Guided build · ~15 min
Subscription hunter
Finds the subscriptions you forgot about and shows what cancelling saves.
No commands. No code. You're about to build this by SAYING what you want — in your own language. The only skill is describing the result well. Here's the whole thing, start to finish.
Finds the subscriptions you forgot about and shows what cancelling saves.
First, how to actually talk to the agent
- 1Describe the RESULT, not the tech: what's on screen, what each button does, what gets saved. The agent handles the 'how'.
- 2Be concrete about screens and fields — 'a form with amount, category and date' beats 'let me add expenses'.
- 3Ask for the smallest working version first. You grow it by talking afterwards — that's Step 2, not the first message.
- 4Decide what's YOURS, not the agent's: name the categories, colours, rules. Don't make it guess what only you know.
Step 1 — Build it live
Prompting for this kind of tool
- 1For a subscription tracker, nail what ONE subscription card holds (name, price, billing cycle monthly-or-yearly, renewal date) and the TWO numbers up top: a true monthly total and a yearly total — and tell Claude to spread yearly plans across twelve months so the monthly figure is honest.
- 2Spell out the 'cancel me' flag and the savings panel yourself: 'add up what cancelling the flagged ones saves per year'. That payoff is the whole point of the tool — don't leave it for Claude to imagine.
- 3Add 'everything stays on my device, nothing is sent anywhere' — a list of everything you pay for is sensitive; it shouldn't touch a server.
- 4Always end with the magic line: 'build the whole thing and tell me exactly how to open it; don't stop to ask questions.'
claude --dangerously-skip-permissions
Open the terminal and run this (if Claude is already running, type /exit first). Then ask it to make a folder for this project and work inside it.
✕ what most people type
you ▸ find all my subscriptions
✓ what actually works — copy it, or better, say it in YOUR words
you ▸ Build me a subscription tracker. An add form takes name, price,
billing cycle (monthly or yearly) and renewal date; the list
shows every subscription as a card with days until its next
renewal and a 'cancel me' flag. A header shows my true monthly
total and yearly total (yearly plans spread across months), and
a savings panel adds up what cancelling the flagged ones would
save per year. The soonest renewal is highlighted. Everything
saves on my device. Clean readable cards, calm look. Build the
whole thing and tell me exactly how to open it; don't stop to
ask questions.Say it in YOUR language — Russian, Spanish, anything. Claude understands.
Build it now — tick as you go
0/6Step 2 — It's built. Now make it yours
Don't panic at the techy link. Claude tells you one of two things. Either a file like index.html — find it in your project folder and double-click it; it opens in your browser. Or a web address starting with http://localhost — copy it into your browser's address bar and press Enter. 'localhost' just means 'this is running on your own computer right now'. That's your tool. It's real.
Now tweak it until YOU like it — just talk
This is the part that makes it YOURS. Don't accept the first version — change it by saying what you want, right there in the same chat. Claude rebuilds and you refresh. Keep going until it fits how you actually work. For this tool, try things like:
you ▸ warn me 3 days before each renewal you ▸ show the yearly total, not just the monthly one you ▸ group them by category — streaming, tools, gym
I don't type long messages. I open voice-to-text (the mic in ChatGPT, or your phone keyboard), and just TALK through everything I think about what it built — what's wrong, what I want next — then select-all, copy, and paste the whole brain-dump into Claude Code. Messy spoken thoughts work fine; the agent sorts them out. It's several times faster than writing.
Step 2.5 — Test it like a real thing (it won't be perfect first try)
The truth no one tells beginners: the first build is a DRAFT. The agent makes something, you run it, you find what's off, you tell it — and THAT loop is the actual work. Don't read the code. Use the tool like a stranger would and watch where it lets you down. For this tool, check exactly this:
- 1Open it (Claude gives a localhost link or an index file — see Step 2) and add three subscriptions: two monthly and one yearly.
- 2Check the header math: the yearly plan must be split into a per-month share, so the monthly total should be the two monthly prices plus one-twelfth of the yearly one — not the full yearly price dumped on one month.
- 3Flag one as 'cancel me' and look at the savings panel — does it show that subscription's yearly cost as what you'd save? Unflag it and the saving should drop back to zero.
- 4Refresh the page (F5 / Cmd-R). Are all three subscriptions still there? If they vanish, 'saves on my device' isn't wired up — fix that next.
- 5Check that the soonest renewal is highlighted and that each card's 'days until renewal' counts down from today's date, not a fixed number.
