car-tco

car-tco is a cursor rule for Cursor from mohitagw15856/pm-claude-skills. It costs 101 tokens per session (1,020 once invoked), scanned B, original, MIT.

A total-cost comparison for owning or leasing a car. It compares depreciation, insurance, maintenance, fuel, and the time you expect to keep the car, rather than looking only at the monthly payment.

In plain words
What is it for?
Use it to compare a new car, used car, lease, or keeping your current car, and to estimate the true monthly cost of each choice.
Why use it?
A monthly payment can hide the biggest ownership costs, while an older car's repair risk can be overstated. Comparing the same costs over the same period gives a more useful picture.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc). Also seen: positional $N argument.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/car_tco.py --new-price 38000 --used-price 24000 --lease-month 420 --keep-value 9000.

Good fit Use it to compare a new car, used car, lease, or keeping your current car, and to estimate the true monthly cost of each choice.

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 · 1,357 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/car-tco

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 car-tco

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

Your own site · 80×15
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/car-tco"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/car-tco.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,020 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00101 $0.01020
Opus 5 $0.00051 $0.00510
Sonnet 5 $0.00020 $0.00204
Haiku 4.5 $0.00010 $0.00102

Measured 8d ago against content hash d70ab0b33653, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

car-tco scanned grade B with 1 finding 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 8d 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

- [ ] Do not moralize the want — price the options honestly and let the user choose with open eyes
exports/cursor/pm-calculators/car-tco/car-tco.mdc · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Car TCO Skill

Cars are sold on monthly payments and owned on total cost — and the two rank options differently. Depreciation (the biggest cost of a new car) never appears on a statement; maintenance (the biggest fear about an old car) is usually smaller than a year of new-car depreciation. This skill compares buy-new, buy-used, lease-forever, and keep-current on the same total-cost basis over the same horizon.

What This Skill Produces

  • Ranked scenario totals — every requested scenario over the same horizon, cheapest first
  • True per-month cost — total ÷ months, the number to compare against the payment the dealer quotes
  • The assumption ledger — depreciation curve, maintenance ramp, insurance deltas, all labeled
  • The not-modeled list — financing interest, jurisdiction taxes, reliability luck

Required Inputs

Ask for these if not provided:

  • Which scenarios to compare — any of: new price, used-equivalent price, lease terms, current car's value + annual maintenance
  • Horizon — years they realistically keep cars (default 8, labeled); short horizons flatter leasing, long ones flatter buying
  • Miles per year and rough fuel/energy cost (defaults 12,000 mi / $0.14 per mile, labeled)

Programmatic Helper

python3 scripts/car_tco.py --new-price 38000 --used-price 24000 --lease-month 420 --keep-value 9000
python3 scripts/car_tco.py --new-price 38000 --keep-value 9000 --keep-maint 1800 --horizon 6 --json

Deterministic. Depreciation: 20% year one then 10%/yr for new, gentler for used/current. Maintenance ramps 8%/yr (used cars start further up the ramp). Leases re-lease at each term end with a fresh drive-off. Resale value is credited back — TCO is what you spent minus what you can recover.

Framework: The Payment Illusion Rules

  • Depreciation is the invisible line item — a new car's largest cost has no bill; it's the resale-value credit shrinking
  • "My old car needs $2,000 of work" is usually cheap — compare the repair to a year of the replacement's depreciation before calling it "not worth fixing"
  • Leasing buys flexibility, not savings — lease-forever means paying peak depreciation years forever; price that honestly and let people buy flexibility knowingly
  • Margins under ~10% are noise — the model's assumptions can't resolve differences that small; say "roughly a tie," not a winner
  • The horizon drives the ranking — always name it; the same inputs rank differently at 3 years vs 10

Read the full file on GitHub · 76 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. 8d ago First seen · 76 lines · 101 tokens per session scan B d70ab0b33653

Subscribe to this mod's changes

car-tco is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,357 stars, last pushed today), licensed MIT. It adds 101 tokens to every session and 1,020 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.