Say "that is outside scope" and keep the client.
An email that sets out what was agreed, what is now being asked, and two or three priced options, so the client makes a choice instead of getting a refusal.
Scope creep arrives politely. One more page, one more revision, a small extra that grows. Freelancers either absorb it and resent it, or reply with a flat no that sounds like an accusation. Both damage the work.
Scope Boundary Email compares the request to the agreed scope, then drafts a warm reply that names the document, not your opinion. It offers real options with a price or time cost, asks for a decision by a date, and adds one line so it does not happen again.
What it produces.
- →A side-by-side check of agreed scope against the new request
- →Two or three priced options the client can pick from
- →A complete email with a decision date
- →A closing line that sets the pattern for future extras
- ✦Freelancers whose projects keep growing past the proposal
- ✦Consultants who give extras away and then resent it
- ✦Designers and developers with a client on revision four of three
- →scope-boundary-email.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →scope-boundary-email-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
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 writes either a firm refusal or an over-apologetic one. This Playbook starts by checking whether the request is actually out of scope, then builds the reply around options the client can choose between.
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.