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.
git clone --depth 1 https://github.com/HasData/booking-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/commands/hasdata/booking-mcp/hotel-shortlist)<a href="https://agentmods.dev/commands/hasdata/booking-mcp/hotel-shortlist"><img src="https://agentmods.dev/badge/commands/hasdata/booking-mcp/hotel-shortlist/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/commands/hasdata/booking-mcp/hotel-shortlist"><img src="https://agentmods.dev/badge/commands/hasdata/booking-mcp/hotel-shortlist.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 | $0.00013 | $0.00332 |
| Opus 5.5 | $0.00005 | $0.00133 |
| Sonnet 5.5 | $0.00003 | $0.00066 |
| Haiku 4.5 | $0.00001 | $0.00033 |
Grade A, and why
hotel-shortlist 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 23d 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.
What it actually says
Build a hotel shortlist.
Ask me for the destination, the dates and the party if I have not given them. Booking needs all of it: check-in, check-out, rooms, adults, and children with their ages.
Then:
- Call
hasdata_booking_search_getBookingSearchResultswith those values, plusprice_max_if I gave a budget. Setcurrencywhen I gave the budget in one, because the band is read in that currency. - Report how many properties came back. Nothing available means the dates are full, not that the destination is wrong.
- Shortlist five: name,
pricePerStayParsed, theexcludedChargesParsedbeside it when the result carries the pair, the starratingout of 5, the guest scorereviews.scoreout of 10 withreviews.count, and the distance to the centre if the payload carries it. Label the two scores so nobody reads a 3 and a 9.4 as the same measure. - Sort by value rather than raw price, and say what you traded. The cheapest room in the wrong district is not the cheapest stay.
- Open
hasdata_booking_place_getBookingPlaceDetailsfor the two I pick, passing the same dates and party alongside the URL, because that tool requires them too. Report the room types, the cancellation terms and what recent reviewers mention.
Every number belongs to the dates I asked about. Repeat them next to the prices so nobody quotes a total for the wrong weekend.
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.
- 23d ago First seen · 18 lines · 13 tokens per session scan A 7b3067a814f2
hotel-shortlist is a command published in the GitHub repository HasData/booking-mcp (11 stars, last pushed 4d ago), licensed MIT. It adds 13 tokens to every session and 332 once invoked, about $0.0001 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 2026-09-23.
Other commands, from other repositories
profile-brief
A brief on a public Instagram account and what it has been posting.
zillow-comps
Comparable sales for an address or an area, pulled from Zillow.
hiring-map
Who is hiring for a role across several cities, with salaries where employers publish them.
tiktok-pulse
What an account posts on TikTok and which videos actually performed.
stay-shortlist
A shortlist of Airbnb stays for a destination, dates and party size.
ddg-baseline
An unpersonalised ranking for a query, used as a baseline.