scope-mvp

scope-mvp is a skill for Claude Code, Codex from impactbrussels/FounderOS. It costs 101 tokens per session (1,320 once invoked), scanned A, original, Apache-2.0.

A planning skill that helps a founder choose the smallest first version of a product. An MVP is the cheapest experiment that tests the riskiest assumption about whether people will use or pay for the product.

In plain words
What is it for?
Use it to identify the key assumption, reduce a feature list, choose what to build first, and define what must be true before shipping.
Why use it?
It prevents a first release from quietly expanding into a large product before the main idea has been tested.

Skill for Claude CodeCodex

Part of the founderos plugin — 23 skills, 3 agents 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/impactbrussels/founderos/scope-mvp
Any agent
npx skills add impactbrussels/FounderOS --skill scope-mvp
Clone the repo
git clone --depth 1 https://github.com/impactbrussels/FounderOS

Made for: Claude Code, Codex.

Or install founderos, the plugin that ships this one along with the rest of its 23 skills, 3 agents.

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-mvp

README.md
[![agentmods](https://agentmods.dev/badge/skills/impactbrussels/founderos/scope-mvp.svg)](https://agentmods.dev/skills/impactbrussels/founderos/scope-mvp)
Your own site
<a href="https://agentmods.dev/skills/impactbrussels/founderos/scope-mvp"><img src="https://agentmods.dev/badge/skills/impactbrussels/founderos/scope-mvp.svg" alt="Measured on agentmods" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,320 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 $0.00101 $0.01320
Opus 5 $0.00051 $0.00660
Sonnet 5 $0.00020 $0.00264
Haiku 4.5 $0.00010 $0.00132

Measured 4d ago against content hash 4f152560bd11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scope-mvp 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 4d 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/scope-mvp/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scope the MVP

The most expensive mistake at this stage is the "tiny version of the full product." Founders list every feature, cut the list in half, and call the rest an MVP - then spend three months building something that still tests nothing. A real MVP is not small-everything; it is the smallest experiment that could prove your riskiest assumption wrong. Often it isn't even software. This skill keeps you honest about what you're actually trying to learn, and ships the cheapest thing that learns it.

The method

Built on the Founder OS scaffold (High tier). Full MVP-type menu, cut-lists, and definition-of-done in references/mvp-scoping.md.

Step 1 - Restate the one assumption you're testing

An MVP tests one thing. Name the [RISKIEST_ASSUMPTION] carried from validate-idea / customer-interviews - in plain language, falsifiable. "People will switch from X to do Y." If you can't state it in one sentence, you're not ready to scope; you're ready to interview.

Step 2 - List candidate features, then expect to cut most

Brain-dump everything the "real" product might do for [ICP] - this is a draft, not a plan, and a draft is not a decision. Sort with MoSCoW (Must / Should / Could / Won't), but judge each feature by one test only: does it help prove or disprove the assumption? If not, it's a Won't - for now.

Step 3 - Cut ruthlessly to the one core flow

Find the single thread of value - the one path a user walks to experience the core promise. Cut everything off that thread: auth, settings, dashboards, edge cases, polish. One flow, one job, one moment of "oh, this is useful." If two features survive, ask which one the assumption actually needs. Honour your [CONSTRAINT] (time, money, skills) - it's a feature, not a limit.

Step 4 - Choose the MVP type

The riskiest assumption decides the type, not your comfort with code. Concierge, Wizard-of-Oz, landing/fake-door, single-feature, or no-code - pick from the menu by matching the type to what you need to learn. The right MVP is frequently manual, faked, or no-build.

Read the full file on GitHub · 94 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 94 lines · 101 tokens per session scan A 4f152560bd11

Subscribe to this mod's changes

scope-mvp is a skill published in the GitHub repository impactbrussels/FounderOS (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 101 tokens to every session and 1,320 once invoked, about $0.0005 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.

Related

Other skills, from other repositories