cabin-codes

cabin-codes is a skill for Claude Code from borski/travel-hacking-toolkit. It costs 36 tokens per session (397 once invoked), scanned A, original, MIT.

A guide to the letter codes used for airline cabins and award-seat inventory. It explains F, J, W, and Y for first, business, premium economy, and economy, plus X, I, and O saver-fare codes.

In plain words
What is it for?
Use it to interpret award-search results, identify saver seats, and understand which cabin or fare class a flight represents.
Why use it?
It makes airline search results easier to read and shows when seats may be bookable through a partner programme at a different price.

Skill for Claude Code

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

Part of the travel-hacker plugin — 48 skills, 1 agent, 6 MCP servers shipped together

Good fit Use it to interpret award-search results, identify saver seats, and understand which…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/borski/travel-hacking-toolkit/cabin-codes
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 borski/travel-hacking-toolkit --skill cabin-codes
Clone the repo
git clone --depth 1 https://github.com/borski/travel-hacking-toolkit

Made for: Claude Code.

Or install travel-hacker, the plugin that ships this one along with the rest of its 48 skills, 1 agent, 6 MCP servers.

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 cabin-codes

README.md
[![agentmods](https://agentmods.dev/badge/skills/borski/travel-hacking-toolkit/cabin-codes.svg)](https://agentmods.dev/skills/borski/travel-hacking-toolkit/cabin-codes)
Your own site
<a href="https://agentmods.dev/skills/borski/travel-hacking-toolkit/cabin-codes"><img src="https://agentmods.dev/badge/skills/borski/travel-hacking-toolkit/cabin-codes.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 397 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 $0.00036 $0.00397
Opus 5 $0.00018 $0.00198
Sonnet 5 $0.00007 $0.00079
Haiku 4.5 $0.00004 $0.00040

Measured 7d ago against content hash aea2d5ae57b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cabin-codes 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 7d 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.

plugins/travel-hacking-toolkit/skills/cabin-codes/SKILL.md · 34 lines

What it actually says

Cabin Codes

When reading Seats.aero results or discussing award inventory, these cabin codes appear:

Code Cabin Notes
F First Class Includes true first class suites
J Business Class Lie-flat seats on long-haul
W Premium Economy Also sometimes coded as "P"
Y Economy Standard seating

Fare Class Codes for Saver Awards

These are critical for partner bookings. If you see these fare codes available on united.com (or equivalent), the flight is bookable through partner programs at their (often lower) rates.

Code Meaning Programs That Use It
X Economy Saver United MileagePlus, bookable through partners
I Business Saver United MileagePlus, bookable through Turkish M&S and others
O First Saver United MileagePlus

Why This Matters

Partner award rates are often dramatically lower than the operating airline's own rates. United business saver (I class) bookable through Turkish Miles&Smiles is a classic example: a route that costs 80,000 United miles might only cost 45,000 Turkish miles. But Turkish (and other partners) only sees the saver inventory. If only "standard" or "everyday" fares show on united.com, partners cannot book that flight.

When checking award availability for a flight you found on a partner program (Turkish, Aeroplan, ANA, etc.), verify the saver class is open on the operating airline's site before transferring points.

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. 7d ago First seen · 34 lines · 36 tokens per session scan A aea2d5ae57b0

Subscribe to this mod's changes

cabin-codes is a skill published in the GitHub repository borski/travel-hacking-toolkit (652 stars, last pushed 6d ago), licensed MIT. It adds 36 tokens to every session and 397 once invoked, about $0.0002 per session on Opus 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 2026-08-30.