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.
npx agentmods add skills/james-traina/compound-science/causal-mlnpx skills add James-Traina/compound-science --skill causal-mlgit clone --depth 1 https://github.com/James-Traina/compound-scienceWrote 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.
[](https://agentmods.dev/skills/james-traina/compound-science/causal-ml)<a href="https://agentmods.dev/skills/james-traina/compound-science/causal-ml"><img src="https://agentmods.dev/badge/skills/james-traina/compound-science/causal-ml.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00191 | $0.02188 |
| Opus 5 | $0.00096 | $0.01094 |
| Sonnet 5 | $0.00038 | $0.00438 |
| Haiku 4.5 | $0.00019 | $0.00219 |
Grade A, and why
causal-ml 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Causal Machine Learning
Reference for semiparametric ML estimators: DML with cross-fitting, generalized random forests, debiased regularization, and nuisance function approximation. Covers Neyman-orthogonal moment conditions, sample splitting, plug-in bias correction, and heterogeneous treatment effects.
When to Use This Skill
Use when the user is:
- Estimating treatment effects with high-dimensional controls (p large relative to n)
- Interested in heterogeneous treatment effects (CATE) as a primary estimand
- Applying ML for flexible nuisance function estimation within a causal framework
- Implementing cross-fitting, sample splitting, or Neyman-orthogonal estimators
- Using
econml,DoubleML, orgrfpackages
Skip when:
- Sample is small (n < 500 — ML nuisance models need data)
- A well-specified parametric model is available and defensible
- The task is standard IV/DiD/RDD without high-dimensional controls (use
causal-inferenceskill) - Structural modeling is needed (use
structural-modelingskill) - The task needs formal identification proof (use
identification-proofsskill)
Where to Start
- Choosing a method? Jump to Method Selection Guide
- ATE with many controls? See
references/dml.md - Heterogeneous treatment effects? See
references/grf-meta-learners.md - Variable selection for controls? See
references/high-dim-cross-fitting.md - Reporting HTE results? See
references/hte-inference.md - Connecting to traditional methods? See
references/connections-traditional.md
Causal ML vs Traditional Methods
| Dimension | Traditional (IV, DiD, RDD) | Causal ML |
|---|---|---|
| Functional form | Parametric | Nonparametric / semi-parametric |
| High-dimensional controls | Problematic | Native support |
| Heterogeneous effects | Secondary (subgroup analysis) | Primary estimand (CATE) |
| Sample requirements | Moderate N | ML nuisance needs large N |
| Identification | Explicit (IV, DiD, RCT) | Same assumptions — ML is estimation, not identification |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 138 lines · 191 tokens per session scan A 6bd0ba54cbcb
causal-ml is a skill published in the GitHub repository James-Traina/compound-science (13 stars, last pushed 5mo ago), licensed MIT. It adds 191 tokens to every session and 2,188 once invoked, about $0.0010 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.
Other skills, from other repositories
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…
torchdrug
Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
deepspot-m
Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with…
pyhealth
Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer…
pick-a-pii-model
Select an on-device OpenMed PII model from the committed registry by language, runtime format, and size budget, then require recall validation before deployment. Use when an agent must choose a local PII detector for CPU, Apple Silicon, or a mobile export without relying on live model discovery.
esm
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…