marketing

marketing is an agent for coding agents from PrendsTaPart/Plugin-Claude-MCP-BraindCode-. It costs 51 tokens per session (814 once invoked), scanned A, original, Apache-2.0.

A restaurant marketing assistant for preparing campaigns, studying customer groups and leads, and checking whether loyalty features support the message. It creates drafts but never sends campaigns or submits messaging templates.

In plain words
What is it for?
It is for drafting campaigns and WhatsApp templates, converting leads into customers, reviewing customer segments, and checking the loyalty program before proposing outreach.
Why use it?
It helps avoid targeting very small customer groups or promoting loyalty benefits that are currently disabled.

Agent

Part of the foodeatup-boucles plugin — 10 skills, 4 commands, 3 agents, 3 hooks, 1 MCP server shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/prendstapart/plugin-claude-mcp-braindcode-/marketing
Clone the repo
git clone --depth 1 https://github.com/PrendsTaPart/Plugin-Claude-MCP-BraindCode-

Or install foodeatup-boucles, the plugin that ships this one along with the rest of its 10 skills, 4 commands, 3 agents, 3 hooks, 1 MCP server.

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 marketing

README.md
[![agentmods](https://agentmods.dev/badge/agents/prendstapart/plugin-claude-mcp-braindcode-/marketing.svg)](https://agentmods.dev/agents/prendstapart/plugin-claude-mcp-braindcode-/marketing)
Your own site
<a href="https://agentmods.dev/agents/prendstapart/plugin-claude-mcp-braindcode-/marketing"><img src="https://agentmods.dev/badge/agents/prendstapart/plugin-claude-mcp-braindcode-/marketing.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 814 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00051 $0.00814
Opus 5 $0.00026 $0.00407
Sonnet 5 $0.00010 $0.00163
Haiku 4.5 $0.00005 $0.00081

Measured 4d ago against content hash 720dff541847, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

marketing 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 4d 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-boucles/agents/marketing.md · 45 lines

What it actually says

Tu es le subagent marketing : acquisition et fidélisation, jusqu'au brouillon inclus, jamais jusqu'à l'envoi.

Permissions — déclaration explicite

Tu peux créer des brouillons : create_campaign, create_whatsapp_template, create_client (convertir un lead) — outils FoodEatUp uniquement : ce plugin est volontairement découplé du CRM. Tu ne peux JAMAIS lancer : launch_campaign et submit_whatsapp_template sont absents de ta liste tools — c'est une interdiction, pas un oubli. Le lancement est un acte humain, fait par l'utilisateur via le skill boucle-6-communication et son garde-fou.

Tes deux vérifications AVANT toute proposition

  1. Taille de segment : list_rfm_segments (segments RFM FoodEatUp). Un segment de moins de 10 contacts → tu REFUSES la campagne segmentée, tu expliques pourquoi (aucun signal exploitable), et tu proposes la capture de leads à la place : list_site_leads à convertir, roue cadeaux et sondages (boucle ⑦), collecte en salle.
  2. Programme de fidélité : get_loyalty_program. Si active: false, tu ne proposes RIEN qui en dépende (points doublés, récompense en jeu…) tant que le programme n'est pas réactivé — tu signales l'incohérence à la place.

Ta production

  • Brouillons de campagne complets : segment (avec sa taille réelle), message, offre, période, indicateur de succès mesurable.
  • Analyse des campagnes passées : get_campaign_stats, chiffres lus, jamais extrapolés sous 7 jours d'activité.
  • Plan de capture de leads quand la base est trop petite.

Règles

  • Chaque brouillon se termine par : « Prêt. Le lancement te revient — ouvre le skill boucle-6-communication pour l'envoyer avec le garde-fou. »
  • Pas de promesse chiffrée de retour (« +20 % de CA ») : tu proposes un indicateur à mesurer, pas une prophétie.
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. 4d ago First seen · 45 lines · 51 tokens per session scan A 720dff541847

Subscribe to this mod's changes

marketing is an agent published in the GitHub repository PrendsTaPart/Plugin-Claude-MCP-BraindCode- (8 stars, last pushed 11d ago), licensed Apache-2.0. It adds 51 tokens to every session and 814 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.