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 atlas-obscuragit 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/atlas-obscura)<a href="https://agentmods.dev/skills/borski/travel-hacking-toolkit/atlas-obscura"><img src="https://agentmods.dev/badge/skills/borski/travel-hacking-toolkit/atlas-obscura/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/atlas-obscura"><img src="https://agentmods.dev/badge/skills/borski/travel-hacking-toolkit/atlas-obscura.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 | $0.00044 | $0.01204 |
| Opus 5 | $0.00022 | $0.00602 |
| Sonnet 5 | $0.00009 | $0.00241 |
| Haiku 4.5 | $0.00004 | $0.00120 |
Grade A, and why
atlas-obscura 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 12d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atlas Obscura
Find genuinely interesting hidden gems near any destination via Atlas Obscura. Searches by coordinates, scores places for interestingness, and filters out mundane historical markers.
No API key needed. Uses the atlas-obscura-api npm scraper.
Prerequisites
Install dependencies (one time):
cd skills/atlas-obscura && npm install
City Coordinates Reference
Common cities for trip planning. Use these with the search commands.
| City | Lat | Lng |
|---|---|---|
| New York | 40.7128 | -74.0060 |
| London | 51.5074 | -0.1278 |
| Paris | 48.8566 | 2.3522 |
| Tokyo | 35.6762 | 139.6503 |
| Bangkok | 13.7563 | 100.5018 |
| Rome | 41.9028 | 12.4964 |
| Barcelona | 41.3874 | 2.1686 |
| Istanbul | 41.0082 | 28.9784 |
| Mexico City | 19.4326 | -99.1332 |
| Lisbon | 38.7223 | -9.1393 |
| Seoul | 37.5665 | 126.9780 |
| Oslo | 59.9139 | 10.7522 |
| Copenhagen | 55.6761 | 12.5683 |
| Stockholm | 59.3293 | 18.0686 |
Commands
All commands run from the repo root. Output is JSON. Image URLs are excluded by default to keep output lean. Add --images to any command when you need them (e.g. generating HTML pages).
Search Nearby (Filtered)
Finds places near coordinates, fetches full details, scores for interestingness, and filters out boring stuff. Slower (fetches each place) but gives you the good stuff.
node skills/atlas-obscura/ao.mjs search <lat> <lng>
Example:
node skills/atlas-obscura/ao.mjs search 35.6762 139.6503
Returns up to 20 places sorted by interest score. Each has full description, tags, and directions.
Timeout note: This makes ~20 HTTP requests (one per place). Allow 30-60 seconds.
Quick Search (Unfiltered)
Fast nearby search. Returns title, subtitle, coordinates, distance. No detail fetching or scoring.
node skills/atlas-obscura/ao.mjs quick <lat> <lng>
Search Unfiltered with Details
Same as filtered search but keeps everything, including boring plaques.
What ships with it
3 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.
- 12d ago First seen · 147 lines · 44 tokens per session scan A e66998e4b5a8
atlas-obscura is a skill published in the GitHub repository borski/travel-hacking-toolkit (659 stars, last pushed 4d ago), licensed MIT. It adds 44 tokens to every session and 1,204 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
docs-builder
Reorg a docs corpus, split an oversized doc, search it, keep pages current, index them.
live-canvas
Conduct design interviews, generate UI variations, and collect live click-to-annotate feedback that streams into the session so edits land without leaving the browser. Use when the user wants rapid iterative UI refinement, not just batched feedback.
remember
Consolidate stashes + friction into project memory.
branch-review
Review a branch before merge [target] [level].
root-cause
Use when any test fails, bug appears, or behaviour surprises you, before proposing a fix - find the cause and prove it, by reading real evidence, tracing bad values back to their origin, comparing against a working case, and testing one hypothesis at a time.
ship
Mechanical pre-deploy gate — tests, build, tree state.