agentleFS
Itsme23476Itsme23476/everyday-claude-skills/subscription-audit/SKILL.md

subscription-audit

Skill1 starsChanged 3 months agoMITView on GitHub

Find the user's recurring subscriptions from their email receipts and bank/statement data, total them up, and flag which ones look forgotten or unused so they can cancel. Use when the user says "what am I subscribed to", "audit my subscriptions", "where is my money going", or "find subscriptions to cancel".

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Look across whatever's connected:

    line 12
  2. Distinctive:

    Don't guess a charge is a subscription without evidence (recurring, same amount).

    line 50
  3. Distinctive:

    Never store or repeat full card numbers or account numbers.

    line 52

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Subscription Audit

Surface the quiet monthly drain most people forget about.

Find them (read-only)

Look across whatever's connected:

  • Email receipts — search for "receipt", "invoice", "your subscription", "payment", "renews", "trial ending". Recurring senders are the giveaway.
  • Statements / bank export, if the user provides one — recurring charges of the same amount on a regular cadence.

For each subscription, capture: name, amount, cadence (monthly/yearly), and when you last saw activity or a receipt.

Judge

Sort into three:

  1. Active & wanted — recent use or obviously in-use.
  2. Probably forgotten — no sign of use, an old free-trial that converted, or a duplicate (two things that do the same job).
  3. Can't tell — flag for the user to decide.

Deliver

You're spending ~£146/month · ~£1,750/year across 11 subscriptions.

LOOK AT THESE
  Adobe CC      £52/mo   — last opened? no receipts opened in 4 months
  Gym           £40/mo   — no check-in data visible; still going?
  Two cloud drives — Dropbox £10 + iCloud £8, likely overlapping

KEEPING (look fine)
  Spotify, Netflix, ...

Lead with the annual total — that's the number that changes behaviour.

Rules

  • Never cancel anything. You surface and recommend; the user cancels.
  • Don't guess a charge is a subscription without evidence (recurring, same amount). One-off purchases aren't subscriptions.
  • Never store or repeat full card numbers or account numbers. If you see them in a statement, refer to the last 4 digits only.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.