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/ilpr/waitlister-mcp/getting-startednpx skills add ilpr/waitlister-mcp --skill getting-startedgit clone --depth 1 https://github.com/ilpr/waitlister-mcpWrote 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/ilpr/waitlister-mcp/getting-started)<a href="https://agentmods.dev/skills/ilpr/waitlister-mcp/getting-started"><img src="https://agentmods.dev/badge/skills/ilpr/waitlister-mcp/getting-started.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 | $0.00987 |
| Opus 5 | $0.00051 | $0.00494 |
| Sonnet 5 | $0.00020 | $0.00197 |
| Haiku 4.5 | $0.00010 | $0.00099 |
Grade A, and why
waitlister-getting-started 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 3d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Getting started with Waitlister
Waitlister is waitlist software for product launches: a hosted landing page, signups with queue positions, and a referral program where referrals move people up the list.
1. Make sure there's an API key
Every tool here needs WAITLISTER_ACCOUNT_KEY set in the environment. If a tool call
fails with an authentication error, or the user has never used Waitlister here before,
walk them through it:
- Create a free account at https://waitlister.me (no credit card).
- Go to Settings → API keys and create an account API key — it starts with
wl_acct_. - Set it as
WAITLISTER_ACCOUNT_KEYin the environment and restart the session.
Account keys work on every plan, including free, and can create waitlists on their own — the user never needs to touch the dashboard to get started.
Never ask the user to paste the key into the chat. If they do anyway, tell them to revoke it in Settings → API keys and issue a new one.
Confirm the key with get_account before doing anything else. It is read-only and
answers three things in one call: whether the key is alive (an invalid or revoked key
fails here, so a dead key stops looking like a malformed request), the plan, and
waitlists.can_create — whether the next create_waitlist would actually succeed. Check
that rather than discovering the plan's waitlist cap from an error partway through a setup.
2. Launch a waitlist in one step
create_waitlist provisions the waitlist and its landing page in a single call — prefer
this over creating them separately:
name— the product name (required).landing_page— pass{ headline, description, button_text, collect_name, theme }to get a hosted page as a draft in the same call.headlineis required, 3–120 characters.
Then publish_landing_page takes it live at waitlister.me/p/{slug}. Report the live URL
back to the user, and mention that form_action_url from the create response already
collects signups on any site (the domain must be whitelisted in the waitlist's settings).
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.
- 3d ago First seen · 81 lines · 101 tokens per session scan A efb9e9a8421c
waitlister-getting-started is a skill published in the GitHub repository ilpr/waitlister-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 101 tokens to every session and 987 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
Landing Page Copy Improver
Rewrites landing page copy to be more compelling, benefit-focused, and conversion-optimized.
copy
Professional copywriter for SaaS and startups. Expert in landing page copy, positioning, messaging, conversion optimization, and voice-of-customer research. Use when writing compelling copy for SaaS products, landing pages, marketing materials, or when you need help with product positioning and messaging strategy.
new-landing
Создать новый статический лендинг в этой системе по паттерну (встроенные SEO, аналитика, A/B), прогнать самопроверку и завести ветку с превью-URL. Использовать, когда нужно сделать новый лендинг / посадочную страницу, вариант под кампанию или гипотезу для A/B. Это dev-time генератор (вариант A из дорожной карты…
init-landing-system
Развернуть систему генерации лендингов (скиллы new-landing/landing-experiment/landing-journal/landing-ads + CI + nginx + docs/adr + experiments + стартовые README/CLAUDE) в уже существующем проекте. Использовать, когда нужно поставить эту систему в другой репозиторий/проект, забутстрапить лендинг-проект с нуля или…
landing-ads
Подготовить рекламные материалы для лендинга — UTM-разметку, тексты объявлений, ключевые фразы и минус-слова под Яндекс.Директ и Google Ads, с экспортом для Директ.Коммандера / Google Ads Editor. Использовать, когда нужно завести рекламную кампанию на лендинг или вариант A/B. Генерирует артефакты (без трат и без живых…
landing-experiment
Создать A/B-эксперимент на лендинге — из брифа и гипотезы сгенерировать вариант(ы) на одном URL (inline-сплит, SEO-безопасно), настроить трекинг варианта в Метрике/GA4, завести карточку эксперимента и записи в аудит-журнал, выдать чеклист запуска. Использовать, когда нужно подготовить A/B-тест, вариант под гипотезу…