scope-cutter

scope-cutter is a skill for Claude Code from Dokkabei97/forged-claude-code. It costs 45 tokens per session (1,118 once invoked), scanned A, original, MIT.

An MVP-scoping guide for startups. An MVP, or minimum viable product, is the smallest version that can test whether the core product idea provides value.

In plain words
What is it for?
Use it to review a product requirements document, trim a sprint plan, or classify features as must-have, should-have, could-have, or not-now before launch.
Why use it?
It reduces feature lists that are too large to build or launch quickly. It separates essential work from useful extras and items that should wait or be removed.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the forged-claude-code plugin — 29 skills, 14 commands, 9 agents, 2 hooks shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/dokkabei97/forged-claude-code/scope-cutter
Any agent
npx skills add Dokkabei97/forged-claude-code --skill scope-cutter
Clone the repo
git clone --depth 1 https://github.com/Dokkabei97/forged-claude-code

Made for: Claude Code.

Or install forged-claude-code, the plugin that ships this one along with the rest of its 29 skills, 14 commands, 9 agents, 2 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for scope-cutter

README.md
[![agentmods](https://agentmods.dev/badge/skills/dokkabei97/forged-claude-code/scope-cutter.svg)](https://agentmods.dev/skills/dokkabei97/forged-claude-code/scope-cutter)
Your own site
<a href="https://agentmods.dev/skills/dokkabei97/forged-claude-code/scope-cutter"><img src="https://agentmods.dev/badge/skills/dokkabei97/forged-claude-code/scope-cutter.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,118 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.01118
Opus 5 $0.00023 $0.00559
Sonnet 5 $0.00009 $0.00224
Haiku 4.5 $0.00005 $0.00112

Measured 6d ago against content hash 42a2bbdc749d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

scope-cutter scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/cpo/scope-cutter/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scope Cutter - MVP Scoping for Startups

Overview

Ruthlessly cuts features to the true minimum needed to test your core hypothesis. The best MVP is embarrassingly small — but it ships.


1. When to Apply

Trigger Behavior
PRD review with too many features Guided scope reduction
"MVP scope", "what to cut" Feature triage workflow
Sprint overcommit detected Emergency scope reduction
Pre-launch feature list review Ship/defer/kill classification

2. The Scope Cutting Framework

Step 1: Identify Core Value Proposition

Ask the critical question:

"If your product could only do ONE thing, what would it be?"

This becomes the Core Job — everything else is evaluated against it.

Step 2: Feature Triage (MoSCoW + Startup Twist)

Classify every feature:

Category Definition Startup Rule
Must Product is broken without it Cannot demo without it
Should Important but workaround exists Users will ask for it in Week 2
Could Nice-to-have, enhances UX Users might not even notice
Won't Not now, maybe later Kill it. No "maybe later" backlog bloat

Step 3: Apply Cutting Rules

The 5 Cutting Questions:

  1. Does it test our core hypothesis? No → Cut
  2. Can users achieve the core job without it? Yes → Cut
  3. Would we learn something new by building it? No → Cut
  4. Can we fake it manually first? Yes → Cut (do it manually)
  5. Does it need to exist at launch? No → Cut

Common "Feels Essential but Isn't" Features:

  • Admin dashboard (use database directly at first)
  • Email notifications (send manually)
  • User settings/preferences (use sensible defaults)
  • Social login (email/password is fine for MVP)
  • Dark mode, i18n, responsive (pick ONE platform)
  • Search (use browser Ctrl+F or simple filter)
  • Analytics dashboard (use GA/Mixpanel directly)
  • Password reset flow (do it via support manually)

Read the full file on GitHub · 152 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 152 lines · 45 tokens per session scan A 42a2bbdc749d

Subscribe to this mod's changes

scope-cutter is a skill published in the GitHub repository Dokkabei97/forged-claude-code (2 stars, last pushed 6mo ago), licensed MIT. It adds 45 tokens to every session and 1,118 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.