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 setupgit 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/setup)<a href="https://agentmods.dev/skills/awardtravelfinder/mcp/setup"><img src="https://agentmods.dev/badge/skills/awardtravelfinder/mcp/setup/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/setup"><img src="https://agentmods.dev/badge/skills/awardtravelfinder/mcp/setup.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 | $0.00077 | $0.00896 |
| Opus 5.5 | $0.00031 | $0.00358 |
| Sonnet 5.5 | $0.00015 | $0.00179 |
| Haiku 4.5 | $0.00008 | $0.00090 |
Grade A, and why
setup 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 19d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up Award Travel Finder
The tools named below are on the Award Travel Finder MCP connector. If they are not available, tell the user to connect https://mcp.awardtravelfinder.com/mcp (setup: https://awardtravelfinder.com/developers/mcp).
Plan: may not be included in every account plan:
update_points_balance,create_route_monitorbeyond the first monitor. If a tool reports that it is not included in the account's plan, tell the user and use the other steps where the skill gives one.
Goal: a connected account, saved profile data and one real award result in a few minutes.
Rules
- The user signs in themselves. Never ask for a password, token or API key.
- Never open a sign-in link for the user.
- Ask one question set, in one message.
1. Check the connection
- Call
get_profile. - If the call fails, or the user is signed out, tell the user to approve the sign-in in their browser. Say that the sign-in takes about 30 seconds and needs no card.
- Wait for the user to confirm. Then call
get_profileagain. - If the call still fails, point the user to https://awardtravelfinder.com/developers/mcp and stop.
- Call
list_points_balancesandlist_my_cards. Do not ask for data that is already saved.
2. Ask one question set
Send one message that asks for:
- Home airport (name or code).
- The points programmes they hold, with balances.
- The credit cards they hold.
- A destination, if they have one (optional).
- Whether they want an alert when award seats open on a route.
Tell the user they can answer in part, and that screenshots work.
3. Save the answers
- Save each balance with
update_points_balance. - Save each card with
add_card. If the card name is not clear, calllist_catalogue_cardsto find it. - If the user has screenshots, use
import_balances_from_imagefor balances andimport_cards_from_imagefor cards. - If the user has a browser agent, offer the read-only capture skills. Call
get_skillwithcapture-from-airline-hotel-accountfor balances and status. Callget_skillwithcapture-cards-and-bonusesfor cards and bonuses. The user signs in themselves. - Say what you saved. Do not guess a value the user did not give.
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.
- 19d ago Changed 45177d988547
- 20d ago First seen · 72 lines · 77 tokens per session scan A 903faa854b2c
setup is a skill published in the GitHub repository AwardTravelFinder/mcp (16 stars, last pushed 20d ago), licensed MIT. It adds 77 tokens to every session and 896 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 2026-10-31.
setup compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| setupAwardTravelFinder/mcp | Skill | 16 | 20d ago | MIT | A | 77 | Claude Code |
| trader-riskmillw14/merrymen | Skill | 55 | yesterday | MIT | A | 301 | Claude Code |
| trader-budgetmillw14/merrymen | Skill | 55 | yesterday | MIT | A | 213 | Claude Code |
| trader-scannermillw14/merrymen | Skill | 55 | yesterday | MIT | A | 187 | Claude Code |
| trader-pelosimillw14/merrymen | Skill | 55 | yesterday | MIT | A | 155 | Claude Code |
| merrymen-monitormillw14/merrymen | Skill | 55 | yesterday | MIT | A | 45 | Cursor |
| connectmillw14/merrymen | Skill | 55 | yesterday | MIT | A | 58 | Claude Code |