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 tickadoo/tickadoo-mcp --skill near-a-landmarkgit clone --depth 1 https://github.com/tickadoo/tickadoo-mcpWrote 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/tickadoo/tickadoo-mcp/near-a-landmark)<a href="https://agentmods.dev/skills/tickadoo/tickadoo-mcp/near-a-landmark"><img src="https://agentmods.dev/badge/skills/tickadoo/tickadoo-mcp/near-a-landmark/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/tickadoo/tickadoo-mcp/near-a-landmark"><img src="https://agentmods.dev/badge/skills/tickadoo/tickadoo-mcp/near-a-landmark.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 | $0.00066 | $0.00840 |
| Opus 5 | $0.00033 | $0.00420 |
| Sonnet 5 | $0.00013 | $0.00168 |
| Haiku 4.5 | $0.00007 | $0.00084 |
Grade A, and why
near-a-landmark 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 11d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Near a landmark with tickadoo
Use the tickadoo MCP tools (mcp.tickadoo.com/mcp) when the ask is anchored to a PLACE inside a city. "Things to do near the Louvre" is a different question from "things to do in Paris".
When to use this
The user names a landmark, neighbourhood, square, venue or area: "near the Louvre", "in Trastevere", "around Times Square". If the place is unnamed ("walking distance from my hotel"), ask which hotel or area they mean — never guess. If they mean the whole city, use city-wide discovery instead.
The workflow (tool chain)
- Place-anchored search —
search_local_experiences(place_hint, city?)is the primary tool. It takes the coarse place phrase directly (no coordinates) and matches first by exact venue/neighbourhood, then falls back to the city centre. Do not usefind_nearby_experiencesfrom ChatGPT (it needs real coordinates), and never guess coordinates. - Say what "near" meant — prefer exact venue or neighbourhood matches over city-centre fallback results, and say which you got ("I couldn't anchor to that exact spot, so these are central-Paris options"). Do not claim or rank by walking time unless returned location data supports it.
- Enrich the picks —
get_experience_details(product_id or slug)for the actual location before making any proximity claim. - Check the pick —
get_availabilityfor the selected product (date range, party size, fresh when supported), thencheck_availability(slug, date, party_size)only when the user wants the date-specific booking link. For a same-day check ("this afternoon"), use the venue-local calendar date (e.g. from the selected result'sstart_time), never the assistant's system timezone. - "While you are there" pair — run a new
search_local_experiencescall anchored to the selected venue or area.get_travel_tips(city, topic: "transport")if they ask how to get there.
Show results as cards
When a search_local_experiences set will be shown, immediately call render_experience_cards exactly once for it: only the product_id values exactly as returned by the discovery tool (IDs are internal — pass them verbatim, never display or read them aloud), a required render_type from the callable schema, optionally render_context.intent_summary ("near the Louvre this afternoon"). Do not re-list the same experiences in text.
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.
- 11d ago First seen · 36 lines · 66 tokens per session scan A 601c9547e345
near-a-landmark is a skill published in the GitHub repository tickadoo/tickadoo-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 66 tokens to every session and 840 once invoked, about $0.0003 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
gws-gmail-send
Skill "gws-gmail-send" from googleworkspace/cli, covering gmail +send, usage, flags, examples and tips.
gws-shared
The gws binary must be on $PATH. See the project README for install options.
gws-sheets
Google Sheets: Read and write spreadsheets.
gws-gmail
Gmail: Send, read, and manage email.
gws-modelarmor-create-template
Google Model Armor: Create a new Model Armor template.
gws-modelarmor
Google Model Armor: Filter user-generated content for safety.