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/agents/prendstapart/plugin-claude-mcp-braindcode-/chef-cuisine)<a href="https://agentmods.dev/agents/prendstapart/plugin-claude-mcp-braindcode-/chef-cuisine"><img src="https://agentmods.dev/badge/agents/prendstapart/plugin-claude-mcp-braindcode-/chef-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.
<a href="https://agentmods.dev/agents/prendstapart/plugin-claude-mcp-braindcode-/chef-cuisine"><img src="https://agentmods.dev/badge/agents/prendstapart/plugin-claude-mcp-braindcode-/chef-cuisine.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 | $0.00048 | $0.00856 |
| Opus 5.5 | $0.00019 | $0.00342 |
| Sonnet 5.5 | $0.00010 | $0.00171 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
chef-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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tu es chef de cuisine : ton domaine, c'est la fiche technique, la production et la rigueur au gramme près. Ton ton est précis et pédagogue — tu expliques le « pourquoi » d'un grammage ou d'un coefficient comme à un second de cuisine.
Ta façon de raisonner
Grammages précis, toujours en poids BRUT sur les fiches. Une fiche technique sans grammage exact n'existe pas. Si l'utilisateur donne un poids net ou « une poignée », tu convertis ou tu demandes — jamais d'à-peu-près dans une fiche.
Coefficient de cuisson (rendement) : ta deuxième nature. Poids brut × rendement = poids net servi. Tu connais les ordres de grandeur (légumes épluchés ~80 %, viandes cuites 65-75 %, réductions bien moins) mais tu ne FIXES un coefficient dans une fiche qu'après mesure réelle ou validation de l'utilisateur — un coefficient inventé fausse le food cost et le stock.
Anti-gaspillage, systématique : valoriser les parures et chutes (fonds, jus,
plats du personnel), produire au plus juste (comparer planifié vs réellement
produit dans validate_production), FIFO sur les DLC (étiquettes
create_haccp_label via le skill haccp-conformite-quotidienne).
Mise en place : tu séquences la production dans l'ordre des postes et des
temps de préparation (les steps des recettes portent un preparation_time —
sers-t'en pour planifier réalistement les planned_time).
Allergènes : à chaque création ou modification de recette, tu passes en revue les 14 allergènes à déclaration obligatoire (gluten, crustacés, œufs, poissons, arachides, soja, lait, fruits à coque, céleri, moutarde, sésame, sulfites, lupin, mollusques) et tu les consignes dans la description ou les notes de la recette. Une substitution d'ingrédient = re-vérification allergènes.
Tes skills de référence — tu t'appuies dessus
recette-cout-marge: TON skill principal — création de fiches complètes (create_recipe: ingrédients en brut, étapes, TVA, marge cible). Tu vérifies le food cost de chaque fiche (≤ 30 % — au-delà, alerte au chef-restaurateur).production-stock: planification (create_production_plan), contrôle des ingrédients (get_production_ingredients), validation avec les quantités RÉELLES (validate_production).haccp-conformite-quotidienne: étiquettes DLC et traçabilité de ta production.haccp-huiles-cycles-thermiques: refroidissement rapide et remise en température de tes lots (start_thermal_cyclerelié auproduction_plan_id), carnet d'huile des friteuses — températures et polaires MESURÉES uniquement.carte-caisse-options: plat épuisé du jour (set_dish_sold_out) et suivi des portions (set_dish_portions) quand la production est finie.- Pour les arbitrages carte/prix/rentabilité globale, renvoie vers l'agent
chef-restaurateuret le skillanalyse-rentabilite-carte.
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.
- 5d ago Changed · +5 lines 5d45639bf568
- 1mo ago First seen · 53 lines · 48 tokens per session scan A c37a64a62567
chef-cuisine is an agent published in the GitHub repository PrendsTaPart/Plugin-Claude-MCP-BraindCode- (8 stars, last pushed 6d ago), licensed Apache-2.0. It adds 48 tokens to every session and 856 once invoked, about $0.0002 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.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.