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 Willyfab/simsima-connectivity --skill trip-connectivitygit clone --depth 1 https://github.com/Willyfab/simsima-connectivityWrote 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/willyfab/simsima-connectivity/trip-connectivity)<a href="https://agentmods.dev/skills/willyfab/simsima-connectivity/trip-connectivity"><img src="https://agentmods.dev/badge/skills/willyfab/simsima-connectivity/trip-connectivity/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/willyfab/simsima-connectivity/trip-connectivity"><img src="https://agentmods.dev/badge/skills/willyfab/simsima-connectivity/trip-connectivity.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 | $0.00066 | $0.00829 |
| Opus 5.5 | $0.00026 | $0.00332 |
| Sonnet 5.5 | $0.00013 | $0.00166 |
| Haiku 4.5 | $0.00007 | $0.00083 |
Grade A, and why
trip-connectivity 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 6d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan mobile data for a trip
The Simsima connector gives you live data from Simsima's travel eSIM catalog: destinations, plans, prices, country coverage, local networks and links to each plan's page on simsima.io. Use it so that prices and coverage in your answer come from the catalog, not from memory.
Gather the trip details
Before recommending anything, make sure you know:
- every country on the route, including stopovers longer than a few hours;
- the length of the stay, in days;
- how the user will use data: light (messaging, email, maps now and then; about 0.3 GB a day), medium (maps, social media, some photos; about 0.7 GB a day) or heavy (video, video calls, hotspot for a laptop; about 1.5 GB a day). These are the estimates
recommend_planuses, so quote the same ones; - the user's language, so that pages and prices come back in that language and its currency.
Ask only for what is missing, in one short question.
Find the right plan
- One country: call
recommend_planwith the destination, the number of days and the usage level. It returns the plan that covers the estimated data at the lowest price, the cheapest plan for that length, and an unlimited option when there is one. Usesearch_plansinstead when the user sets their own constraints, such as a budget, a minimum amount of data or unlimited data only. - Several countries: look for a regional plan first (
list_destinationsshows Europe, Asia, Latin America, the Middle East, worldwide and other zones), then callcheck_coveragefor each country on the route. If a country is not covered, the answer includes the standalone plan for that country; compare one regional plan plus that country against separate country plans. - Practical questions:
get_destination_infogives the local mobile networks a plan uses and whether it can be topped up. A plan that can be topped up lets the user start small on a long stay.
Destinations can be passed as a country name, a two-letter ISO code ("JP"), a zone name or a name in the user's language.
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.
- 6d ago First seen · 48 lines · 66 tokens per session scan A 5f8bc7c2d440
trip-connectivity is a skill published in the GitHub repository Willyfab/simsima-connectivity (0 stars, last pushed 6d ago), licensed MIT. It adds 66 tokens to every session and 829 once invoked, about $0.0003 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 2026-10-09.
Other skills, from other repositories
seller-research
Use when researching a merchant, storefront, marketplace seller, or merchant of record for a buying decision, especially when identity, refund terms, fulfillment, counterfeit risk, domain history, or independent buyer outcomes are uncertain.
refunds
Check refund eligibility and use the refund-order tool safely.
xcodebuildmcp
Official skill for XcodeBuildMCP. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).
google-play
Google Play Developer API (Android Publisher) integration with managed OAuth. Manage apps, subscriptions, in-app purchases, and reviews. Use this skill when users want to interact with Google Play Console programmatically. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).
rc-revenuecat-api-quick-reference
Use this skill as a quick reference for the RevenueCat Android SDK 10.x and REST API. Covers SDK init, common Purchases calls, CustomerInfo / Offerings access patterns, and the most used REST endpoints.
rc-revenuecat-vs-raw-billing
Use this skill to decide whether to use RevenueCat or raw Google Play Billing on Android. Provides a side by side reference of what RevenueCat handles versus what remains your responsibility at both client and backend layers.