cineplex-mcp: Skill for Claude Code

.claude/skills/cineplex-seat-map/SKILL.md

cineplex-seat-map is a skill for Claude Code from yinbri/cineplex-mcp. It costs 112 tokens per session (1,377 once invoked), scanned A, original, MIT.

Instructions for showing an interactive Cineplex cinema seat map when the user explicitly asks for a visual view. Cineplex is a cinema chain, and a seat map displays the screening's seats and their availability.

In plain words
What is it for?
Use it to render an interactive seat map inside the conversation for a requested Cineplex screening; use text and seat-search tools for regular booking questions.
Why use it?
It separates requests to see a visual map from ordinary questions about showtimes or seat quality, so the correct response method is used.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is yinbri/cineplex-mcp's own configuration. It tells Claude Code how to work on cineplex-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cineplex-mcp configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/yinbri/cineplex-mcp/master/.claude/skills/cineplex-seat-map/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/yinbri/cineplex-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for cineplex-seat-map

README.md
[![agentmods](https://agentmods.dev/badge/skills/yinbri/cineplex-mcp/cineplex-seat-map/github.svg)](https://agentmods.dev/skills/yinbri/cineplex-mcp/cineplex-seat-map)
Your own site
<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.

agentmods 80×15 button for cineplex-seat-map

Your own site · 80×15
<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>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,377 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash a7a75829e1f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

.claude/skills/cineplex-seat-map/SKILL.md · 105 lines

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.

Read the full file on GitHub · 105 lines

Changes

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.

  1. 9d ago First seen · 105 lines · 112 tokens per session scan A a7a75829e1f4

Subscribe to this mod's changes

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.