student-loan-strategy

student-loan-strategy is a cursor rule for Cursor from mohitagw15856/pm-claude-skills. It costs 102 tokens per session (1,302 once invoked), scanned B, original, MIT.

A comparison of three ways to use extra money when repaying student loans: paying loans faster, investing while making minimum payments, or following a forgiveness plan. It separates the guaranteed saving from reducing loan interest from the uncertain return of investments.

In plain words
What is it for?
Use it to compare repayment paths using each loan's balance, interest rate, minimum payment, and federal or private status, then review the assumptions behind the result.
Why use it?
The choice depends on loan rates, forgiveness rules, investment risk, and cash-flow needs. Extra payments can also reduce the balance that might otherwise be forgiven.

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/student_loan_strategy.py --loan "grad:38000:6.8:410" --loan "undergrad:12000:4.5:130" --extra 400.

Good fit Use it to compare repayment paths using each loan's balance, interest rate, minimum payment, and federal or private status, then review the assumptions behind the result.

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/student-loan-strategy

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 student-loan-strategy

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

Your own site · 80×15
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/student-loan-strategy"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/student-loan-strategy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,302 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 $0.00102 $0.01302
Opus 5 $0.00051 $0.00651
Sonnet 5 $0.00020 $0.00260
Haiku 4.5 $0.00010 $0.00130

Measured 7d ago against content hash dc3d9458d178, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

student-loan-strategy 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 7d 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 debt urgency — a 3.5% loan is cheap money and saying so is honesty, not heresy
exports/cursor/pm-calculators/student-loan-strategy/student-loan-strategy.mdc · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Student Loan Strategy Skill

The student-loan question is really an allocation question: the same $400/month can attack the balances (a guaranteed return equal to the weighted APR), sit in investments (a higher assumed return with risk attached), or — on a forgiveness track — do active damage, since extra payments shrink the amount that would have been forgiven. The right answer depends on the APRs, the program, and the person's risk temperament, and the honest move is simulating all three on the actual loans and naming which assumptions carry the conclusion.

What This Skill Produces

  • The three-path comparison — attack / minimums-plus-invest / forgiveness-ride, from the script, on the real loans
  • The honest framing — guaranteed APR vs. assumed return, stated as the different things they are
  • The forgiveness math — what riding costs, what gets discharged, and the extra-payments-hurt-here warning
  • The decision sheet — the numbers plus the non-model factors (risk temperament, cash-flow relief, program-trust), position taken

Required Inputs

Ask for these if not provided:

  • Every loan — balance, APR, minimum (federal vs. private noted: forgiveness and income-driven options generally attach to federal only — flagged jurisdiction/program-specific)
  • The extra amount — the real monthly number in play
  • Forgiveness status — on a track (employment-based, income-driven horizon)? Months remaining and the program named; not on one? The branch disappears honestly
  • The temperament — how they'd feel about market losses while carrying debt; it's a legitimate input, not noise

Programmatic Helper

python3 scripts/student_loan_strategy.py --loan "grad:38000:6.8:410" --loan "undergrad:12000:4.5:130" --extra 400
python3 scripts/student_loan_strategy.py --loan "fed:52000:6.2:560" --extra 300 --forgiveness-months 84 --json

Deterministic. Attack = avalanche; invest = extra compounding at the assumed return until natural payoff; forgiveness = minimums to the horizon with the remainder shown as discharged (program rules verify-required).

Read the full file on GitHub · 77 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. 7d ago First seen · 77 lines · 102 tokens per session scan B dc3d9458d178

Subscribe to this mod's changes

student-loan-strategy is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 3d ago), licensed MIT. It adds 102 tokens to every session and 1,302 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.