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 compare-flightsgit 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/compare-flights)<a href="https://agentmods.dev/skills/borski/travel-hacking-toolkit/compare-flights"><img src="https://agentmods.dev/badge/skills/borski/travel-hacking-toolkit/compare-flights.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.03094 |
| Opus 5 | $0.00023 | $0.01547 |
| Sonnet 5 | $0.00009 | $0.00619 |
| Haiku 4.5 | $0.00005 | $0.00309 |
Grade A, and why
compare-flights 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 8d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compare Flights
Search every available source for a route and present one unified comparison. Combines cash pricing, award availability, portal pay-with-points, and transfer partner optimization into a single table.
This is an orchestration skill. It tells the agent which tools to run and how to combine results. No standalone script.
Companion reference skills. Load these for deeper context:
flight-search-strategy— full source priority, market selection, source accuracy hierarchypoints-valuations— CPP rules, floor/ceiling, surcharge programs, transfer bonusespartner-awards— alliance + bilateral partnership reachabilitylessons-learned— Seats.aero workflow, Southwest specifics, Companion Pass mathfallback-and-resilience— what to do when a source failstransfer-bonuses— current active transfer bonuses (live data); changes effective ratios when computing options 4-7 of the comparison tablestopovers— when an itinerary has a long layover or multi-city, check if a stopover-allowing program priced lower than separate one-waysround-the-world— for 3+ stop multi-region itineraries, RTW products may beat sum-of-parts award pricingaward-holds— many major Western programs (UA, Aeroplan, AS, DL, BA, ANA, Qatar, Korean) no longer offer holds. Some still do: AA (24h online), Lufthansa M&M (5 days), Flying Blue (3 days, $25 phone fee), Cathay (2 days, $39 fee), Turkish (2 days), Virgin Atlantic (1-2 days, free phone), Singapore (agent discretionary). Affects whether the recommended path is "transfer first then ticket" or "ticket immediately"status-match— when comparing options that include upgrades or elite-only benefits (lounge access, free bags, priority); status changes the real cost of a flight
When to Use
- "Find me the best way to get from SFO to CDG in August"
- "Should I pay cash or use points for this flight?"
- "Compare all options for SFO to NRT business class"
- Any flight search where the user wants the full picture
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.
- 8d ago First seen · 214 lines · 46 tokens per session scan A 73a903f894d5
compare-flights is a skill published in the GitHub repository borski/travel-hacking-toolkit (653 stars, last pushed 7d ago), licensed MIT. It adds 46 tokens to every session and 3,094 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
analyze
Instant full trading analysis — just type a symbol. Auto-detects asset class, timeframe, and runs the complete 18-phase master workflow. Use for ANY ticker/symbol like "EURUSD", "AAPL", "BTCUSD", "XAUUSD", "SPY", "NQ", "ES". This is THE one-command entry point.
analyze-gold
Pre-configured combination command for gold (XAUUSD) analysis. Runs the full pair-analyze pipeline tuned for gold's volatility profile, session behavior, and dollar sensitivity. USE FOR - analyze gold, analyze XAUUSD, gold setup, trade gold, gold analysis, XAUUSD plan.
analyze-us30
Pre-configured combination command for US30 (Dow Jones Industrial Average CFD) analysis. Runs the full pair-analyze pipeline tuned for US30's session-driven flow, earnings sensitivity, and Fed-rate reactivity. USE FOR - analyze US30, analyze Dow, analyze Dow Jones, US30 setup, trade US30, DJ30 plan.
worktrees
Manage Git worktrees as OMO safe isolated coding lanes for complex, risky, or parallel work.
using-ao
Catalog of the AO (Agent Orchestrator) ao CLI: spawning workers, managing sessions and projects, sending messages, controlling the shared browser, previewing pages, and daemon control. Use when using the ao CLI, spawning workers, or managing AO sessions in an AO workspace.
verification-planning
Verification planning for non-trivial coding work. Use before implementing a feature, bug fix, refactor, cross-system change, or high-confidence behavior change that needs a credible project-specific evidence path.