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 award-sweet-spotsgit 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/award-sweet-spots)<a href="https://agentmods.dev/skills/borski/travel-hacking-toolkit/award-sweet-spots"><img src="https://agentmods.dev/badge/skills/borski/travel-hacking-toolkit/award-sweet-spots/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/award-sweet-spots"><img src="https://agentmods.dev/badge/skills/borski/travel-hacking-toolkit/award-sweet-spots.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 | $0.00069 | $0.01062 |
| Opus 5 | $0.00034 | $0.00531 |
| Sonnet 5 | $0.00014 | $0.00212 |
| Haiku 4.5 | $0.00007 | $0.00106 |
Grade A, and why
award-sweet-spots 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 11d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Award Sweet Spots
Reference data: data/sweet-spots.json
When making recommendations, cross-reference against known sweet spots. If a route matches a sweet spot, flag it prominently.
Tier System
Sweet spots are ranked by tier:
- Legendary: Outsized value that travel hackers build entire trips around
- Examples: ANA First via Virgin Atlantic, Hyatt All-Inclusive via World of Hyatt
- Excellent: Consistently great value, reliable availability
- Examples: Iberia Avios to Madrid, Qatar Qsuites via various programs, Virgin Atlantic economy to London
- Good: Solid value but may have caveats like devaluations, limited availability, or surcharges
Devaluations Matter
Always check the devaluation_date field in data/sweet-spots.json. If a sweet spot was recently devalued, mention the old vs new rates so users understand the change. A "legendary" tier sweet spot from 2023 may only be "good" or even "poor" today.
How to Use This Reference
When a user's search returns options that match a known sweet spot:
- Flag it prominently in the output. "This is the legendary Iberia Avios to Madrid sweet spot."
- Show the current rate vs cash value.
- Note any caveats (surcharges, booking-window restrictions, devaluations).
- Compare against the next-best option to make the value concrete.
Oceania / South Pacific Sweet Spots
Getting to Australia, New Zealand, and the South Pacific on points is hard — demand is high, distances are long, and premium cabin space is scarce. Proven plays, ranked:
- Air New Zealand business via Virgin Atlantic (Excellent) — 62.5K one-way from the US, 45K from Hawaii. The same flights United sells for 110K. Availability is the bottleneck: rare in advance, opens inside 30 days. Phone booking only. Reachable from Amex, Chase, Citi, Bilt, Wells Fargo, and Capital One (via Virgin Red).
- ANA Mileage Club business to Oceania (Excellent) — roughly 68.5K+ one-way on ANA metal (seasonal, under the June 2025 chart; one-ways now bookable) with wide routing via Japan or direct on Air NZ. No fuel surcharges on United, Air Canada, or Air NZ. Limitation: reachable only from Amex MR (plus Marriott at a poor ratio). Verify current rates on ana.co.jp — avoid its still-hosted pre-June-2025 legacy chart pages.
- Aeroplan business to Oceania (Good) — 75-115K one-way, but the killer feature is adding an Asia stopover for +5K miles, turning Australia into Asia + Australia. No fuel surcharges. Reachable from Amex, Chase, Capital One, Bilt.
- Air France LAX-Tahiti nonstop (Good) — ~30K economy one-way on one of the few US-Tahiti nonstops. Business (~113K) is usually poor value; economy is the play. Watch for Flying Blue transfer bonuses.
- Atmos/Alaska to the South Pacific (Good) — HNL-Kiritimati on Fiji Airways in the lowest distance band is a perennial steal, and HNL-Tahiti/Rarotonga on Hawaiian is cheap. Free stopover, no change/cancel fees. Reachable only from Bilt (plus Marriott).
- United MileagePlus business (Good) — 85-100K on United metal, ~110K on partners. The most lenient routing rules, but partner space is almost always cheaper via Virgin Atlantic (62.5K) or ANA.
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.
- 11d ago First seen · 57 lines · 69 tokens per session scan A 190b6812c05a
award-sweet-spots is a skill published in the GitHub repository borski/travel-hacking-toolkit (659 stars, last pushed 4d ago), licensed MIT. It adds 69 tokens to every session and 1,062 once invoked, about $0.0003 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.
Other skills, from other repositories
stock-liquidity
Analyze stock liquidity using bid-ask spreads, volume profiles, order book depth, market impact estimates, and turnover ratios via Yahoo Finance data. Use this skill whenever the user asks about liquidity, trading costs, bid-ask spread, market depth, volume analysis, slippage, market impact, turnover ratio, or how…
company-valuation
Estimate the intrinsic value of a public company using DCF, relative (peer multiple) and sum-of-parts (SOTP) methods, then triangulate to an implied share price with upside/downside versus the current market price. Use this skill whenever the user asks: "what is AAPL worth", "valuation of NVDA", "fair value of TSLA"…
fintel-data
Query Fintel (fintel.io) institutional market intelligence via the REST API at https://api.fintel.io/v1 with FINTELAPIKEY (X-API-KEY header), or the official MCP server at https://mcp.fintel.io/mcp. Read-only data: short interest, borrow rate/fee and shares available to borrow, daily short volume, fails-to-deliver…
estimate-analysis
Deep-dive into analyst estimates and revision trends for any stock using Yahoo Finance data. Use when the user wants to understand analyst estimate direction, how EPS or revenue forecasts changed over time, compare estimate distributions, or analyze growth projections across periods. Triggers: "estimate analysis for…
earnings-preview
Generate a pre-earnings briefing for any stock using Yahoo Finance data. Use this skill whenever the user wants to prepare for an upcoming earnings report, understand what analysts expect, review a company's beat/miss track record, or get a quick overview before an earnings call. Triggers include: "earnings preview…
earnings-recap
Generate a post-earnings analysis for any stock using Yahoo Finance data. Use when the user wants to review what happened after earnings, understand beat/miss results, see stock reaction, or get an earnings recap. Triggers: "AAPL earnings recap", "how did TSLA earnings go", "MSFT earnings results", "did NVDA beat…