More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Scope Creep Firewall — Classify Change Requests & Draft the Reply

    1

    When a client asks for “one more thing,” this skill checks it against your signed scope, tells you in / gray / out, recommends what to do, and drafts a professional reply (it does not send anything).

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Scope Creep Firewall — Classify Change Requests & Draft the Reply

    Scope Creep Firewall — Classify Change Requests & Draft the Reply

    Example session with this skill installed

    Project: Harborline Logistics — Ops Dashboard MVP (week 3 of 6)
    SOW: 4 web views, 2 roles, Postgres read replica, Azure deploy, 2 revision rounds
    Exclusions: mobile/push, supplier portals, Excel migration, training videos, …
    Fee: $22,400 fixed · 6 weeks · cutover date fixed

    Slack from Priya
    "Supplier ASN self-service upload? iOS push for exceptions?
    Migrate 3 years Excel inventory? Training video? Dark mode if easy?"

    • Read your context and instructions
    • Compiled the scope creep firewall

    Classification: OUT-OF-SCOPE
    Action: CHANGE-ORDER
    Confidence: High · Precedent: High

    Matches

    • Supplier upload → OUT (exclusion: supplier portals)
    • iOS push → OUT (exclusion: mobile/push)
    • Excel migration → OUT (exclusion: Excel migration)
    • Training video → OUT (exclusion: training videos)
    • Dark mode → GRAY (not in deliverables)

    Impact (estimate only): ~55–85 hrs · +2–4 wks if pre-launch · ~$7.7k–$11.9k band
    Recommend: CO #1 + Phase 2 post-cutover; do not absorb mid-build
    3 reply drafts + change-order scaffold + Firewall Log JSON

    Connects securely to your tools. The creator never sees your data.

    About this skill

    The problem

    • “Quick addition” requests eat margin and slip launches when teams say yes without checking the signed scope.
    • Responding from memory leads to inconsistent boundaries, weak change orders, or relationship-damaging pushback.
    • You need a clear in / gray / out call, impact (including precedent risk), and a reply you can send — not a full new proposal.

    What it does

    • Compares the client’s new ask to your original deliverables, exclusions, and assumptions — with evidence quotes.
    • Classifies each item as IN-SCOPE, GRAY-ZONE, or OUT-OF-SCOPE.
    • Estimates effort, timeline, cost band, delivery risk, and precedent risk (will saying yes open the floodgates?).
    • Recommends an action: ABSORB, CLARIFY, NEGOTIATE, CHANGE-ORDER, or DECLINE.
    • Drafts three reply tones (collaborative, firm, formal) plus a change-order scaffold when needed, and a Firewall Log JSON.

    Not a proposal builder

    • This skill (firewall): post-sale. You already have a SOW; a change request just arrived.
    • Proposal / scope builders: pre-sale. They turn discovery notes into tiered packages, pricing, and a full SOW.
    • Use the firewall to defend scope; use a proposal skill to define and sell scope. Different jobs, different outputs.

    Frameworks & tools

    • Works from any written SOW, proposal excerpt, or statement of work plus the incoming client message.
    • Stack-agnostic (web, product, marketing, ops tools) — classification is against the agreement, not a framework.
    • SKILL.md workflow for Claude Code, Cursor, Codex CLI, OpenClaw, and similar agents. No integrations required.

    Why this beats prompting it yourself

    • Evidence table tied to real exclusions/deliverables — not gut feel.
    • Decision matrix includes precedent risk, not only hours.
    • Multi-item requests are split and classified line by line.
    • Three ready reply drafts + CO scaffold so you respond the same day.
    • Draft only: nothing is sent; estimates stay labeled as estimates; not legal advice.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Business & Operations.

    • Needs the original scope/SOW for a strong classification
    • Cost/timeline figures are estimates, not fixed quotes
    • Not legal advice; real contract disputes need a professional
    • Drafts only — does not send messages
    • Quality drops if the agreement is vague or missing

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 21 days ago

    Permissions

    Read Files

    This skill only reads the scope and client request you give it. It drafts a reply and change-order notes for you to copy. It does not send email, post to Slack, update a CRM, run shell commands, or call the internet. Grant Read only; leave Shell, Write, Browser, Network, and Env off.

    Listed3 months ago

    What's inside

    Frequently Asked Questions

    It classifies client requests as in-scope, out-of-scope, or gray-zone by comparing them against your original Statement of Work (SOW). It identifies 'precedent risk' and provides three ready-to-send reply drafts, helping you defend your margins without damaging client relationships.

    The skill is designed for any AI agent that supports the SKILL.md format, including Claude Code, Cursor, Codex CLI, and OpenClaw. It is stack-agnostic and works with any written agreement, whether it's for web development, marketing, or consulting.

    No, this skill is strictly a 'draft-only' tool that helps you prepare your response. It provides professional reply options and change-order scaffolds, but you maintain full control and must manually send the final communication to your client.

    You will receive the structured SKILL.md file containing the logic for classification, impact estimation, and response drafting. The package also includes a Firewall Log JSON template to help you track scope changes over the life of a project.

    Unlike a simple prompt, this skill performs line-by-line evidence mapping against your specific exclusions and deliverables. It doesn't just look at hours; it evaluates delivery risk and whether saying 'yes' once will set a difficult precedent for future requests.

    New in Business & Operations