coordination-cuisine

coordination-cuisine is a skill for Claude Code from PrendsTaPart/Plugin-Claude-MCP-BraindCode-. It costs 87 tokens per session (1,213 once invoked), scanned A, original, Apache-2.0.

A kitchen-service workflow that keeps each dish on a restaurant order moving through the kitchen display system (KDS), from waiting to being served.

In plain words
What is it for?
Updating dish statuses, spotting delayed orders, and signalling when a complete order is ready to pass to the dining room.
Why use it?
It prevents kitchen and front-of-house staff from losing track of individual dishes or leaving orders waiting too long.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the foodeatup plugin — 27 skills, 6 agents shipped together

Good fit Updating dish statuses, spotting delayed orders, and signalling when a complete order is ready to pass to the dining room.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add PrendsTaPart/Plugin-Claude-MCP-BraindCode-
Claude Code
/plugin install foodeatup

Made for: Claude Code.

Or install foodeatup, the plugin that ships this one along with the rest of its 27 skills, 6 agents.

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 coordination-cuisine

README.md
[![agentmods](https://agentmods.dev/badge/skills/prendstapart/plugin-claude-mcp-braindcode-/coordination-cuisine/github.svg)](https://agentmods.dev/skills/prendstapart/plugin-claude-mcp-braindcode-/coordination-cuisine)
Your own site
<a href="https://agentmods.dev/skills/prendstapart/plugin-claude-mcp-braindcode-/coordination-cuisine"><img src="https://agentmods.dev/badge/skills/prendstapart/plugin-claude-mcp-braindcode-/coordination-cuisine/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 coordination-cuisine

Your own site · 80×15
<a href="https://agentmods.dev/skills/prendstapart/plugin-claude-mcp-braindcode-/coordination-cuisine"><img src="https://agentmods.dev/badge/skills/prendstapart/plugin-claude-mcp-braindcode-/coordination-cuisine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,213 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 $0.00087 $0.01213
Opus 5.5 $0.00035 $0.00485
Sonnet 5.5 $0.00017 $0.00243
Haiku 4.5 $0.00009 $0.00121

Measured 5d ago against content hash b9963f6dbd72, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

coordination-cuisine 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 5d 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.

foodeatup/skills/coordination-cuisine/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coordination cuisine (passe / KDS)

Pendant le service, la cuisine dicte l'état des plats (« le tartare de la 12 est prêt ») et ce skill tient le KDS à jour, plat par plat, jusqu'au passage de la commande complète. Complète gestion-commandes (statut de la COMMANDE) en travaillant au niveau de l'ITEM.

Étape 0 — Références et établissement (obligatoire)

  1. Charger ${CLAUDE_PLUGIN_ROOT}/reference/directives-outils.md et appliquer ses règles pendant toute l'exécution (IDs, confirmations, données, formats, erreurs).
  2. S'assurer d'avoir l'establishment_id (le demander si absent) avant tout appel.
  3. Règle « Résolution des noms » (directives § 1 ter) : tout nom parlé ou écrit (produit, ingrédient, plat, équipement, table, recette) se résout via search_entities AVANT tout autre appel — fuzzy FR géré par le serveur (accents, pluriels) ; si ambiguous=true, présenter les candidats et DEMANDER confirmation avant d'agir. Jamais d'ID deviné.

Machine à états d'un plat (KDS)

pending → in_progress → ready → served — vérifié serveur. Transitions STRICTES : jamais de saut en avant (pending ne passe pas directement à ready), jamais de retour arrière sans confirmation explicite. served (plat envoyé en salle) : uniquement quand la salle confirme l'envoi.

Workflow

  1. Vue du passe — list_orders (establishment_id, status: "en_preparation" — ajouter confirmee si la cuisine veut voir ce qui arrive) : commandes en cours avec leurs items. L'item_id d'un plat est l'ID de l'ITEM DE COMMANDE (ligne boutique_commande_items renvoyée dans la commande) — jamais l'ID du plat au menu.
  2. Résoudre les noms dictés à l'oral — quand l'utilisateur nomme un plat (« le burger », « la 12 »), croiser d'abord avec les items des commandes en cours ; si le nom reste ambigu, search_entities (establishment_id, query, types: ["dish", "table"]) pour retrouver le plat ou la table — si ambiguous=true, DEMANDER confirmation avant d'agir. Ne jamais deviner quel item d'une commande correspond à un nom flou.
  3. Faire avancer les plats — update_kds_item_status (establishment_id, item_id, status) plat par plat : pending → in_progress quand la cuisine attaque, → ready quand le plat est au passe, → served quand la salle l'a envoyé. Annoncer chaque changement (« Tartare table 12 → prêt »).
  4. Commande complète — quand TOUS les plats d'une commande sont ready, le signaler et PROPOSER update_order_status (order_id, status: "prete") — décision de l'utilisateur, jamais automatique (machine à états des commandes : voir gestion-commandes).
  5. Commandes qui attendent — à chaque vue du passe, signaler toute commande en cours depuis plus que le seuil maison (./rapido-kb/processus-internes.md, défaut 15 min) : « ⏱ table 7 attend depuis 18 min ». Proposer l'action, ne pas la décider.
  6. Charge par poste — get_station_load (establishment_id) : la file de chaque poste (grill, froid, pâtisserie…). Un poste qui déborde pendant que les autres respirent = proposer de re-séquencer les lancements, pas d'empiler. À lire avant d'annoncer un temps d'attente à la salle.

Read the full file on GitHub · 81 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. 5d ago Changed · +9 tokens per session b9963f6dbd72
  2. 1mo ago First seen · 81 lines · 78 tokens per session scan A d3a87ef1df8b

Subscribe to this mod's changes

coordination-cuisine is a skill published in the GitHub repository PrendsTaPart/Plugin-Claude-MCP-BraindCode- (8 stars, last pushed 6d ago), licensed Apache-2.0. It adds 87 tokens to every session and 1,213 once invoked, about $0.0003 per session on Opus 5.5. 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.

Related

Other skills, from other repositories

asc-subscription-localization

Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.

rorkai/app-store-connect-cli-skills · 60 tokens

food-order

Reorder previous Foodora orders, preview cart contents, and track delivery ETA/status with ordercli. Use when the user wants to reorder food, check delivery status, or browse recent Foodora order history. Never confirm an order without explicit user approval.

Bitterbot-AI/bitterbot-desktop · 53 tokens

Product Photoshoot Workflow

A workflow for turning one product photo into a set of four e-commerce images from different visual directions.

jau123/MeiGen-AI-Design-MCP · 111 tokens

amazon-reviews-api-skill

This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…

browser-act/skills · 124 tokens

amazon-competitor-analyzer

Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.

browser-act/skills · 48 tokens

cloudbase-wechat-integration

A guide for connecting CloudBase applications to WeChat services, including payments, official accounts, and user identity.

TencentCloudBase/CloudBase-AI-Toolkit · 94 tokens