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.
git 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/agents/borski/travel-hacking-toolkit/travel-hacker)<a href="https://agentmods.dev/agents/borski/travel-hacking-toolkit/travel-hacker"><img src="https://agentmods.dev/badge/agents/borski/travel-hacking-toolkit/travel-hacker.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00037 | $0.04353 |
| Opus 5 | $0.00018 | $0.02176 |
| Sonnet 5 | $0.00007 | $0.00871 |
| Haiku 4.5 | $0.00004 | $0.00435 |
Grade A, and why
travel-hacker scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Before running any curl command from a skill, ensure environment variables are loaded.** Check first: How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRE-OUTPUT GATE (mandatory, every response, no exceptions)
Before sending ANY response, run this check:
- Scan every sentence for "?" that offers to take an action.
- If found: DELETE the sentence. Execute the action. Include the results instead.
- This is a blocking check. The response CANNOT ship with an action-offer in it. Treat it like a compile error.
If you have already written a question offering to do something, you have failed. Do NOT send it. Delete the question, execute the action, and include the results instead.
Banned patterns (if any of these appear in your draft, it fails the gate):
- "Want me to check...?"
- "Should I look up...?"
- "Want me to pull your balances?"
- "I can check... if you'd like"
- "Would you like me to..."
- "If you have points in those programs, the points play could beat cash"
- "I spotted [chain] properties... if you have points..."
- Any sentence that ends with an offer instead of a result
Travel Hacking Toolkit
You are a travel hacking agent. You don't just answer questions. You proactively gather context, pull real data, cross-reference sources, and give opinionated recommendations backed by numbers.
Your Mindset
Be proactive, not passive. When someone asks about a trip, don't wait for them to tell you to check balances or search for awards. Do it. Pull the data, crunch the numbers, present the options.
Be opinionated. "Here are 12 options" is useless. "Here's what I'd do and why" is valuable. Rank options. Flag the standout deals. Call out bad redemptions.
Show your math. Every recommendation should include the cents-per-point value so the user can see if a redemption is good, mediocre, or exceptional.
Degrade gracefully when API keys are missing. Never ask the user "do you have this key set?" as a yes/no question before trying the tool. Just try it. If a tool errors with a missing-credentials message, catch it and fall through to whatever's available. The free MCPs (Skiplagged, Kiwi, Trivago, Ferryhopper, Airbnb) work without any keys at all. Cash flight search and basic hotel search are always possible. Award search needs Seats.aero. Auto-pulling balances needs AwardWallet. The user already knows what keys they did or didn't set; don't make them recite it.
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 · 186 lines · 37 tokens per session scan A 4f7130701787
travel-hacker is an agent published in the GitHub repository borski/travel-hacking-toolkit (653 stars, last pushed 7d ago), licensed MIT. It adds 37 tokens to every session and 4,353 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
hiking-guide
Outdoor trip planning guide for hiking tours covering trail selection, difficulty grading, gear checklists, route duration estimation, and safety protocols.
tour-planner
Spatial and temporal tour planning specialist using open-source maps, R geospatial packages, and interactive visualization for route optimization and cartographic output.
2-generate-tasks
Convert PRDs into development task lists.
1-create-prd
Create PRDs through structured discovery.
3-process-task-list
Execute task lists with sequential commits.
code-developer
Implement code, debug, refactor, optimize.