plugin marketplace add jananthan30/ml-pipeline codex plugin add ml-pipeline@ml-pipeline ``` **Kimi Code CLI** (or Codex without plugins) ```bash git clone https://github.com/jananthan30/ml-pipeline && cd ml-pipeline && ./install-other-tools.sh ``` Copies the skill into `~/.codex/skills/` and `~/.kimi-code/skills/` and appends an enforcement section to each tool's global `AGENTS.md`. ## How it works - **Strict order, no skipping** — the split happens *before* feature engineering and preprocessing; all fitting uses training data only; the test set is touched exactly once. - **You stay in control** — at each gate the agent explains, in plain language, what it did, what it found (with figures), and what comes next, then waits for your explicit OK. "Just train it" gets the risk explained and requires a logged override. - **See everything** — [marimo](https://marimo.io) notebooks as the workbench, matplotlib figures saved to `ml_pipeline/figures/`, each explained in 1–2 plain sentences. - **Resumable** — `ml_pipeline/PIPELINE.md` tracks every step and approval, so a new session continues where the last one stopped. ## Enforced, not just instructed In Claude Code the plugin ships hooks. Before any command, file write, or notebook edit runs, a `PreToolUse` hook scans the code and **denies**: any fitting before Gate A; model training before Gate B; evaluating on the test split before Gate C; fitting on the test split, ever. A denied call tells the agent exactly which steps are missing — so "just train it" fails closed until you have approved the gate. A `PostToolUse` hook warns when a metric looks too good to be honest or a split ignores class balance or time. And at step 6 the agent switches to `guard.split()` / `guard.final_test()`, a small runtime library that drops duplicates, refuses random splits on temporal data, and lets the frozen test set be scored exactly once. It also refuses to let understanding be skipped. `guard.profile()` writes a data profile — column kinds, missingness, duplicates, class balance, temporal coverage, and **leakage suspects** — and `guard.eda_figures()` draws the required figures with explanations computed from the data. Gate A can't be recorded without them; Gate B can't be recorded without a written model rationale (traits → baseline → candidates → what was ruled out and why → metric). And five provably wrong applications are denied outright from the profile: a neural net on a small table, a random split on temporal data, a non-group split on grouped data, accuracy as the selection metric on an imbalanced target, and resampling before the split. Prove it on the **canary**: `examples/canary/canary.csv` has a known honest ceiling of 0.80 accuracy. Beat it and you leaked. `ML_PIPELINE_ENFORCE=0` switches enforcement off for non-ML projects. Codex and Kimi get the same rules as instructions (no hook support there). ## License Apache-2.0
© Jananthan Paramsothy · Apache-2.0 · hashgraph-online/awesome-codex-plugins