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 borski/travel-hacking-toolkit --skill duffelgit clone --depth 1 https://github.com/borski/travel-hacking-toolkitWrote 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/borski/travel-hacking-toolkit/duffel)<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>- NVIDIA SkillSpector warn
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.
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 | $0.00041 | $0.02037 |
| Opus 5 | $0.00020 | $0.01019 |
| Sonnet 5 | $0.00008 | $0.00407 |
| Haiku 4.5 | $0.00004 | $0.00204 |
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 *) 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_LIVEenvironment variable set with a live API token- Token needs
air.offer_requests.createpermission
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:
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.
- 8d ago First seen · 244 lines · 41 tokens per session scan A 7214acbac149
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.
Other skills, from other repositories
docs-builder
Reorg a docs corpus, split an oversized doc, search it, keep pages current, index them.
remember
Consolidate stashes + friction into project memory.
live-canvas
Conduct design interviews, generate UI variations, and collect live click-to-annotate feedback that streams into the session so edits land without leaving the browser. Use when the user wants rapid iterative UI refinement, not just batched feedback.
branch-review
Review a branch before merge [target] [level].
root-cause
Use when any test fails, bug appears, or behaviour surprises you, before proposing a fix - find the cause and prove it, by reading real evidence, tracing bad values back to their origin, comparing against a working case, and testing one hypothesis at a time.
ship
Mechanical pre-deploy gate — tests, build, tree state.