duffel

duffel is a skill for Claude Code from borski/travel-hacking-toolkit. It costs 41 tokens per session (2,037 once invoked), scanned A, original, MIT.

A flight-search guide that uses the Duffel service to find current airline offers, including prices, cabins, baggage details, and booking links.

In plain words
What is it for?
Use it to search one-way, return, or multi-city flights, choose a cabin, and set preferred travel times.
Why use it?
It gives you live cash fares with details that can vary by fare type, while excluding Southwest flights.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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

Good fit Use it to search one-way, return, or multi-city flights, choose a cabin, and set preferred travel times.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/borski/travel-hacking-toolkit/duffel
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 duffel
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 duffel

README.md
[![agentmods](https://agentmods.dev/badge/skills/borski/travel-hacking-toolkit/duffel.svg)](https://agentmods.dev/skills/borski/travel-hacking-toolkit/duffel)
Your own site
<a href="https://agentmods.dev/skills/borski/travel-hacking-toolkit/duffel"><img src="https://agentmods.dev/badge/skills/borski/travel-hacking-toolkit/duffel.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,037 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 6 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 7
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 32
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 55
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 85
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 108
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 199
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 $0.00041 $0.02037
Opus 5 $0.00020 $0.01019
Sonnet 5 $0.00008 $0.00407
Haiku 4.5 $0.00004 $0.00204

Measured 8d ago against content hash 7214acbac149, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

duffel scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

allowed-tools: Bash(curl *)
plugins/travel-hacking-toolkit/skills/duffel/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Duffel Flights

Search for real-time flight offers across airlines via the Duffel API. Returns live pricing, cabin details, baggage info, and booking links. Supports one-way, round-trip, and multi-city searches.

Source: duffel.com

Prerequisites

  • DUFFEL_API_KEY_LIVE environment variable set with a live API token
  • Token needs air.offer_requests.create permission

API Basics

  • Base URL: https://api.duffel.com
  • Version header: Duffel-Version: v2 (REQUIRED, v1 is deprecated)
  • Auth: Authorization: Bearer $DUFFEL_API_KEY_LIVE
  • Content-Type: application/json
  • Rate limit: 60 requests per 60 seconds

Search Flights (One-Way)

curl -s -X POST "https://api.duffel.com/air/offer_requests?return_offers=true&supplier_timeout=15000" \
  -H "Accept: application/json" \
  -H "Duffel-Version: v2" \
  -H "Authorization: Bearer $DUFFEL_API_KEY_LIVE" \
  -H "Content-Type: application/json" \
  -d '{
    "data": {
      "slices": [{
        "origin": "SFO",
        "destination": "NRT",
        "departure_date": "2026-08-15"
      }],
      "passengers": [{"type": "adult"}],
      "cabin_class": "economy"
    }
  }'

Search Flights (Round-Trip)

Add a second slice with origin/destination reversed:

curl -s -X POST "https://api.duffel.com/air/offer_requests?return_offers=true&supplier_timeout=15000" \
  -H "Accept: application/json" \
  -H "Duffel-Version: v2" \
  -H "Authorization: Bearer $DUFFEL_API_KEY_LIVE" \
  -H "Content-Type: application/json" \
  -d '{
    "data": {
      "slices": [
        {
          "origin": "SFO",
          "destination": "NRT",
          "departure_date": "2026-08-15"
        },
        {
          "origin": "NRT",
          "destination": "SFO",
          "departure_date": "2026-08-22"
        }
      ],
      "passengers": [{"type": "adult"}],
      "cabin_class": "business"
    }
  }'

Search Flights (Multi-City)

Add as many slices as needed:

Read the full file on GitHub · 244 lines

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. 8d ago First seen · 244 lines · 41 tokens per session scan A 7214acbac149

Subscribe to this mod's changes

duffel is a skill published in the GitHub repository borski/travel-hacking-toolkit (653 stars, last pushed 7d ago), licensed MIT. It adds 41 tokens to every session and 2,037 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.