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 aimeos/pagible --skill launchgit clone --depth 1 https://github.com/aimeos/pagibleWrote 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/aimeos/pagible/launch)<a href="https://agentmods.dev/skills/aimeos/pagible/launch"><img src="https://agentmods.dev/badge/skills/aimeos/pagible/launch/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/aimeos/pagible/launch"><img src="https://agentmods.dev/badge/skills/aimeos/pagible/launch.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 | $0.00051 | $0.01047 |
| Opus 5.5 | $0.00020 | $0.00419 |
| Sonnet 5.5 | $0.00010 | $0.00209 |
| Haiku 4.5 | $0.00005 | $0.00105 |
Grade A, and why
launch 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Launch Theme Design System
Direction
Use a confident, precise and calm layout like the best product sites (Linear, Vercel, Stripe, Resend): lots of whitespace, one clear message per section and the product itself as the main visual. Lead with the outcome for the user, show the product right below the hero, then prove it with customer logos, features, numbers and testimonials, and close with pricing, questions and a call to action. Show real product screenshots or clean UI mockups; avoid generic stock photos of people pointing at screens, abstract 3D blobs and decorative illustrations without meaning.
Foundations
- Use only the markup and classes supplied by
./theme/views/. - Use system fonts (Inter or Geist if installed) with tight letter-spacing on headings, monospace for dates and code, and the existing
--pico-*variables. - Keep page content within a
1200pxmaximum width and text sections within46rem. - Use zinc neutrals (
#09090B,#3F3F46,#71717A,#FAFAFA) for text and surfaces, indigo (#4F46E5,#A5B4FCin dark mode) for links, primary buttons and glows, and the indigo to violet to cyan gradient only for accents in headlines (*...*), icon tiles and figures. - Support light and dark mode; never place fixed light colors on themeable backgrounds.
- Use
0.75remcorners, pill-shaped buttons and badges and thin borders instead of heavy shadows.
Components
- Hero: centered text with a pill eyebrow for news ("New: …"), a headline of at most eight words with an accent in
*...*, one sentence of text, a primary and a secondary action, and a wide 16:10 product screenshot infiles. - Logos:
cardsin thebadgeslayout with company names and optional monochrome logos directly below the hero. - Features:
cardsin three columns with six items form a bento grid; give the 1st and 4th card a longer text because they span two columns, and use white line icons as SVG images. - Feature details:
image-textwithgrid-end/grid-startalternating, a screenshot, an H2 with an accent, a sentence and three bullet points starting with a bold keyword. - Figures:
cardsin thefigureslayout with four short numbers (uptime, customers, speed, rating). - Testimonials: six quotes with name, role and company and round portraits; put the strongest quote first.
- Pricing: three or four plans with monthly and yearly prices (same
unitvalues in every plan), a free plan, one highlighted plan with the badge "Most popular" and an enterprise plan with "Custom" and a "Talk to sales" link. For checkout, setaccess,urland priceid,kind,interval,currencyandreference. Follow with a comparisontableand questions about billing. - Changelog: a
verticaltimeline with dates as labels, the release as title and Markdown bullet lists with the changes, newest first. - FAQ: six
questionswith short, direct answers about the free plan, billing, data storage and discounts. - Call to action: one
ctabefore the footer with a headline accent, a short sentence and two buttons. - Footer: cards with a short product blurb first, then product, company and legal links; the layout adds the status link, notice and copyright.
- Product details: the
productconfig adds theSoftwareApplicationJSON-LD, the announcement bar, "Sign in" and "Get started" in the header and the status pill in the footer.
What ships with it
60 files 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.
- .gitattributes 60 B
- composer.json 1.1 KB
- database/seeders/LaunchDemo.php 84 KB
- i18n/af.po 3.7 KB
- i18n/ar.po 4.0 KB
- i18n/az.po 3.8 KB
- i18n/bg.po 4.4 KB
- i18n/ca.po 3.8 KB
- i18n/cs.po 3.7 KB
- i18n/da.po 3.6 KB
- i18n/de.po 3.6 KB
- i18n/el.po 4.5 KB
- i18n/en.po 3.6 KB
- i18n/es.po 3.8 KB
- i18n/et.po 3.5 KB
- i18n/fa.po 4.3 KB
- i18n/fi.po 3.6 KB
- i18n/fr.po 3.8 KB
- i18n/he.po 4.0 KB
- i18n/hr.po 3.7 KB
- i18n/hu.po 3.7 KB
- i18n/id.po 3.7 KB
- i18n/it.po 3.7 KB
- i18n/ja.po 3.9 KB
- i18n/km.po 5.1 KB
- i18n/ko.po 3.7 KB
- i18n/lt.po 3.8 KB
- i18n/lv.po 3.7 KB
- i18n/messages.pot 2.8 KB
- i18n/nl.po 3.6 KB
- i18n/no.po 3.6 KB
- i18n/pl.po 3.7 KB
- i18n/pt-BR.po 3.8 KB
- i18n/pt.po 3.8 KB
- i18n/ro.po 3.7 KB
- i18n/ru.po 4.5 KB
- i18n/sk.po 3.7 KB
- i18n/sl.po 3.7 KB
- i18n/sr.po 4.3 KB
- i18n/sv.po 3.6 KB
- i18n/th.po 4.9 KB
- i18n/tr.po 3.7 KB
- i18n/uk.po 4.4 KB
- i18n/vi.po 3.9 KB
- i18n/zh-TW.po 3.5 KB
- i18n/zh.po 3.5 KB
- lang/af.json 119 B
- lang/ar.json 154 B
- lang/az.json 123 B
- lang/bg.json 155 B
- lang/ca.json 131 B
- lang/cs.json 126 B
- lang/da.json 119 B
- lang/de.json 121 B
- lang/el.json 162 B
- lang/en.json 119 B
- lang/es.json 138 B
- lang/et.json 118 B
- lang/fa.json 139 B
- lang/fi.json 132 B
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 · 49 lines · 51 tokens per session scan A aa536713fdfc
launch is a skill published in the GitHub repository aimeos/pagible (596 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 1,047 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-14.
Other skills, from other repositories
strapi-cms
Customisable headless CMS with Strapi.
payload
Use when working with Payload projects (payload.config.ts, collections, fields, hooks, access control, Payload API). Use when debugging validation errors, security issues, relationship queries, transactions, or hook behavior.
api-integration-architect
Design, implement, debug, and optimize API integrations with expert-level patterns for REST, GraphQL, webhooks, and authentication flows.
scalar-design-system
Scalar's design system — design tokens, theming (@scalar/themes), CSS variables, and the @scalar/components library. Use when designing or implementing Scalar UI, especially with Paper (code-to-design / design-to-code), so output matches real Scalar tokens, colors, typography, spacing, and components instead of…
lap
LAP CLI -- compile, search, and manage API specs for AI agents. Use when working with API specifications (OpenAPI, GraphQL, AsyncAPI, Protobuf, Postman), compiling specs to LAP format, searching the LAP registry, generating skills from API specs, or publishing APIs. Commands: init, compile, search, get, skill…
api-connector-builder
Use when writing a client for someone else's REST or GraphQL API: auth flow choice and token refresh, pagination to exhaustion, retry-with-jitter on transient failures only, rate-limit-aware throttling. NOT inbound callbacks (that is webhooks), NOT chaining services (that is automation-flows), NOT designing your own…