agentmods.dev

cancel-or-change-award

cancel-or-change-award is a skill for Claude Code from AwardTravelFinder/mcp. It costs 69 tokens per session (533 once invoked), scanned A, original, MIT.

A guided process for cancelling, changing, or rebooking a flight bought with reward points. It checks the booking, the airline's fee, where the points will be returned, and whether a new booking costs less.

In plain words
What is it for?
Use it to inspect an award booking, calculate its cancellation fee, check loyalty-status exceptions, and compare keeping the ticket with changing or rebooking it.
Why use it?
Reward tickets can have different rules depending on which loyalty programme issued them. This helps avoid losing track of fees, refunded points, or a cheaper rebooking option.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the award-travel-finder plugin — 17 skills, 2 commands, 1 MCP server shipped together

not rated 12repo +1 2d ago A scan 69 tokens original MIT

Good fit Use it to inspect an award booking, calculate its cancellation fee, check loyalty-status exceptions, and compare keeping the ticket with changing or rebooking it.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/awardtravelfinder/mcp/cancel-or-change-award
View source ↗ AwardTravelFinder/mcp awardtravelfinder.com
Install

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.

Any agent
npx skills add AwardTravelFinder/mcp --skill cancel-or-change-award
Clone the repo
git clone --depth 1 https://github.com/AwardTravelFinder/mcp

Made for: Claude Code.

Or install award-travel-finder, the plugin that ships this one along with the rest of its 17 skills, 2 commands, 1 MCP server.

Wrote 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.

agentmods badge for cancel-or-change-award

README.md
[![agentmods](https://agentmods.dev/badge/skills/awardtravelfinder/mcp/cancel-or-change-award/github.svg)](https://agentmods.dev/skills/awardtravelfinder/mcp/cancel-or-change-award)
Your own site
<a href="https://agentmods.dev/skills/awardtravelfinder/mcp/cancel-or-change-award"><img src="https://agentmods.dev/badge/skills/awardtravelfinder/mcp/cancel-or-change-award/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.

agentmods 80×15 button for cancel-or-change-award

Your own site · 80×15
<a href="https://agentmods.dev/skills/awardtravelfinder/mcp/cancel-or-change-award"><img src="https://agentmods.dev/badge/skills/awardtravelfinder/mcp/cancel-or-change-award.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 533 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.00533
Opus 5.5 $0.00028 $0.00213
Sonnet 5.5 $0.00014 $0.00107
Haiku 4.5 $0.00007 $0.00053

Measured 20d ago against content hash 3656ecaa777c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cancel-or-change-award 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 20d 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.

skills/cancel-or-change-award/SKILL.md · 46 lines

What it actually says

Cancel or change an award

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: needs Premium: search_monthly_availability, update_flight_booking, delete_flight_booking. If the user is on the free plan, tell them before you call these tools, and use the free steps where the skill gives one.

1. Find the booking

  • Call list_flight_bookings. Match by confirmation number, route or date.
  • Call get_flight_booking for the programme, points spent and taxes.
  • Ask only for what is missing: the booking programme is the most important fact.

2. Fee

  • Call get_cancellation_fee for the airline.
  • The fee is for the airline's own programme. If the ticket was booked through a partner programme, say that the partner's rules apply and the fee can differ.
  • Check the elite exemptions in the result against list_loyalty_statuses.

3. Where the points go

  • Points return to the programme that issued the ticket, not to the bank currency they came from.
  • Taxes are refunded to the card, less the fee, when the fee is taken from taxes.

4. Change instead of cancel

  • If the user wants new dates, call search_all_airlines or search_monthly_availability for the new dates.
  • Compare: fee + new points cost vs. keeping the ticket.
  • If the new award is cheaper than the old one, rebooking can save points even after the fee.

5. Update records

  • After a change, call update_flight_booking. After a cancel, call delete_flight_booking.

Output format

  1. Fee and who is exempt.
  2. Points and taxes returned, and to where.
  3. Rebook option with the net cost, if the user wants new dates.
  4. Steps to cancel or change (online or by phone).
Changes

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.

  1. 20d ago First seen · 46 lines · 69 tokens per session scan A 3656ecaa777c

Subscribe to this mod's changes

cancel-or-change-award is a skill published in the GitHub repository AwardTravelFinder/mcp (12 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 533 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 2026-09-27.

Finance and fintechaward-travelclaude-code-pluginmcpmcp-servermodel-context-protocolpoints-and-miles
Related

Other skills, from other repositories

sec_edgar

US public company filings (10-K, 10-Q, 8-K) via SEC EDGAR full-text search — financial and regulatory disclosures for research.

0xmariowu/Autosearch · 35 tokens

xueqiu

Chinese stock market platform — stock search, trending posts, hot stock rankings. Use for financial/investment queries in Chinese.

0xmariowu/Autosearch · 30 tokens

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.

Blazemeter/bzm-mcp · 67 tokens

alpha-arcade-interaction

Trade on Alpha Arcade prediction markets on Algorand — browse markets, read orderbooks, place limit/market orders, manage positions, cancel/amend orders, split/merge shares, and claim winnings. Use when user asks about prediction markets, event betting, YES/NO shares, orderbooks, or Alpha Arcade.

GoPlausible/algorand-mcp · 71 tokens

haystack-router-interaction

Route and execute optimal token swaps on Algorand using Haystack Router via Algorand MCP tools. Use when getting best-price quotes across multiple Algorand DEXes and LST protocols, executing atomic swaps, and checking asset opt-in — all through the Algorand MCP server.

GoPlausible/algorand-mcp · 65 tokens

x402-discovery

Agents discover paid artefact rails via GET https://councilof.ai/.well-known/x402.json (mode is reported from runtime env, Base eip155:8453, USDC; amounts from challenge only — no invent price). Catalog GET /api/x402. Free door GET /api/free-door amount 0 settles and charges nothing — proves the rail. Living board GET…

CSOAI-ORG/councilof-ai · 367 tokens