double-check-ai-math-manually

double-check-ai-math-manually is a skill for Claude Code from alivirgo/Major-AI-Skills. It costs 27 tokens per session (1,120 once invoked), scanned A, original, MIT.

A procedure for checking calculations produced by an AI, especially for invoices, ownership tables, taxes, and loan estimates.

In plain words
What is it for?
Use it to verify financial quotes, invoices, equity cap tables, budgets, tax calculations, and loan estimates with formulas and programmatic calculations.
Why use it?
Language models can produce plausible arithmetic with an incorrect final total. The procedure adds deterministic checks to catch those errors before results are shared.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument; mentions Codex.

Part of the mas-common-sense-pack plugin — 5 skills shipped together

Good fit Use it to verify financial quotes, invoices, equity cap tables, budgets, tax calculations, and loan estimates with formulas and programmatic calculations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alivirgo/major-ai-skills/double-check-ai-math-manually
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.

Any agent
npx skills add alivirgo/Major-AI-Skills --skill double-check-ai-math-manually
Clone the repo
git clone --depth 1 https://github.com/alivirgo/Major-AI-Skills

Made for: Claude Code.

Or install mas-common-sense-pack, the plugin that ships this one along with the rest of its 5 skills.

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.

agentmods badge for double-check-ai-math-manually

README.md
[![agentmods](https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/double-check-ai-math-manually/github.svg)](https://agentmods.dev/skills/alivirgo/major-ai-skills/double-check-ai-math-manually)
Your own site
<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/double-check-ai-math-manually"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/double-check-ai-math-manually/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.

agentmods 80×15 button for double-check-ai-math-manually

Your own site · 80×15
<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/double-check-ai-math-manually"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/double-check-ai-math-manually.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,120 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.01120
Opus 5 $0.00014 $0.00560
Sonnet 5 $0.00005 $0.00224
Haiku 4.5 $0.00003 $0.00112

Measured today against content hash f52e7224d7b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

double-check-ai-math-manually 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 today.

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.

plugins/mas-common-sense-pack/skills/double-check-ai-math-manually/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Double-Check AI Math Manually (Deterministic Verification) (AI Skill)

Overview

Because Large Language Models are probabilistic language generators rather than algebraic engines, they can generate an impeccable financial breakdown where the individual line items look flawless, but the sum at the bottom is subtly wrong by $150 or 2.5%.

The 3-Tier Math Verification Ladder provides a safety net to ensure that no AI-generated financial quote, invoice, equity cap table, or budget is delivered without deterministic proof of accuracy.


The 3-Tier Math Verification Ladder

┌─────────────────────────────────────────────────────────────┐
│                 3-Tier Math Safety Ladder                   │
│                                                             │
│  [ TIER 1: AI Formula Derivation ]                          │
│  • Define variables, logic, and standard formulas           │
│                           │                                 │
│                           ▼                                 │
│  [ TIER 2: Code / Python Execution ]                        │
│  • Force the AI to execute Python math programmatically     │
│                           │                                 │
│                           ▼                                 │
│  [ TIER 3: Deterministic Human Check ]                      │
│  • Paste values into Excel, Google Sheets, or a calculator  │
│  • 100% Guaranteed Mathematical Integrity                   │
└─────────────────────────────────────────────────────────────┘

High-Risk Math Scenarios Requiring Tier-3 Verification

  1. Client Invoices & Estimates: Multi-line hourly rates with discounts and tax percentages.
  2. Cap Tables & Equity Dilution: Post-money SAFE notes, option pools, and vesting calculations.
  3. Loan & Mortgage Amortization: Compound interest formulas ($M = P \frac{r(1+r)^n}{(1+r)^n - 1}$).
  4. Tax Withholdings & Deductions: Progressive bracket brackets and FICA thresholds.

Read the full file on GitHub · 113 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.

  1. today Changed · -11 tokens per session f52e7224d7b5
  2. 12d ago First seen · 113 lines · 38 tokens per session scan A ef02231da972

Subscribe to this mod's changes

double-check-ai-math-manually is a skill published in the GitHub repository alivirgo/Major-AI-Skills (1 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 1,120 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

invoicing

Use when issuing an invoice, quote, or credit note and moving it draft-to-paid — the legally required VAT fields, gap-free numbering, per-country e-invoicing mandates, dunning overdue ones. NOT recording a paid invoice in the books (that is bookkeeping), NOT Stripe SDK plumbing (that is stripe), NOT setting the price…

ericrisco/rsc-harness · 82 tokens

ai-pricing

AI Pricing Skill workflow skill. Use this skill when the user needs When the user wants to price an AI product, choose a charge metric, design pricing tiers, or optimize margins. Also use when the user mentions 'AI pricing,' 'usage-based pricing,' 'consumption pricing,' 'outcome pricing,' 'BYOK,' 'bring your own key,'…

diegosouzapw/awesome-omni-skills · 148 tokens

alpha-vantage-v2

Alpha Vantage — Financial Market Data workflow skill. Use this skill when the user needs Access 20+ years of global financial data: equities, options, forex, crypto, commodities, economic indicators, and 50+ technical indicators and the operator should preserve the upstream workflow, copied support files, and…

diegosouzapw/awesome-omni-skills · 73 tokens

aomi-transact-v2

Use this skill to operate the Aomi CLI for natural-language crypto and DeFi workflows, including balance checks, route simulation, transaction review, and explicit user-approved signing flows across EVM chains.

diegosouzapw/awesome-omni-skills · 46 tokens

azure-cost-management

Expert knowledge for Cost Management development including troubleshooting, best practices, decision making, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when managing Azure cost exports, budgets/alerts, tags, reservations/savings plans, or billing APIs, and other Cost…

MicrosoftDocs/Agent-Skills · 99 tokens

azure-payment-hsm

Expert knowledge for Azure Payment Hsm development including troubleshooting, best practices, decision making, architecture & design patterns, security, and configuration. Use when configuring Payment HSM VNets/peering, FastPath, payShield Manager access, SKUs, HA/DR topologies, or traffic routing, and other Azure…

MicrosoftDocs/Agent-Skills · 118 tokens