---
title: "quantitative-grounding"
description: "Add decision-useful quantitative structure for scale, comparison, likelihood, economics, uncertainty, and consequential empirical claims without numerical theater or false precision."
canonical: https://agentpluginsdirectory.com/plugins/quantitative-grounding
last-updated: 2026-09-21
---

# quantitative-grounding
Add decision-useful quantitative structure for scale, comparison, likelihood, economics, uncertainty, and consequential empirical claims without numerical theater or false precision.
- Slug: quantitative-grounding
- Publisher: Andrew Fai
- Repository: https://github.com/andydrewie/quantitative-grounding
- Manifest: plugin.json
- Version: 1.0.3
- License: MIT
- Category (editorial): agent-tooling
- Skills: 1 (quantitative-grounding)
- MCP servers: 0
- Stars: 2
- Repository created: 2026-08-04
- Repository last pushed: 2026-08-07
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/quantitative-grounding
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What quantitative-grounding does, in the publisher's words

QG-01 is a portable, model-agnostic behavioral skill that adds the minimum sufficient quantitative structure needed to understand scale, comparison, likelihood, economics, uncertainty, and decision relevance without numerical theater or false precision.

> Quantify when numbers reveal reality. Do not quantify when numbers merely imitate certainty.

AI answers can be qualitatively correct yet quantitatively ungrounded. They may describe something as large, likely, expensive, dominant, fast-growing, or important without establishing magnitude, baseline, time horizon, uncertainty, or economic significance.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/andydrewie/quantitative-grounding/HEAD/README.md

## Skills

- quantitative-grounding: Add the minimum sufficient quantitative structure needed to understand scale, comparison, likelihood, economics, uncertainty, and decision relevance without numerical theater or false precision. Use by default for substantive analytical requests involving rankings, companies, markets, probability,…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.