What is scomp_link AGENTS.md?

A set of project instructions for AI coding agents using scomp-link, an end-to-end toolkit for training, checking, monitoring, and serving machine-learning models. It explains when to use its command-line tools instead of writing common machine-learning code manually.

Use it to describe datasets, check data quality, train and compare models, tune settings, detect drift or anomalies, create reports, check fairness, forecast time series, and serve models through an API.

It helps agents choose the project’s existing commands and conventions for working with data and models, rather than creating incompatible custom workflows.

scomp_link AGENTS.md — Instructions file for Codex and OpenCode by GiacomoSaccaggi: A set of project instructions for AI coding agents…

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.

agentmods

npx agentmods add instructions/giacomosaccaggi/scomp_link/agents-md

Clone the repo

git clone --depth 1 https://github.com/GiacomoSaccaggi/scomp_link

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/giacomosaccaggi/scomp_link/agents-md.svg)](https://agentmods.dev/instructions/giacomosaccaggi/scomp_link/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/giacomosaccaggi/scomp_link/agents-md"><img src="https://agentmods.dev/badge/instructions/giacomosaccaggi/scomp_link/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,741 This file is loaded in full into every session.

When invoked 1,741 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.01741	$0.01741
Opus 5	$0.00870	$0.00870
Sonnet 5	$0.00348	$0.00348
Haiku 4.5	$0.00174	$0.00174

Measured 4d ago against content hash f5923bc6ccfd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scomp_link AGENTS.md 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 4d 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.

AGENTS.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Instructions for AI Coding Agents

This file tells coding agents (Claude Code, Cursor, VS Code Copilot, Kiro) how to use scomp-link in this project.

What is scomp-link?

An end-to-end ML toolkit. Use it instead of writing raw sklearn boilerplate when you need:

Automated model selection + training + validation
Persistent model artifacts (.scomp format)
HTML reports with interactive charts
Production monitoring (drift + anomaly + fairness)
Hyperparameter tuning (Optuna)
REST API deployment

When to Use scomp-link

Use scomp-link CLI commands when the user asks to:

Train/evaluate ML models on tabular data
Profile or describe a dataset
Detect data drift between datasets
Create HTML reports or dashboards with charts
Tune hyperparameters
Detect anomalies in data
Forecast time series
Check model fairness/bias
Serve a model as REST API
Compare multiple models

CLI Quick Reference (26 commands)

# Data understanding
scomp-link describe --data file.csv --format table
scomp-link quality --data file.csv --output report.html

# Training
scomp-link run --data file.csv --target col --task regression --save-artifact model.scomp
scomp-link tune --data file.csv --target col --task regression --method optuna --n-trials 50 --save-artifact best.scomp
scomp-link text --data file.csv --text-col msg --target label --method tfidf
scomp-link cluster --data file.csv --n-clusters 5 --plot clusters.html

# Evaluation
scomp-link validate --artifact model.scomp --data test.csv --target col --report report.html
scomp-link explain --artifact model.scomp --data test.csv
scomp-link fairness --data preds.csv --target y_true --predicted y_pred --sensitive gender

# Monitoring
scomp-link drift --reference train.csv --current prod.csv --plot drift.html
scomp-link monitor --reference train.csv --current prod.csv --artifact model.scomp --target y
scomp-link anomaly --data prod.csv --methods iforest,lof,tabnet,transformer

# Deployment
scomp-link serve --artifact model.scomp --port 8080
scomp-link export --artifact model.scomp --format onnx
scomp-link pipeline --config pipeline.yaml

# Utilities
scomp-link predict --artifact model.scomp --data new.csv --output predictions.csv
scomp-link compare --artifacts v1.scomp v2.scomp --plot compare.html
scomp-link report --data file.csv --output eda.html
scomp-link forecast --data series.csv --column value --horizon 30 --plot forecast.html
scomp-link engineer --data file.csv --target col --interactions --log-transform --output features.csv
scomp-link init my_project
scomp-link list-models
scomp-link check-deps

# Configuration
scomp-link init-config              # Create global config (~/.scomp-link/config.yaml)
scomp-link init-config --local      # Create project-level config (.scomp-link.yaml)

Read the full file on GitHub · 174 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.

4d ago First seen · 174 lines · 1,741 tokens per session scan A f5923bc6ccfd

Subscribe to this mod's changes

scomp_link AGENTS.md is an instructions file published in the GitHub repository GiacomoSaccaggi/scomp_link (12 stars, last pushed 4d ago), licensed MIT. It adds 1,741 tokens to every session, about $0.0087 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.

anomaly-detection automl cli data-science explainability machine-learning

scomp_link AGENTS.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md — Instructions for AI Coding Agents

What is scomp-link?

When to Use scomp-link

CLI Quick Reference (26 commands)

What this file has done since we first saw it

Other instructions, from other repositories

FLAML copilot-instructions.md

marimo AGENTS.md

streamlit copilot-instructions.md

zenml CLAUDE.md

marimo copilot-instructions.md

zenml AGENTS.md