tornado-sensitivity

tornado-sensitivity is a cursor rule for Cursor from mohitagw15856/pm-claude-skills. It costs 100 tokens per session (769 once invoked), scanned A, original, MIT.

A way to test which assumptions have the biggest effect on a model's result. It changes one input at a time between defensible low and high values and ranks the resulting output swings in a tornado table.

In plain words
What is it for?
It helps analyze models such as LTV, return on investment, or forecasts, including models stored in spreadsheets after tracing the relevant inputs.
Why use it?
It prevents discussions from focusing on assumptions that barely matter and shows where better evidence or decisions are most needed.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/tornado.py run tornado.xlsx --model model.json.

Good fit It helps analyze models such as LTV, return on investment, or forecasts, including models stored in spreadsheets after tracing the relevant inputs.

Compare 6 cursor rules from other repositories ↓
About the project

PM Skills is a collection of plain-Markdown instructions that teach AI assistants structured methods for handling professional, personal, and life-admin tasks. People use it with Claude, ChatGPT, Gemini, Cursor, Codex, and other supported agents for work such as writing product requirements, reviewing documents, or planning difficult situations.

mohitagw15856/pm-claude-skills · 1,352 stars · on GitHub · mohitagw15856.github.io

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills
agentmods
npx agentmods add rules/mohitagw15856/pm-claude-skills/tornado-sensitivity

Made for: Cursor.

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 tornado-sensitivity

README.md
[![agentmods](https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/tornado-sensitivity/github.svg)](https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/tornado-sensitivity)
Your own site
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/tornado-sensitivity"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/tornado-sensitivity/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 tornado-sensitivity

Your own site · 80×15
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/tornado-sensitivity"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/tornado-sensitivity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 769 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 $0.00100 $0.00769
Opus 5 $0.00050 $0.00385
Sonnet 5 $0.00020 $0.00154
Haiku 4.5 $0.00010 $0.00077

Measured 6d ago against content hash 15797f1910d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

tornado-sensitivity 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 6d 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.

exports/cursor/pm-calculators/tornado-sensitivity/tornado-sensitivity.mdc · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tornado Sensitivity

Every model has four drivers people argue about and one that actually controls the answer — usually not the same one. The tornado ranks them: hold everything at base, swing one driver to its low and high, measure the output range, sort. Diligence goes to the top bar; the bottom bars stop hijacking meetings.

Required Inputs

  • The model — output name, a formula over named drivers (arithmetic + min/max/abs/sqrt/log/exp only), and per-driver low/base/high. The lows and highs should be defensible bounds ("the worst quarter we've seen", "the vendor's contractual ceiling"), not ±10% ritual.
  • If the requester has a spreadsheet instead of a formula: extract the output cell's driver chain into a formula first, and show it for confirmation.

Output Format

  1. The tornado table — drivers sorted by output swing, with input range, output at each end, and share of total swing. The top driver's share is the headline ("lifetime owns 33% of the uncertainty").
  2. The meeting verdict — one paragraph: what deserves diligence, what deserves a decision-and-move-on, and any driver whose bounds are the real problem (huge swing because nobody actually knows the range).
  3. The interaction caveat — one-at-a-time ignores correlated drivers; if two move together in reality (price and churn), say so and model the pair as one driver.

Programmatic Helper

Ships scripts/tornado.pyzero dependencies, with a restricted evaluator (driver names + six math functions; anything else is rejected — injection-tested):

python3 scripts/tornado.py run tornado.xlsx --model model.json

Prints base=1.371 · top driver: lifetime (swing 1.097, 33% of total) and writes Summary + Tornado sheets. Requires a code-execution environment.

Quality Checks

  • Swings computed by the script, quoted — never reasoned in prose
  • Bounds provenance is stated per driver (measured / contractual / guess) — a tornado of guesses is honestly labelled one
  • Share-of-swing sums are shown so the ranking's decisiveness is visible
  • Correlated drivers are named and the caveat applied to them specifically
  • The verdict names what to STOP arguing about — the negative guidance is half the value

Read the full file on GitHub · 47 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. 6d ago First seen · 47 lines · 100 tokens per session scan A 15797f1910d9

Subscribe to this mod's changes

tornado-sensitivity is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 2d ago), licensed MIT. It adds 100 tokens to every session and 769 once invoked, about $0.0005 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.