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 AwardTravelFinder/mcp --skill find-my-bookings-and-balancesgit clone --depth 1 https://github.com/AwardTravelFinder/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/awardtravelfinder/mcp/find-my-bookings-and-balances)<a href="https://agentmods.dev/skills/awardtravelfinder/mcp/find-my-bookings-and-balances"><img src="https://agentmods.dev/badge/skills/awardtravelfinder/mcp/find-my-bookings-and-balances/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/awardtravelfinder/mcp/find-my-bookings-and-balances"><img src="https://agentmods.dev/badge/skills/awardtravelfinder/mcp/find-my-bookings-and-balances.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 | $0.00097 | $0.01004 |
| Opus 5.5 | $0.00039 | $0.00402 |
| Sonnet 5.5 | $0.00019 | $0.00201 |
| Haiku 4.5 | $0.00010 | $0.00100 |
Grade A, and why
find-my-bookings-and-balances 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 2d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find my bookings and points balances
Plan: needs Premium:
import_booking,update_points_balance,import_balances_from_image,list_hotel_bookings. If the user is on the free plan, tell them before you search.
Do not over-promise: do not offer to schedule or do something later unless a real tool exists for it. Call
list_points_balancesbeforeupdate_points_balanceand reuse its program slugs.
Award Travel Finder cannot read the user's email or browser. You use the user's own connectors, then pass what you find to the tools below.
Hard rules
- Never ask the user for a password, a one-time code, or security answers. Never type credentials into any page.
- The user signs in themselves. If a page shows a login form, skip that programme and tell the user.
- Read only. Do not book, cancel, change, redeem, transfer, buy, reply to, delete or move anything, in email or on any site.
- Do not paste email bodies or page text back to the user. Pass them only to the tools below.
1. Check what you can use
- Look at your available tools. Note each email connector (Gmail, Outlook, Apple Mail) and each browser or computer control tool.
- If you have neither, stop. Tell the user to connect an email or browser connector, or to upload screenshots for
import_balances_from_image. - Call
list_points_balances,list_loyalty_statuses,list_flight_bookingsandlist_hotel_bookings. This is the baseline. You report changes against it at the end.
2. Email pass (do this first: it is fast and needs no sign-in)
Bookings. Follow the search and import steps in the import-bookings-from-inbox skill. Import oldest first with import_booking.
Balances. Programmes send a balance in their monthly statement and account emails. Search the last 3 months, for example in Gmail:
subject:(statement OR "account summary" OR "your balance" OR "points balance" OR "miles balance" OR "activity") newer_than:3mfrom:(ba.com OR united.com OR aa.com OR delta.com OR virginatlantic.com OR flyingblue.com OR aircanada.com OR marriott.com OR hilton.com OR hyatt.com OR ihg.com OR americanexpress.com OR chase.com) subject:(balance OR statement) newer_than:3m
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.
- 2d ago First seen · 68 lines · 97 tokens per session scan A 996a5645dfa7
find-my-bookings-and-balances is a skill published in the GitHub repository AwardTravelFinder/mcp (12 stars, last pushed 3d ago), licensed MIT. It adds 97 tokens to every session and 1,004 once invoked, about $0.0004 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 2026-10-15.
Other skills, from other repositories
fetch-playwright
Interactive browser automation (click, type, wait, screenshot, navigate) for dynamic pages that need user-like actions — pagination, login, form submission, infinite scroll. Uses Microsoft's official @playwright/mcp server; no autosearch-side Python. Use when fetch-jina and fetch-crawl4ai still cannot get the content.
fetch-crawl4ai
Deep URL fetch using crawl4ai (Playwright-powered) for JS-rendered pages, anti-bot sites, and dynamic content. Slower than fetch-jina but handles sites that block simple fetchers. Requires user-installed crawl4ai package.
sec_edgar
US public company filings (10-K, 10-Q, 8-K) via SEC EDGAR full-text search — financial and regulatory disclosures for research.
xueqiu
Chinese stock market platform — stock search, trending posts, hot stock rankings. Use for financial/investment queries in Chinese.
blazemeter-usage-billing
Guide for BlazeMeter Usage & Billing, including credit types and charging. Use when working with usage and billing for (1) Understanding BlazeMeter credit types (VU, VUH, Tests), (2) Calculating credit consumption for different test types, or any other usage and billing tasks.
scrape-batch
Extract many known URLs in one polite, rate-limited pass. Use when the user hands over a list of links, a set of search hits to read in full, or asks to "scrape these pages" / "pull the content from all of them". Drives extract(action="batch"), which fans out with per-domain rate limiting and returns partial results…