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 agentmods add skills/borski/travel-hacking-toolkit/serpapinpx skills add borski/travel-hacking-toolkit --skill serpapigit 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/serpapi)<a href="https://agentmods.dev/skills/borski/travel-hacking-toolkit/serpapi"><img src="https://agentmods.dev/badge/skills/borski/travel-hacking-toolkit/serpapi.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.02321 |
| Opus 5 | $0.00018 | $0.01161 |
| Sonnet 5 | $0.00007 | $0.00464 |
| Haiku 4.5 | $0.00004 | $0.00232 |
Grade A, and why
serpapi scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://serpapi.com/search?engine=google_flights&departure_id=SFO&arrival_id=NRT&outbound_date=2026-08-10&type=2&adults=2&travel_class=1¤cy=USD&stops=2&sort_by=2&api_key=$SERPAPI_API_KEY" | jq '{best: [.be How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SerpAPI Skill
Scrape Google Flights, Google Hotels, and Google Travel Explore via SerpAPI. Provides cash flight prices (for Chase/Amex portal comparison), hotel pricing, and destination discovery.
Source: serpapi.com — Free tier available, paid plans for higher volume.
Authentication
SERPAPI_API_KEY is set in .env. All requests use api_key query parameter.
API Base
https://serpapi.com/search
Google Flights (Cash Prices)
Search for flight prices and schedules. Essential for comparing: "Is 88,000 United miles better than paying $900 cash through the Chase portal?" (Chase portal pricing is now dynamic via Points Boost, ~1.5-2.0 cpp on select bookings; verify the actual quote.)
One-Way Search
curl -s "https://serpapi.com/search?engine=google_flights&departure_id=SFO&arrival_id=NRT&outbound_date=2026-08-10&type=2&adults=2&travel_class=1¤cy=USD&stops=2&sort_by=2&api_key=$SERPAPI_API_KEY" | jq '{best: [.best_flights[]? | {price: .price, duration: .total_duration, stops: (.layovers | length), flights: [.flights[] | {from: .departure_airport.id, to: .arrival_airport.id, airline: .airline, flight: .flight_number, depart: .departure_airport.time, arrive: .arrival_airport.time}]}], price_insights: .price_insights}'
Parameters
| Param | Required | Description |
|---|---|---|
engine |
Yes | google_flights |
departure_id |
Yes | Airport code(s), comma-separated: SFO,PDX |
arrival_id |
Yes | Airport code(s), comma-separated: NRT,HND |
outbound_date |
Yes | YYYY-MM-DD |
return_date |
Round trip | YYYY-MM-DD (required if type=1) |
type |
No | 1 = round trip (default), 2 = one way, 3 = multi-city |
adults |
No | Default 1 |
children |
No | Default 0 |
travel_class |
No | 1 = economy, 2 = premium economy, 3 = business, 4 = first |
stops |
No | 0 = any, 1 = nonstop, 2 = 1 stop or fewer, 3 = 2 stops or fewer |
sort_by |
No | 1 = top flights, 2 = price, 3 = departure, 4 = arrival, 5 = duration |
include_airlines |
No | IATA codes: SK,KL,UA or alliances: STAR_ALLIANCE,SKYTEAM,ONEWORLD |
max_price |
No | Maximum ticket price in USD |
max_duration |
No | Maximum flight duration in minutes |
bags |
No | Number of carry-on bags |
deep_search |
No | true for browser-identical results (slower) |
currency |
No | Default USD |
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.
- 5d ago First seen · 160 lines · 37 tokens per session scan A 6f8e8f560454
serpapi is a skill published in the GitHub repository borski/travel-hacking-toolkit (650 stars, last pushed 4d ago), licensed MIT. It adds 37 tokens to every session and 2,321 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
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.
summarize-session
Summarize the current session and generate reusable Claude rules, skills, or commands.
new-adapter
Add support for a new AI tool with adapters, CLI, completion, and tests.
update-knowledge-base
Analyze code changes and update KNOWLEDGEBASE.md with architectural and feature changes.
sync-readme
Synchronize English README.md with Chinese READMEZH.md, maintaining content parity.
update-docs
Update all project documentation after code changes.