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.
/plugin marketplace add PrendsTaPart/Plugin-Claude-MCP-BraindCode-/plugin install foodeatupWrote 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/prendstapart/plugin-claude-mcp-braindcode-/analyse-rentabilite-carte)<a href="https://agentmods.dev/skills/prendstapart/plugin-claude-mcp-braindcode-/analyse-rentabilite-carte"><img src="https://agentmods.dev/badge/skills/prendstapart/plugin-claude-mcp-braindcode-/analyse-rentabilite-carte/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/prendstapart/plugin-claude-mcp-braindcode-/analyse-rentabilite-carte"><img src="https://agentmods.dev/badge/skills/prendstapart/plugin-claude-mcp-braindcode-/analyse-rentabilite-carte.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 | $0.01147 |
| Opus 5 | $0.00033 | $0.00574 |
| Sonnet 5 | $0.00013 | $0.00229 |
| Haiku 4.5 | $0.00007 | $0.00115 |
Grade A, and why
analyse-rentabilite-carte 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyse de rentabilité de la carte (ingénierie de menu)
Étape 0 — Références et établissement (obligatoire)
- Charger
${CLAUDE_PLUGIN_ROOT}/reference/directives-outils.mdet appliquer ses règles pendant toute l'exécution (IDs, confirmations, données, formats, erreurs). - S'assurer d'avoir l'
establishment_id(le demander si absent) avant tout appel.
Méthode — matrice popularité × marge
Chaque plat est classé sur deux axes, calculés sur des DONNÉES RÉELLES :
- Marge : marge brute unitaire = prix de vente HT − coût matière. Food cost = coût matière / prix de vente HT (cible ≤ 30 %).
- Popularité : volume vendu/produit sur la période, comparé à la popularité moyenne de la catégorie (seuil classique : 70 % de la moyenne).
| Marge haute | Marge basse | |
|---|---|---|
| Populaire | ⭐ Stars | 🐴 Plow-horses |
| Peu populaire | 🧩 Puzzles | 🐶 Dogs |
Workflow
- Collecter les données — aucun chiffre inventé :
list_dishes+list_recipes: la carte et ses fiches ;get_recipepar plat : coût matière, prix, marge (si une fiche n'a pas de coût complet, le signaler — le plat sort de l'analyse au lieu d'être estimé) ;list_top_productionset/oulist_orderssur la période : volumes réels (préciser la période analysée ; défaut : 30 derniers jours).
- Calculer avec le SCRIPT — jamais de tête. Utiliser le script pour tout
calcul ; ne jamais calculer de tête.
- Seuil food cost : seuil MAISON de
./rapido-kb/processus-internes.mds'il existe (le passer en 2e argument au script et citer la source), sinon défaut secteur 30 % — en le signalant (« valeur par défaut — lancez l'onboarding pour personnaliser »). - Construire le JSON d'entrée
[{plat, prix_vente, cout_ingredients, quantite_vendue}]à partir des données de l'étape 1, l'écrire dans un fichier temporaire, puis exécuter :python3 "${CLAUDE_PLUGIN_ROOT}/skills/analyse-rentabilite-carte/scripts/menu_matrix.py" <fichier.json> [seuil_maison]Le script renvoie food cost %, marges, quadrants (seuils Kasavana-Smith : popularité ≥ 70 % de la moyenne, marge ≥ moyenne), alertes food cost (au seuil retenu, avec sa source), et les plats exclus faute de données.
- Seuil food cost : seuil MAISON de
- Restituer le tableau à partir de la sortie du script : plat | catégorie | food cost % | marge € | popularité | quadrant — sans recalculer ni arrondir différemment.
- Recommander par quadrant :
- ⭐ Stars (populaire + marge haute) : ne pas toucher — mettre en avant (position sur la carte, suggestion serveur). Surveiller la constance.
- 🐴 Plow-horses (populaire + marge basse) : REPRICER ou re-costifier — hausse de prix modérée (1-2 tests), réduction du coût matière (portion, ingrédient, négociation fournisseur) SANS dégrader la qualité perçue.
- 🧩 Puzzles (peu populaire + marge haute) : REPOSITIONNER — renommer, déplacer sur la carte, faire vendre par l'équipe, photo/description. Si toujours invendu après repositionnement : retirer.
- 🐶 Dogs (peu populaire + marge basse) : RETIRER — ou transformer (recette revisitée, plat du jour pour écouler). Jamais plus d'un cycle de seconde chance.
- Plan d'action : 3 à 5 actions maximum, priorisées par impact sur la marge
globale, chacune adossée au skill concerné (
recette-cout-margepour re-costifier/repricer,update_dish/update_recipepour appliquer — avec confirmation).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 75 lines · 66 tokens per session scan A 01c7672a22d3
analyse-rentabilite-carte is a skill published in the GitHub repository PrendsTaPart/Plugin-Claude-MCP-BraindCode- (8 stars, last pushed 16d ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,147 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…