Subscription Audit logo

Subscription Audit

Organization
openaccountant
subscription-audit

Find recurring subscriptions, calculate total cost, and flag unused ones.

Overview

Publisheropenaccountant
Repositoryskills
Skill namesubscription-audit
Stars
106
Forks
18
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by openaccountant on GitHub. Read the source before you install it.

Installation

Install the Subscription Audit AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/openaccountant/skills/tree/main/personal/subscription-audit
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/openaccountant/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/personal/subscription-audit .claude/skills/subscription-audit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Subscription Audit in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Subscription Audit on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Subscription Audit is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Subscription Audit

Overview

Scans your transaction history for recurring subscription charges, totals your monthly and annual subscription spend, identifies subscriptions with no recent usage pattern changes, and recommends cancellation candidates.

Wilson Tools Used

  • anomaly_detect — detect unused or forgotten subscriptions via type unused_subscriptions
  • transaction_search — find all recurring charges and verify subscription patterns

Workflow

  1. Run anomaly_detect with types: ["unused_subscriptions"] to surface subscriptions that appear to be unused or redundant.
  2. Run transaction_search with query: "subscription OR recurring OR monthly" and months: 6 to pull all subscription-like transactions over the past 6 months.
  3. Group results by merchant name and calculate the monthly charge amount for each subscription.
  4. Sum all recurring charges to produce a total monthly subscription spend and annualized cost.
  5. Cross-reference the anomaly detection results with the transaction list. Flag any subscription that appeared in the unused list.
  6. Present a table with columns: Merchant, Monthly Cost, Annual Cost, Months Active, Status (Active / Flagged for Review).
  7. Recommend cancellation candidates — prioritize subscriptions flagged as unused, then sort remaining by cost descending.
  8. Calculate potential annual savings if all flagged subscriptions were cancelled.

Without Wilson

  1. Export transactions from your bank as a CSV file (Chase: Statements & Documents > Download Account Activity > CSV; Bank of America: Statements & Documents > Download Transactions).
  2. Open the CSV in a spreadsheet (Google Sheets or Excel).
  3. Sort by the Description column and look for repeating merchant names with consistent amounts.
  4. Use a filter: in Google Sheets, add a helper column with =IF(COUNTIF(B:B, B2) > 1, "Recurring", "One-time") where column B is the merchant/description column.
  5. Create a pivot table grouping by merchant name, summing the amounts, and counting occurrences.
  6. Any merchant appearing monthly with a consistent amount is likely a subscription.
  7. Multiply each monthly charge by 12 to get annual cost.
  8. Review each subscription and ask: "Did I use this in the last 30 days?" Cancel anything you answer "no" to.
  9. Common subscription merchants to search for: Netflix, Spotify, Hulu, Disney+, Amazon Prime, Adobe, Dropbox, iCloud, Google One, YouTube Premium, gym memberships, news subscriptions.

Important Notes

  • Subscription detection relies on pattern matching in transaction descriptions. Some merchants use varying names across charges.
  • Annual subscriptions (charged once per year) may not appear in a 6-month window. Extend the search range to 12-18 months to catch these.
  • Free trials that convert to paid subscriptions are easy to miss — look for small initial charges from unfamiliar merchants.

Frequently asked questions

What does the Subscription Audit AI skill do?

Find recurring subscriptions, calculate total cost, and flag unused ones.

Why use Subscription Audit on TypingMind?

Because you install it once and use it with any model. Subscription Audit is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Subscription Audit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/openaccountant/skills/tree/main/personal/subscription-audit. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Subscription Audit?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Subscription Audit?

As many as you like. As long as a model supports skills, you can use Subscription Audit with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Subscription Audit AI skill free?

Yes. It is published on GitHub by openaccountant under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