Cut what nobody would miss. Keep what holds things up.
A line-by-line review of your recurring costs, sorted by renewal date, ending in an action list of cuts, downgrades, and renegotiations.
Recurring costs grow by accretion: a tool someone trialed, a plan sized for a bigger team, a retainer that rolled over. The usual fix is a blunt percentage cut, which removes useful things with the waste, or a review that stalls because every line has a defender.
Cost Review asks the same four questions of every line: who uses it, what breaks without it, when does it renew, and what is the smaller version. It sequences the actions by notice window so a saving is not missed by a week, and checks every cut for what quietly depends on it.
What it produces.
- →An annualized, sorted list of every recurring cost
- →A decision on each line: cut, downgrade, renegotiate, or keep
- →An action table in renewal-date order with owners and deadlines
- →A what-could-bite-back check on every proposed cut
- ✦Owners and office managers tidying up before renewals
- ✦Finance leads inheriting a messy list of subscriptions
- ✦Teams that want savings nobody has to reverse
- →cost-review.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →cost-review-skill.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
- →A README inside the zip with install steps for Claude, ChatGPT, and Gemini
What it does with a real question.
I run a 12-person design studio, and our recurring spend has crept up to about $9,400 a month. Renewals for our Adobe seats, Slack, and the office internet all land in March, and the cleaning contract renews April 1. I've exported the last 12 months from our accounting software, so please start there.
Start with the calendar, not the total. Your $9,400 a month is about $113,000 a year, but the number that matters first is which lines can still be changed before they renew. Adobe, Slack, and the internet all land in March, so that is where the decision window is tightest, and the cleaning contract on April 1 is close behind it. Notice periods often close weeks before the renewal date itself, so check each contract for its cancellation window today.
For the three March items, ask what breaks if each stopped tomorrow, because that question sorts them fast. Slack and internet are probably keeps, but seat counts are another matter. With 12 people, I would bet at least one or two Adobe seats belong to freelancers who rolled off, or to people who only open one app. Pull the last login date for every seat. A seat untouched for 90 days is a cut, and an app used once a month may fit a cheaper single-app plan. Slack deserves the same seat audit, since paid workspaces quietly accumulate departed contractors.
The cleaning contract is your best candidate for renegotiation rather than cancellation: ask whether weekly service could become every other week, or whether a competing quote beats the current rate.
Next move: from your export, filter to the four March and April lines plus anything over $200 a month, and send me the seat lists with last-login dates.
The full Playbook runs the whole procedure and writes the complete deliverable, not this excerpt.
Written by claude-sonnet-5-5 with this Playbook loaded, 2026-10-11. Checked automatically for length and for copied framework text.
No subscription · free updates within v1.x
Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable
Before you buy.
How is this different from just asking Claude directly?
Asked cold, Claude lists generic places to save money. This works through your own list line by line, asks what actually breaks without each cost, orders actions by renewal date, and checks each cut for hidden dependencies such as shared logins, backups, and integrations.
How is this different from a Tool?
Playbooks are systematically produced to a fixed template and priced accordingly ($12.99). Tools are hand-built, one at a time, and go deeper ($39 to $199). A Playbook gives you a reliable method for routine work; a Tool is for when the judgment matters more than the format.
Will this work with ChatGPT, Gemini, and other LLMs?
Yes. You get a native Claude Skill (.zip) that auto-invokes in Claude, plus a plain .md you can paste into a ChatGPT Custom GPT, a Gemini system prompt, or any LLM. The procedure travels with the file.
Can I share this with my team?
It's licensed for your own personal and professional use. The output it produces is yours to circulate. To put the Playbook itself in the hands of a whole team, email hello@authority.md about team licensing.
What if it doesn't work for me?
If the file hasn't been delivered, or arrives defective or empty, we refund in full: see our refund policy.
Finance Playbooks are writing and structuring aids. They are not financial, tax, or accounting advice. Check figures, policies, and anything with legal or tax consequences with a qualified professional.