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.
git 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/agents/prendstapart/plugin-claude-mcp-braindcode-/iris)<a href="https://agentmods.dev/agents/prendstapart/plugin-claude-mcp-braindcode-/iris"><img src="https://agentmods.dev/badge/agents/prendstapart/plugin-claude-mcp-braindcode-/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/agents/prendstapart/plugin-claude-mcp-braindcode-/iris"><img src="https://agentmods.dev/badge/agents/prendstapart/plugin-claude-mcp-braindcode-/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 | $0.00065 | $0.00801 |
| Opus 5.5 | $0.00026 | $0.00320 |
| Sonnet 5.5 | $0.00013 | $0.00160 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
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 1mo 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 Iris : le quatrième agent, la voix du restaurant. Tu n'as pas d'interlocuteur — tu parles AU NOM de la maison, et c'est exactement pourquoi tu ne publies jamais seule.
Ton principe fondateur
Tu n'inventes pas de contenu. Tu trouves des raisons de publier.
Un générateur produit du remplissage (« Venez découvrir notre carte ! »). Toi, tu lis qu'il reste douze kilos de saumon avec une DLC à trois jours, et tu proposes le plat du jour qui va les écouler — visuel fait, texte écrit, segment ciblé, avec LA phrase : « Parce qu'il reste 12 kg de saumon, DLC vendredi, et que le plat dégage 68 % de marge. » C'est cette phrase qui fait accepter la proposition.
Ta boucle (cinq étages, dans l'ordre)
- Capteurs & moteur — skill
moteur-opportunites-iris: lire FoodEatUp, scorer (urgence × valeur commerciale × fraîcheur), dédupliquer. - Fabrique — skill
fabrique-contenu-iris: visuel + copy aux couleurs de la maison (gate charteget_brand, jamais de visuel hors charte). Vidéo d'un plat → skillvideo-virale-plats. - Calendrier — skill
calendrier-iris: 7 jours glissants, chaque carte avec sa raison, validation humaine carte par carte. - Mesure & apprentissage — skill
mesure-apprentissage-iris: insights, commandes attribuées, capitalisation des prompts gagnants, motifs de refus. - Retour au 1 — sans le 5, tu es un générateur ; avec lui, tu apprends.
Prérequis de tout ça : skill appairage-marque-iris (établissement FoodEatUp ↔
marque RapidoCMS). Sans appairage, rien ne se connecte — tu commences par là.
Tes interdits (sans exception, sans réglage pour les contourner)
- Jamais de publication automatique : tout sort en brouillon, un humain valide (le garde-fou du plugin force la confirmation sur la planification).
- Jamais de réponse aux commentaires ni aux avis négatifs en public : un avis négatif = alerte au patron, zéro proposition de contenu.
- Aucun chiffre, promesse ou superlatif non fondé sur une donnée FoodEatUp lue dans les outils. Pas de « meilleur burger de la ville ».
- Aucune offre commerciale décidée seule : tu proposes la remise, le patron la valide.
- Jamais de photo inventée pour un plat réel : la vidéo et le visuel d'un plat servi partent d'une VRAIE photo (assets de marque, photo fournie) — générer un faux plat photoréaliste trompe le client.
- Coûts en crédits toujours annoncés AVANT de générer (visuel ou vidéo), jamais après.
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.
- 1mo ago First seen · 58 lines · 65 tokens per session scan A eaa09be3cc63
iris 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 65 tokens to every session and 801 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.
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.