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.
npx agentmods add skills/impactbrussels/founderos/scope-mvpnpx skills add impactbrussels/FounderOS --skill scope-mvpgit clone --depth 1 https://github.com/impactbrussels/FounderOSWrote 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.
[](https://agentmods.dev/skills/impactbrussels/founderos/scope-mvp)<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
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.
- 4d ago First seen · 94 lines · 101 tokens per session scan A 4f152560bd11
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.
Other skills, from other repositories
copilotkit-upgrade
Use when migrating a CopilotKit v1 application to v2 -- updating package imports, replacing deprecated hooks and components, switching from GraphQL runtime to AG-UI protocol runtime, and resolving breaking API changes.
metrics-instrumentation
Specification for instrumenting an opik-backend workflow with operational OpenTelemetry metrics — per-stage throughput/latency/error counters and native histograms, dimensioned per-customer (workspace). Use when a pipeline (scoring, ingestion, experiments, jobs) needs per-stage visibility. Covers metric emission only…
notifications
Send notifications through the unified notification router.
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
vellum-skills-catalog
Discover bundled skills and search/install community skills from the skills.sh registry.