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.
npx skills add PrendsTaPart/Plugin-Claude-MCP-BraindCode- --skill moteur-opportunites-irisgit clone --depth 1 https://github.com/PrendsTaPart/Plugin-Claude-MCP-BraindCode-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.
[](https://agentmods.dev/skills/prendstapart/plugin-claude-mcp-braindcode-/moteur-opportunites-iris)<a href="https://agentmods.dev/skills/prendstapart/plugin-claude-mcp-braindcode-/moteur-opportunites-iris"><img src="https://agentmods.dev/badge/skills/prendstapart/plugin-claude-mcp-braindcode-/moteur-opportunites-iris/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-/moteur-opportunites-iris"><img src="https://agentmods.dev/badge/skills/prendstapart/plugin-claude-mcp-braindcode-/moteur-opportunites-iris.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 | $0.00087 | $0.00940 |
| Opus 5 | $0.00044 | $0.00470 |
| Sonnet 5 | $0.00017 | $0.00188 |
| Haiku 4.5 | $0.00009 | $0.00094 |
Grade A, and why
moteur-opportunites-iris 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 10d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Moteur d'opportunités (le cœur d'Iris)
C'est ce qu'aucun outil de social media ne peut copier : il faut les données d'exploitation pour le faire tourner. Le stock parle au marketing.
Capteurs (lecture seule, dans cet ordre)
| Signal | Source FoodEatUp | Contenu proposé | Urgence |
|---|---|---|---|
| Surstock avec DLC proche | list_stocks · list_haccp_labels |
Plat du jour qui écoule | 🔴 |
| Créneau de réservation faible | reservation_availability |
Offre flash sur le créneau | 🔴 |
| Avis négatif | list_reviews |
Alerte patron — AUCUN post | 🔴 |
| Nouveau plat à la carte | list_dishes · list_recipes |
Post de lancement + story | 🟠 |
| Avis 5 étoiles | list_reviews |
Verbatim en visuel | 🟠 |
| Jour creux récurrent | list_orders (historique) |
Campagne segment à risque | 🟠 |
| Segment endormi | list_rfm_segments |
Réactivation | 🟠 |
| Plat star sous-exposé | list_top_productions |
Mise en avant récurrente | 🟢 |
| Happy hour configurée | list_happy_hours |
Rappel la veille | 🟢 |
| Production signature planifiée | list_production_plans |
Contenu coulisses | 🟢 |
| Anniversaire client | list_clients |
Message personnel — jamais un post | 🟢 |
Scoring et déduplication
score = urgence × valeur_commerciale × fraîcheur- Valeur commerciale : la marge réelle du plat, lue via
get_recipe— jamais estimée. Marge indisponible = le dire, scorer sur l'urgence seule. - Fraîcheur : un sujet traité dans les 14 derniers jours est déclassé —
vérifier dans
./rapido-kb/iris/journal-signaux.md(l'historique local). - Déduplication obligatoire : deux signaux qui pointent le même plat fusionnent en UNE opportunité (le score le plus élevé gagne).
- Seuils d'échantillon : un « jour creux » identifié sur moins de 3 commandes
par jour observé = « données insuffisantes », pas une opportunité (même
règle que le skill
croisement-servicedu plugin foodeatup-boucles).
Règles absolues
- Un avis négatif ne produit JAMAIS de proposition de contenu : alerte au
patron (
create_notification), et c'est tout. - Chaque opportunité retenue porte sa raison en une phrase : « Parce que… », fondée sur la donnée qui l'a déclenchée (chiffre + source).
- Tout ce qui est détecté — retenu ou non — est consigné avec son score dans
./rapido-kb/iris/journal-signaux.md: c'est le journal qui crée la confiance (le restaurateur voit qu'Iris regarde tout).
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.
- 10d ago First seen · 63 lines · 87 tokens per session scan A 14fccdbad591
moteur-opportunites-iris is a skill published in the GitHub repository PrendsTaPart/Plugin-Claude-MCP-BraindCode- (8 stars, last pushed 17d ago), licensed Apache-2.0. It adds 87 tokens to every session and 940 once invoked, about $0.0004 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…