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 compare-before-you-bookgit 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/compare-before-you-book)<a href="https://agentmods.dev/skills/tickadoo/tickadoo-mcp/compare-before-you-book"><img src="https://agentmods.dev/badge/skills/tickadoo/tickadoo-mcp/compare-before-you-book/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/compare-before-you-book"><img src="https://agentmods.dev/badge/skills/tickadoo/tickadoo-mcp/compare-before-you-book.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 | $0.00071 | $0.00812 |
| Opus 5 | $0.00036 | $0.00406 |
| Sonnet 5 | $0.00014 | $0.00162 |
| Haiku 4.5 | $0.00007 | $0.00081 |
Grade A, and why
compare-before-you-book 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 10d 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.
Compare before you book with tickadoo
Use the tickadoo MCP tools (mcp.tickadoo.com/mcp) when the user is DECIDING between specific options. Turn "X or Y?" into a grounded comparison with a clear recommendation.
When to use this
Use a pair of clearly identified product names or previously shown cards. If either side is a category ("a river cruise"), run discovery first and obtain a specific contender before comparison.
The workflow (tool chain)
- Resolve 2-5 specific contenders — search each prose name with
search_experiences(city, query). If a search returns several plausible products or ticket variants, show the distinctions and ask the user to choose. Never take the first slug silently. If the contenders came from a prior result set, reuse those exact slugs. - Compare —
compare_experiences(slugs)with 2-5 slugs. It returns a comparison table plus documented per-axis winners (value, rating, popularity, family-fit) — echo those, don't bury them. - Check before recommending — if accessibility, cancellation terms or a fixed date could change the decision, fetch
get_experience_detailsfor both finalists and live-check both (get_availabilitywith the date and party size, fresh when supported) BEFORE making the final recommendation. The eventual winner may be unavailable while the runner-up is bookable. - Recommend and close — one clear recommendation tied to the user's stated priority, then
check_availability(slug, date, party_size)only when the user wants the date-specific booking link. - Weak field? — run
recommend_experienceswith the city and the user's priorities, orsearch_experienceswith a precise query, to resolve one new specific contender, then compare again. Do not callget_related_experiencesfrom ChatGPT.
Show results as cards
Do not pass compare_experiences output directly to render_experience_cards. Render contenders only when their product_id values came from a renderer-supported discovery result set (e.g. the resolver search_experiences calls) — pass those IDs verbatim (they are internal; never display or read them aloud) — and render that set immediately, once, with a required render_type from the callable schema. Use render_type: "comparison" only when the callable schema permits it. Do not re-list rendered products 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.
- 10d ago First seen · 36 lines · 71 tokens per session scan A 0b9dc5b9671e
compare-before-you-book is a skill published in the GitHub repository tickadoo/tickadoo-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 812 once invoked, about $0.0004 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.