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 american-airlinesgit 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/american-airlines)<a href="https://agentmods.dev/skills/borski/travel-hacking-toolkit/american-airlines"><img src="https://agentmods.dev/badge/skills/borski/travel-hacking-toolkit/american-airlines/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/american-airlines"><img src="https://agentmods.dev/badge/skills/borski/travel-hacking-toolkit/american-airlines.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 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 MCP Rug Pull · line 24 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 42 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium Rogue Agent · line 49 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 53 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00047 | $0.01272 |
| Opus 5 | $0.00023 | $0.00636 |
| Sonnet 5 | $0.00009 | $0.00254 |
| Haiku 4.5 | $0.00005 | $0.00127 |
Grade A, and why
american-airlines 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
American Airlines AAdvantage
Check AAdvantage award miles balance, elite status (Gold/Platinum/Platinum Pro/Executive Platinum), loyalty points, and million miler status. Uses Patchright (undetected Playwright fork) because AA blocks standard browser automation.
Requires Patchright. AA.com blocks vanilla Playwright and agent-browser.
Prerequisites
pip install patchright && patchright install chromium
Or use Docker (no local install needed):
docker pull ghcr.io/borski/aa-miles-check:latest
# or build locally:
docker build -t aa-check skills/american-airlines/
Usage
Pass credentials via environment variables or flags. If you use a secrets manager (1Password, Vault, etc.), inject them however you normally would.
# Environment variables
AA_USERNAME=your_aa_number AA_PASSWORD=your_password \
python3 scripts/check_balance.py --json
# Flags
python3 scripts/check_balance.py --username YOUR_AA_NUMBER --password YOUR_PASSWORD --json
# Docker
docker run --rm -e AA_USERNAME=your_aa_number -e AA_PASSWORD=your_password aa-check --json
2FA Handling
AA requires email verification on first login from a new device. The script waits up to 120 seconds for the code.
You (the agent) do NOT have access to the user's email. AA sends the 2FA code to the account holder's email address. When the script hits 2FA, you MUST ask the user for the 6-digit code. This is not optional. Do not try to read their email. Do not guess. Do not skip. Ask them, wait for the answer, then write it to the code file.
Agent workflow
- Run the script in the background (
nohup ... &,disown) - Poll stderr for
"2FA REQUIRED"to confirm the code was sent - Ask the user for the 6-digit code AA emailed them
- Write the code to the code file:
echo "123456" > /tmp/aa-2fa-code.txt - Wait for the script to complete and read stdout for the JSON result
Persistent profiles (skip 2FA on repeat runs)
Use --profile name to save browser cookies. After the first successful 2FA, subsequent runs with the same profile skip 2FA entirely. Profiles are stored at ~/.aa-browser-profiles/{name}/. Sessions last hours, not days.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 126 lines · 47 tokens per session scan A 92b9ccdfac8b
american-airlines is a skill published in the GitHub repository borski/travel-hacking-toolkit (659 stars, last pushed 3d ago), licensed MIT. It adds 47 tokens to every session and 1,272 once invoked, about $0.0002 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
freetaxusa
Guides users through filing US federal and state taxes on FreeTaxUSA.com using document extraction, tax research, and browser-based form automation. Use when the user asks to file taxes, prepare a tax return, or automate FreeTaxUSA form filling.
lienfi
Research and buy tokenized US tax lien certificates on LienFi (Base, USDC) — screen the live book by NET yield with no credential, then, once your operator has authorized your wallet in a browser, register and run the prepare → sign → confirm → submit → report purchase loop from the wallet you control. LienFi signs…
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
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"…
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-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…