Found something wrong? Say it like this
You fix nothing yourself — you DESCRIBE what's wrong in plain words and the agent fixes it. Be specific: what you saw vs. what you expected. Real examples for this tool:
you ▸ 'the monthly total is wrong — spread yearly plans across twelve months instead of charging the whole year to one month' you ▸ 'when I refresh the page my subscriptions disappear — save them on my device so they stay' you ▸ 'the days-until-renewal number is frozen — calculate it fresh from today's date every time I open the app'
Don't stop at v1 — grow it
A tool you built in ten minutes is a starting point, not the finish line. The people who get hooked keep saying 'now also…'. Each line below is one sentence you paste into the same chat to level this tool up:
you ▸ 'warn me a few days before any renewal charges, right on the card' — catches the silent re-bills before they hit, which is the money this tool exists to save. you ▸ 'group the cards by category — streaming, tools, gym — and show a total for each group' — shows you where the money actually leaks. you ▸ 'add a free-trial flag with the date it converts to paid, and shout about it the day before' — trials you forgot are the most expensive subscriptions of all. you ▸ 'let me mark a subscription as cancelled but keep it in a history list with the date' — so you can see how much you've already trimmed.
Step 3 — Connect it to the world (optional)
Free data & APIs for this one
An API is just how your tool pulls in outside data or sends things out — many are free. You rarely need to research them yourself; the move that works for ANY idea is to ask the agent to find them:
- 1To start you need NO external API — all the totals and savings math runs locally on your device.
- 2Want renewals on your phone? You don't need an API to begin, but you could later ask Claude to export each renewal as a calendar (.ics) file you import into Google Calendar — no key, no account.
- 3Reusable move for ANY idea: ask Claude — 'look up free or open APIs that fit a subscription tracker and tell me which actually need a key.' It will list them; you pick.
About paying for the AI parts
- 1You don't pay for Claude twice. With a Claude subscription you create an API key right in the terminal and use it inside your projects — within your plan.
- 2From June 15 the rule splits: automation through that key gets its own monthly credit — about $20 on Pro, $100 or $200 on Max. Stay under it and it works as before.
- 3Run out and you pay per use (pay-as-you-go); unused credit doesn't roll over. So check your account and see whether the included credit already covers what you're building.
A tool gets superpowers when it can talk to other services — send you a message, read a sheet, pull live data. Each service hands out an 'API key' (a long password that says 'this is me'). For THIS tool, the useful ones are:
Which keys this tool can use
- 1Telegram — ping you a few days before a renewal charges
- 2Google Calendar — drop each renewal date into your calendar
Getting any key is the same recipe: log into the service → find Settings → 'API' or 'Developers' → 'Create key' → copy it → paste it to Claude once ('here's my key: …'). Claude stores it and you never touch it again.
Step 4 — Put it online (only if someone else needs it)
Just for you, on your computer? You're already done — skip this step with a clear conscience. Put it online only if someone ELSE should open it, or you want to reach it from your phone away from home.
Step 6 — Stay safe (two easy habits)
- 1Back up anything you'd hate to lose. If the tool holds real data (your budget, health log, client list), ask Claude early: 'add an export/backup button' — one click saves your data to a file. Do it before you ever rebuild from scratch or move the folder.
- 2Don't hand Claude the keys to dangerous rooms. Keep it pointed at this project's own folder. Never connect a learning project to your bank, your crypto, or anything irreversible. Receipts and calendars — yes. Savings — no.
- 3Think before you ask. Claude does what you say in the folder you're in. 'Optimize my photos' optimizes them; it won't delete them — unless you ask for something reckless. Sane requests, clean workspace, and there's simply nothing scary left.
The mistakes that stop most people
- 1Asking for something vague ('make me an app') and getting something vague back. Name the screens, the buttons, what gets saved.
- 2Cramming in ten features at once. Ask for the tiniest working version first — then grow it with follow-up requests.
- 3Stopping at the first error. An error isn't failure — paste it to Claude or describe what you see, and it fixes it. That loop IS the work.
- 4Deciding you need to 'learn programming first'. You don't need to understand the code Claude writes. You need to describe the result.
- 5Forgetting the magic line — 'build the whole thing, don't stop to ask questions' — then wondering why it keeps pausing.
- 6Building for an imaginary audience. Build the version YOU will open tomorrow. Polish never; use immediately.
Normal. Tell Claude what's wrong in plain words ('the button does nothing', 'the page is blank') or paste the red error text. It finds and fixes it. You check. Repeat until it works.
That's it. You built a real tool.
Notice what just happened: no commands, no code — words. This is the entire skill. The people who 'can build things' are just people who describe what they want and let Claude do the typing.
More to build