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 skills add san-npm/skills-ws --skill mvp-launchergit clone --depth 1 https://github.com/san-npm/skills-wsWrote 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/san-npm/skills-ws/mvp-launcher)<a href="https://agentmods.dev/skills/san-npm/skills-ws/mvp-launcher"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/mvp-launcher/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/san-npm/skills-ws/mvp-launcher"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/mvp-launcher.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00079 | $0.05835 |
| Opus 5 | $0.00039 | $0.02917 |
| Sonnet 5 | $0.00016 | $0.01167 |
| Haiku 4.5 | $0.00008 | $0.00583 |
Grade A, and why
mvp-launcher 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 12d 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MVP Launcher
1. Validate Before Building
Minimum validation checklist (do ALL before writing code):
- Problem interviews with 5+ target users (ask about pain, not your solution — see interview script in §13)
- Competitor analysis — list top 5, identify gaps
- Landing page + waitlist (a no-code builder like Carrd, Framer, or a single Next.js page) — target 100+ signups or 5%+ visitor→signup conversion
- Fake-door test: advertise the feature, measure clicks before building (read the ethics rules below first)
- Define success metric: "MVP is successful if X users do Y within Z days"
Kill signals: <50 waitlist signups after 500 visits, zero users willing to pay, problem already solved well by incumbents.
Ethical fake-door / waitlist testing — non-negotiable. A fake-door test measures intent, not deception.
- Disclose state. Label it "Join the waitlist" / "Coming soon" / "Request early access" — never imply a feature exists if clicking can't deliver it. Don't take payment for something you can't ship; if you charge to validate willingness-to-pay, use a refundable pre-order/deposit and say so.
- Minimize data. Collect only an email (and optionally one qualifying question). No unnecessary PII; no pre-checked marketing opt-ins. State why you're collecting it and add a one-line privacy note + link (see §10).
- Honor the implied promise. Email everyone who signed up — even if you kill the idea ("we're not building this") — and let them unsubscribe.
- Don't run misleading paid ads. Ad platforms (and consumer-protection law in the EU/UK/US) prohibit advertising products that don't exist or can't be bought. Frame ads as "early access / beta," not "buy now."
For deeper interview technique and ongoing feedback loops, pair this with the customer-feedback skill; for early-community and waitlist growth tactics, see community-building.
2. Scope with MoSCoW
| Priority | Definition | Example |
|---|---|---|
| Must | Product is useless without it | Core value proposition, auth, data persistence |
| Should | Expected but can workaround | Email notifications, search, mobile responsive |
| Could | Nice to have, adds polish | Dark mode, export, keyboard shortcuts |
| Won't | Explicitly cut for v1 | Admin dashboard, API, integrations, i18n |
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.
- 12d ago First seen · 316 lines · 79 tokens per session scan A b3fe4dc4f545
mvp-launcher is a skill published in the GitHub repository san-npm/skills-ws (2 stars, last pushed 5d ago), licensed MIT. It adds 79 tokens to every session and 5,835 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…