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 skills add zjunlp/Mechanist --skill foundational-and-estimator-based-shapgit clone --depth 1 https://github.com/zjunlp/MechanistWrote 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/zjunlp/mechanist/foundational-and-estimator-based-shap)<a href="https://agentmods.dev/skills/zjunlp/mechanist/foundational-and-estimator-based-shap"><img src="https://agentmods.dev/badge/skills/zjunlp/mechanist/foundational-and-estimator-based-shap/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zjunlp/mechanist/foundational-and-estimator-based-shap"><img src="https://agentmods.dev/badge/skills/zjunlp/mechanist/foundational-and-estimator-based-shap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00110 | $0.08518 |
| Opus 5 | $0.00055 | $0.04259 |
| Sonnet 5 | $0.00022 | $0.01704 |
| Haiku 4.5 | $0.00011 | $0.00852 |
Grade A, and why
shap 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 11d 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 — 991 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SHAP – SHapley Additive exPlanations
When to Use
Activate this skill when any of the following apply:
- Model Explainability: A user wants to understand why a model made a specific prediction
- Feature Importance: Computing global or local feature importance for any ML model
- Tree Ensembles: Explaining XGBoost, LightGBM, CatBoost, scikit-learn, or PySpark tree models with the fast TreeExplainer
- Deep Learning: Explaining TensorFlow, Keras, or PyTorch neural networks with DeepExplainer or GradientExplainer
- NLP Models: Explaining Hugging Face Transformers text classification or other NLP pipelines
- Model-Agnostic Explanations: Using KernelExplainer for any black-box model (SVMs, random forests, custom functions)
- Visualization: Generating waterfall plots, force plots, beeswarm plots, bar charts, scatter/dependence plots, or text explanations
- SHAP Interaction Values: Computing pairwise interaction effects between features
- Audit / Fairness: Investigating which features drive predictions for regulatory or fairness purposes
Keywords that trigger this skill: shap, shapley, explainability, interpretability, feature importance, model explanation, waterfall plot, beeswarm, force plot, TreeExplainer, KernelExplainer, DeepExplainer, GradientExplainer, SHAP values, model attribution, local explanation, global explanation.
Quick Reference
| Resource | URL |
|---|---|
| PyPI Package | https://pypi.org/project/shap/ |
| Conda-Forge | https://anaconda.org/conda-forge/shap |
| Documentation | https://shap.readthedocs.io/en/latest/ |
| GitHub Repository | https://github.com/shap/shap |
| Binder (Interactive Notebooks) | https://mybinder.org/v2/gh/shap/shap/master |
| Nature MI Paper (Tree SHAP) | https://rdcu.be/b0z70 |
| Nature BME Paper (Force Plots) | https://rdcu.be/baVbR |
| Sample Notebooks | https://github.com/shap/shap/tree/master/notebooks |
Installation / Setup
Standard Installation
pip install shap
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.
- 11d ago First seen · 991 lines · 110 tokens per session scan A 769092ef38c0
shap is a skill published in the GitHub repository zjunlp/Mechanist (74 stars, last pushed 15d ago), licensed MIT. It adds 110 tokens to every session and 8,518 once invoked, about $0.0006 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
nanoresearch-experiment
Generate a Python code skeleton from an experiment blueprint.
nanoresearch-writing
Draft a LaTeX research paper from all previous stage outputs.
nanoresearch-ideation
Search academic literature and generate research hypotheses.
nnsight-remote-interpretability
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
sparse-autoencoder-training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
transformer-lens-interpretability
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.