Borrowing it
Nothing to install: this file belongs to yinbri/cineplex-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/yinbri/cineplex-mcp/master/.claude/skills/cineplex-seat-map/SKILL.mdgit clone --depth 1 https://github.com/yinbri/cineplex-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/yinbri/cineplex-mcp/cineplex-seat-map)<a href="https://agentmods.dev/skills/yinbri/cineplex-mcp/cineplex-seat-map"><img src="https://agentmods.dev/badge/skills/yinbri/cineplex-mcp/cineplex-seat-map/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/yinbri/cineplex-mcp/cineplex-seat-map"><img src="https://agentmods.dev/badge/skills/yinbri/cineplex-mcp/cineplex-seat-map.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 | $0.00112 | $0.01377 |
| Opus 5 | $0.00056 | $0.00688 |
| Sonnet 5 | $0.00022 | $0.00275 |
| Haiku 4.5 | $0.00011 | $0.00138 |
Grade A, and why
cineplex-seat-map 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 9d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cineplex seat map
When the user has explicitly asked to see a Cineplex seat map, use the
cineplex MCP server's render_seat_map_html tool and render its result
inline via the Visualizer's show_widget tool — never as a file, never
opened in a browser or any external viewer.
When this applies — and when it does not
This skill is opt-in. It fires on a request to see something, not on any question that happens to involve seats.
Use it when the user asks for the map or for a visual:
- "show me the seat map for that showtime"
- "can I see where the free seats are"
- "make that interactive" / "can you visualize it"
- "is there a better view of this"
Do not use it for ordinary ticketing questions, even though they are
about seats. Answer those in text with find_optimal_showtimes /
get_optimal_seats, and call render_seat_map_ascii to show the
recommended seats:
- "which showtime should we book?"
- "are there two seats together for The Odyssey tonight?"
- "find IMAX showtimes with good seats near me"
- "what's the best-seated screening this weekend?"
The distinction is what the user asked for. "Which showtime should we book" is a decision question — the answer is a recommendation, and replacing it with a widget makes the user do the analysis themselves. The widget is a richer way to look, not a substitute for answering.
This skill withholds the widget, never the answer. Do not ask permission before rendering a text diagram — "would you like me to show it as a text diagram?" is not a useful turn. Render the ASCII map as part of the answer, and if the interactive view seems worth offering, say so in a closing line after the answer is already complete.
Calling render_seat_map_ascii does not display anything. The client
keeps tool results collapsed behind a "tools used" disclosure the user has
to click, so a diagram that was merely returned is a diagram the user never
saw. The result comes back as a display instruction plus a ready-to-paste
payload between ===== COPY ... ===== markers; paste that payload into
your reply verbatim. It is already fenced, already has the buy link outside
the fence — copy it whole rather than rebuilding 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.
- 9d ago First seen · 105 lines · 112 tokens per session scan A a7a75829e1f4
cineplex-seat-map is a skill published in the GitHub repository yinbri/cineplex-mcp (2 stars, last pushed 19d ago), licensed MIT. It adds 112 tokens to every session and 1,377 once invoked, about $0.0006 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
frontmcp-guides
Tutorials, end-to-end walkthroughs, and complete reference projects for FrontMCP. Use when you want a getting-started guide, a full worked example, or to learn best practices by following a step-by-step build rather than a single API reference. Includes a beginner weather-API server (tool plus static resource, Zod…
create-skill
Create instruction-only skills that package knowledge and workflow guides for AI clients.
frontmcp-extensibility
Use when extending FrontMCP beyond the core SDK by integrating external npm packages, libraries, or third-party services into providers and tools. Covers VectoriaDB for in-memory semantic and vector search (ML-based embeddings or TF-IDF keyword engines, with persistence) and the tamper-evident, hash-chained skill…
incident-response-skill
A skill that uses object-style tool references with purpose descriptions and required flags, plus strict validation.
directory-based-skill
A skill loaded from a directory structure with SKILL.md frontmatter, plus file-based and URL-based instruction sources.
parameterized-skill
A skill with customizable parameters, usage examples for AI guidance, and controlled visibility.