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 plurigrid/asi --skill bdd-mathematical-verificationgit clone --depth 1 https://github.com/plurigrid/asiWrote 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/plurigrid/asi/bdd-mathematical-verification)<a href="https://agentmods.dev/skills/plurigrid/asi/bdd-mathematical-verification"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/bdd-mathematical-verification/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/plurigrid/asi/bdd-mathematical-verification"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/bdd-mathematical-verification.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 | $0.00089 | $0.04136 |
| Opus 5 | $0.00044 | $0.02068 |
| Sonnet 5 | $0.00018 | $0.00827 |
| Haiku 4.5 | $0.00009 | $0.00414 |
Grade A, and why
bdd-mathematical-verification 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 — 579 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BDD Mathematical Verification Skill
Overview
This skill enables Behavior-Driven Development (BDD) workflows for mathematics, combining:
- Gherkin Specifications: Plain-text scenario definitions
- RSpec Implementation: Executable Ruby verification code
- mathpix-gem Integration: Automatic LaTeX extraction from images
- Pattern Matching: Syntax-tree validation for mathematical expressions
- Iterative Discovery: Cucumber features guide formula exploration
Core Components
1. Feature Specifications (Gherkin)
Feature: Mathematical Formula Extraction and Verification
Scenario: Extract LaTeX from mathematical image
Given I have a mathematical image file "quadratic.png"
When I extract LaTeX using Mathpix
Then I should get a LaTeX formula matching the pattern "ax^2 + bx + c"
And the formula should be registered as an artifact
Scenario: Verify quadratic formula in standard form
Given a quadratic formula "x^2 - 5*x + 6"
When I verify it is in standard form
Then the coefficients should be [1, -5, 6]
And it should be factorable as "(x - 2)(x - 3)"
Scenario Outline: Verify binomial expansion
Given a binomial expression "<binomial>"
When I expand it using binomial theorem
Then the result should match "<expanded>"
And all terms should be present with correct signs
Examples:
| binomial | expanded |
| (x + 1)^2 | x^2 + 2*x + 1 |
| (a - b)^3 | a^3 - 3*a^2*b + 3*a*b^2 - b^3 |
| (2*x + 3)^2 | 4*x^2 + 12*x + 9 |
2. RSpec Implementation Blocks
describe "Mathematical Formula Verification" do
describe "Formula Extraction" do
context "with valid mathematical image" do
it "extracts LaTeX representation" do
# Extraction step
end
it "normalizes notation to standard form" do
# Normalization step
end
end
context "with multi-page document" do
it "extracts all formulas in order" do
# Batch processing
end
end
end
describe "Formula Verification" do
context "with polynomial expressions" do
it "matches pattern against syntax tree" do
# Pattern matching verification
end
it "verifies algebraic equivalence" do
# Equivalence checking
end
end
context "with nested/complex expressions" do
it "validates form requirement" do
# Form verification (expanded/factored/etc)
end
end
end
describe "Scenario-Driven Discovery" do
context "with parameterized examples" do
it "verifies all example variations" do
# Parameterized testing
end
end
end
end
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 · 579 lines · 89 tokens per session scan A 8f8cb7f803f8
bdd-mathematical-verification is a skill published in the GitHub repository plurigrid/asi (62 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 4,136 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
acceptance-criteria-given-when-then
Use this skill when writing test-first, behavior-driven acceptance criteria in Given/When/Then format for a Salesforce user story. Covers happy path, edge cases, negative paths, permission boundaries, and data-state preconditions so the AC block can drive UAT scripts and Apex test design downstream. Trigger keywords…
Forge
Autonomous quality engineering swarm that forges production-ready code through continuous behavioral verification, exhaustive E2E testing, and self-healing fix loops. Combines DDD+ADR+TDD methodology with BDD/Gherkin specifications, 7 quality gates, defect prediction, chaos testing, and cross-context dependency…
qcsd-refinement-swarm
QCSD Refinement phase swarm for Sprint Refinement sessions using SFDIPOT product factors, BDD scenario generation, and requirements validation.
BDD/Cucumber Patterns
Behavior-Driven Development skill using Cucumber, covering feature files, step definitions, Gherkin best practices, data tables, scenario outlines, and hooks.
Behat BDD Testing
PHP BDD testing with Behat framework using Gherkin feature files, Mink browser extension, context classes, and Symfony integration for behavior-driven acceptance testing.
Behave BDD Testing
Python BDD testing with Behave framework using Gherkin feature files, step definitions, environment hooks, and Selenium integration for behavior-driven acceptance testing.