subscription-audit

subscription-audit is a cursor rule for Cursor from mohitagw15856/pm-claude-skills. It costs 104 tokens per session (1,315 once invoked), scanned A, original, MIT.

An audit of recurring payments that finds subscriptions, converts each cost to a yearly amount, and ranks them from most to least expensive.

In plain words
What is it for?
It helps find recurring charges, total monthly and yearly spending, and sort subscriptions into keep, cancel, downgrade, or negotiate decisions.
Why use it?
Monthly prices can hide how much recurring services cost over a year, and charges may be spread across cards, app stores, payment services, or annual bills.

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/subscription_audit.py --sub "streaming-a:15.99:monthly" --sub "vpn:71.88:yearly" --sub "gym:45:monthly".

Good fit It helps find recurring charges, total monthly and yearly spending, and sort subscriptions into keep, cancel, downgrade, or negotiate decisions.

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/subscription-audit

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 subscription-audit

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

Your own site · 80×15
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/subscription-audit"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/subscription-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,315 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 $0.00104 $0.01315
Opus 5 $0.00052 $0.00658
Sonnet 5 $0.00021 $0.00263
Haiku 4.5 $0.00010 $0.00131

Measured 6d ago against content hash ab9f881213d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

subscription-audit 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/subscription-audit/subscription-audit.mdc · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Subscription Audit Skill

Subscriptions are priced monthly precisely so nobody computes them yearly — $15.99 is a sandwich; $191.88 is a decision. The audit is two passes: find them all (the hunt is the hard part — they hide across cards, app stores, PayPal, and annual charges that only surface one month a year) and annualize and rank them, at which point most of the leak turns out to live in the top three lines. This skill runs both passes and then the honest keep/cancel/downgrade sort — including the note that canceling is sometimes deliberately harder than subscribing, and how to do it anyway.

What This Skill Produces

  • The annualized ranking — every recurring charge at its true yearly cost, from the script, with per-month and per-day totals
  • The hunt checklist — the places subscriptions hide, worked through systematically
  • The sort — keep (used, valued) / cancel (the honest list) / downgrade (the tier nobody remembers choosing) / negotiate (the ones that discount on cancel-intent)
  • The re-audit cadence — because the leak refills

Required Inputs

Ask for these if not provided:

  • The recurring lines — from bank/card statements (2–3 months back, plus one full year scan for annual charges); raw pasted statements are fine — extraction is part of the job
  • The hunt surfaces — which cards, app-store subscriptions (both platforms), PayPal/payment-app recurring, anything on a partner's card that's really shared
  • Honest usage — per service: when last actually used (the calendar answer, not the aspirational one — "I might get back into it" is the leak talking)

Programmatic Helper

python3 scripts/subscription_audit.py --sub "streaming-a:15.99:monthly" --sub "vpn:71.88:yearly" --sub "gym:45:monthly"
python3 scripts/subscription_audit.py --sub "news:4:weekly" --sub "cloud:2.99:monthly" --json

Deterministic. Cadences: weekly/monthly/quarterly/yearly; output ranks by annualized cost and reports the top-three share — usually most of the leak.

Read the full file on GitHub · 79 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 · 79 lines · 104 tokens per session scan A ab9f881213d5

Subscribe to this mod's changes

subscription-audit is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 2d ago), licensed MIT. It adds 104 tokens to every session and 1,315 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.