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-holdsgit 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-holds)<a href="https://agentmods.dev/skills/borski/travel-hacking-toolkit/award-holds"><img src="https://agentmods.dev/badge/skills/borski/travel-hacking-toolkit/award-holds/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-holds"><img src="https://agentmods.dev/badge/skills/borski/travel-hacking-toolkit/award-holds.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 | $0.00053 | $0.02390 |
| Opus 5 | $0.00026 | $0.01195 |
| Sonnet 5 | $0.00011 | $0.00478 |
| Haiku 4.5 | $0.00005 | $0.00239 |
Grade A, and why
award-holds 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Award Hold Policies per Loyalty Program
Reference data for which programs allow you to put an award flight ticket on hold, for how long, at what cost, and via what method (online vs phone). Critical for transferable-currency redemptions where transfers take minutes to days to clear.
Data lives in data/award-holds.json. Refresh cadence is 90 days because hold rules change rarely.
Why Holds Matter
When you find an award seat but the points are sitting in a transferable currency (Amex MR, Chase UR, Citi TYP, Capital One, Bilt, Marriott Bonvoy), you need to transfer them to the loyalty program before booking. Transfer times range from instant (most Amex/Chase partners) to 4 days (Marriott Bonvoy to airline partners).
Without a hold, you risk losing the award seat while the transfer pends. A hold removes the seats from the available pool for the duration, guaranteeing they'll still be there when you ticket.
When to Use This Skill
- User is planning a transferable-points booking and asks "can I hold this?"
- User is comparing programs to redeem the same partner award (e.g., Cathay first/business via AA vs Cathay Asia Miles)
- User asks about the AA 24-hour hold change vs the old 5-day policy
- Trip planning involves Marriott Bonvoy → airline transfers (4 days, must use a hold)
- Researching whether a specific program supports holds before committing to the redemption strategy
When NOT to Use
- Stopover questions (use
stopoversskill) - Cancellation/refund questions (different concept — that's about UNDOING a ticketed booking, not holding before booking)
- Award availability search (use
seats-aero) - Routing-rule questions (use
partner-awards)
Programs That Allow Holds (9 + Singapore agent-discretionary)
| Program | Max Days | Hold Fee | Phone Fee | Online Self-Serve | Confidence |
|---|---|---|---|---|---|
| American AAdvantage | 1 | $0 | $0 (free changes/cancels) | Yes | VERIFIED |
| Lufthansa Miles & More | 5 | $0 | $20 | No | VERIFIED |
| Air France/KLM Flying Blue | 3 | $0 | $25 | No | VERIFIED |
| Cathay Asia Miles | 2 | $0 | $39 | No | VERIFIED |
| Turkish Miles & Smiles | 2 | $0 | varies | No | LIKELY |
| Virgin Atlantic Flying Club | 1-2 | $0 | $0 | No | VERIFIED |
| ANA Mileage Club | 2 | $0 | varies | No | LIKELY |
| Emirates Skywards | 1 | $0 | varies | No | LIKELY |
| EVA Air Infinity MileageLands | 1 | $0 | varies | Yes | LIKELY |
| Singapore KrisFlyer | agent discretion | $0 | $25 or 2,500 miles | No | LIKELY |
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 · 153 lines · 53 tokens per session scan A 961aaab0666b
award-holds is a skill published in the GitHub repository borski/travel-hacking-toolkit (659 stars, last pushed 4d ago), licensed MIT. It adds 53 tokens to every session and 2,390 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…