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 shlomsh/hermes-travel-skills --skill google_placesgit clone --depth 1 https://github.com/shlomsh/hermes-travel-skillsWrote 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/shlomsh/hermes-travel-skills/google_places)<a href="https://agentmods.dev/skills/shlomsh/hermes-travel-skills/google_places"><img src="https://agentmods.dev/badge/skills/shlomsh/hermes-travel-skills/google_places/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/shlomsh/hermes-travel-skills/google_places"><img src="https://agentmods.dev/badge/skills/shlomsh/hermes-travel-skills/google_places.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00024 | $0.00805 |
| Opus 5 | $0.00012 | $0.00402 |
| Sonnet 5 | $0.00005 | $0.00161 |
| Haiku 4.5 | $0.00002 | $0.00081 |
Grade A, and why
google_places 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Places
Live discovery engine for places.
Work Efficiently (Orchestration)
You must adapt your usage of this skill based on your assigned Execution Flavor:
Flavor: ONLINE (Low Latency / Minimum Steps)
- Plan your execution to meet the exact request in the absolute minimum number of steps.
- Craft the perfect
searchquery on the first try. - Use
--top N(e.g.--top 10) to fetch a large enough buffer of results so you can filter and pick the best options locally. - Do NOT run the
detailscommand. Thesearchcommand already provides theeditorialSummaryand ratings, so runningdetailsin an online context wastes API tokens and latency.
Flavor: RESEARCH (Deep Dive / Thorough)
- You may execute multiple
searchqueries to compare different areas or keywords. - You may use the
detailscommand if you need exhaustive information (like full reviews or extensive opening hours) not covered by thesearchsummary.
Available flags for search:
--open: Use if the user asks for places open right now.--min-rating X: E.g.--min-rating 4.5--top N: E.g.--top 5
Orchestration Example
To ensure you can present exactly 3 high-quality options, query a buffer of places (e.g. --top 5) so you still have 3 valid choices even if some are closed or poorly rated.
# 1-Shot Search: Fetch top 5 places and use their basic data and editorialSummary
python google_places.py search "trendy cafes in Brooklyn" --top 5
Formatting the Best Search Query
Do not just search for a generic category (like "restaurant"). The Places API is a semantic engine. Always inject qualitative modifiers and specific locations directly into the <query> string to let Google do the heavy lifting on ranking.
- Good Query:
"top rated kid friendly Italian restaurants in Times Square" - Bad Query:
"Italian restaurant"(too broad, leaves the ranking to chance)
Examples / Use Cases
Map the user's ask straight to a query:
# "top rated coffee around times square, open now"
python google_places.py search "top rated coffee around Times Square" --open --top 3
# "popular steak house in new york"
python google_places.py search "popular steak house in New York" --min-rating 4.5 --top 5
What ships with it
1 file 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 · 70 lines · 24 tokens per session scan A 7eaa0d7debf8
google_places is a skill published in the GitHub repository shlomsh/hermes-travel-skills (8 stars, last pushed 3mo ago), licensed MIT. It adds 24 tokens to every session and 805 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
local-knowledge-router
Route local operational questions to indexed skills, scripts, runbooks, cron jobs, MCP servers, and docs before guessing paths or doing broad file search.
c-location
Search Apple Maps, find nearby places, and get directions using the goplaces CLI. Supports keyword searches, category filters (restaurants, coffee, gas), and turn-by-turn directions by driving, walking, or transit.
tomtom
TomTom Maps MCP integration — search, routing, traffic, maps, POIs, and EV via hosted endpoint.
local-knowledge-router
Route local operational questions to indexed skills, scripts, runbooks, cron jobs, MCP servers, and docs before guessing paths or doing broad file search.
flyai-travelmapify
Copy Xiaohongshu travel planning homework into interactive route maps with real FlyAI hotel search in seconds.
add-component
Add a new visualization component to Unovis end to end — the TypeScript core, the shared registry, the generated framework wrappers, a dev example, a gallery example, and docs. Use when asked to add/create a new component, chart type, plot, or diagram to the library, or to wire an existing core component through to…