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 trip-calculatorgit 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/trip-calculator)<a href="https://agentmods.dev/skills/borski/travel-hacking-toolkit/trip-calculator"><img src="https://agentmods.dev/badge/skills/borski/travel-hacking-toolkit/trip-calculator/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.
<a href="https://agentmods.dev/skills/borski/travel-hacking-toolkit/trip-calculator"><img src="https://agentmods.dev/badge/skills/borski/travel-hacking-toolkit/trip-calculator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.02563 |
| Opus 5.5 | $0.00015 | $0.01025 |
| Sonnet 5.5 | $0.00007 | $0.00513 |
| Haiku 4.5 | $0.00004 | $0.00256 |
Grade A, and why
trip-calculator 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trip Cost Calculator
"Should I pay cash or use points?" answered with math.
Compares the true cost of booking with cash versus each available points currency, accounting for transfer ratios, taxes/fees, and the opportunity cost of burning your points.
No API key needed. Uses local JSON data files plus flight/hotel search results.
Data Files
| File | Purpose |
|---|---|
data/points-valuations.json |
CPP valuations per program (floor/ceiling) |
data/transfer-partners.json |
Credit card → loyalty program transfer ratios |
When to Use
- User has both cash prices (from Duffel/Ignav/Google Flights) and award prices (from seats.aero)
- User asks "should I pay cash or use points?"
- User wants to know the CPP of a specific redemption
- User is deciding between multiple booking strategies for a trip
Core Concepts
Cents Per Point (CPP)
The value you're getting per point when redeeming:
cpp = (cash_price - taxes_on_award) / points_needed × 100
A CPP above the floor valuation from points-valuations.json means you're getting above-average value. Below floor = poor redemption.
Opportunity Cost
Points have value even when unspent. Burning 100K Chase UR at 1.7 cpp (floor) means you're "spending" $1,700 in future travel flexibility:
opportunity_cost = points_needed × floor_cpp / 100
If the cash price is lower than the opportunity cost, pay cash. If higher, use points.
The Decision Framework
IF cash_price < opportunity_cost → PAY CASH (points are worth more saved)
IF cash_price > opportunity_cost → USE POINTS (good redemption)
IF cash_price ≈ opportunity_cost → PAY CASH (preserve flexibility)
The tie goes to cash because points maintain optionality.
Workflow
Step 1: Gather Prices
Cash prices (use one or more sources):
Duffel API → exact bookable fares
Ignav API → fast comparison prices
Google Flights → browser-based, includes Southwest
Award prices (use seats.aero):
Seats.aero API → cached availability across 25+ programs
Seats.aero web → live search (local Patchright only)
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.
- 2mo ago First seen · 235 lines · 37 tokens per session scan A 54d3b9adc074
trip-calculator is a skill published in the GitHub repository borski/travel-hacking-toolkit (926 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 2,563 once invoked, about $0.0001 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 2026-08-30.
trip-calculator compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| trip-calculatorborski/travel-hacking-toolkit | Skill | 926 | today | MIT | A | 37 | Claude Code |
| analyzemahmoud20138/Tradecraft | Skill | 17 | 6mo ago | MIT | A | 75 | Claude Code |
| analyze-goldmahmoud20138/Tradecraft | Skill | 17 | 6mo ago | MIT | A | 65 | Claude Code |
| analyze-us30mahmoud20138/Tradecraft | Skill | 17 | 6mo ago | MIT | A | 73 | Claude Code |
| orca-jirastablyai/orca | Skill | 120k | today | MIT | A | 74 | Claude Code, Codex |
| using-aoUntrivial-ai/agent-orchestrator | Skill | 14k | 2d ago | Apache-2.0 | A | 71 | Claude Code, Codex |
| alpha-vantageforyourhealth111-pixel/Vibe-Skills | Skill | 3.8k | today | Apache-2.0 | A | 126 | Claude Code, Codex |