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 plan-tripgit 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/plan-trip)<a href="https://agentmods.dev/skills/borski/travel-hacking-toolkit/plan-trip"><img src="https://agentmods.dev/badge/skills/borski/travel-hacking-toolkit/plan-trip.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 | $0.00036 | $0.01050 |
| Opus 5 | $0.00018 | $0.00525 |
| Sonnet 5 | $0.00007 | $0.00210 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade A, and why
plan-trip 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Trip Skill
The user invoked this skill explicitly. Run a guided trip planning workflow that produces a concrete, opinionated recommendation with cents-per-point math, transfer paths, and a booking plan.
How to run this
If the user already gave details in their prompt arguments, use those. Otherwise, ask in this order, one question at a time. Don't fire all the questions at once.
- Where? Destination(s). Accept regions ("Scandinavia"), cities ("Tokyo"), or specific airports.
- When? Departure month or date range. Note flexibility: "exact dates" vs "any week in March" matters a lot for award availability.
- Who? Number of travelers, ages if children/infants. The toolkit supports infant pricing and seat configurations.
- What class? Economy / premium economy / business / first. Default to economy if unstated.
- Trip length? Number of nights at destination if applicable.
- Points or cash? Three valid answers: "best of both" (default), "points only" (treat cash as last resort), "cash only" (skip award search).
After question 6, confirm the plan back to the user in one sentence and start the workflow.
The workflow
Once you have the inputs:
- Load lessons-learned first. Non-optional. Other skills depend on it.
- Load flight-search-strategy for the canonical parallel search plan.
- Pull balances via the awardwallet skill if the user's intent is points or "best of both" AND if balances aren't already in this session's context. Skip the pull if you already know them.
- Run cash search in parallel via duffel, ignav, google-flights, and the relevant free MCPs (Skiplagged, Kiwi).
- Run award search in parallel via seats-aero across ALL programs (never filter to one program upfront — see lessons-learned).
- Cross-reference with transfer-partners and transfer-bonuses to find the cheapest currency you actually have.
- Apply points-valuations to compute cents-per-point on each award option.
- Surface anything from award-sweet-spots that matches this route.
- Check stopovers if the destination involves a connection. Multi-city trips might unlock "two destinations for the price of one" via Aeroplan, Alaska, or Flying Blue.
- Show the math in a markdown table. One row per option, ranked. Columns: program, miles cost, cash co-pay, total $ value, cpp, hold-before-transfer rule, recommendation.
- Pick a winner with one-sentence reasoning.
- Show booking next steps via booking-guidance: which program to call, hold rules, transfer timing, phone numbers if needed.
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 · 67 lines · 36 tokens per session scan A 94007ad4230b
plan-trip is a skill published in the GitHub repository borski/travel-hacking-toolkit (653 stars, last pushed 7d ago), licensed MIT. It adds 36 tokens to every session and 1,050 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
oh-my-opencode-slim
Configure and improve oh-my-opencode-slim for the current user. Use when users want to tune agents, models, prompts, custom agents, skills, MCPs, presets, or plugin behavior. Also use when recurring workflow friction suggests a safe config or prompt improvement.
clonedeps
Clone important project dependency source code into an ignored local workspace so OpenCode can inspect library internals. Use when the user asks to clone dependencies, inspect dependency/source internals, understand SDK/framework behavior from source, debug library implementation details, or make core dependency repos…
codemap
Generate comprehensive hierarchical codemaps for UNFAMILIAR repositories. Expensive operation - only use when explicitly asked for codebase documentation or initial repository mapping.
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.
simplify
Simplifies code for clarity without changing behavior. Use for readability, maintainability, and complexity reduction after behavior is understood.