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 mesure-apprentissage-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-/mesure-apprentissage-iris)<a href="https://agentmods.dev/skills/prendstapart/plugin-claude-mcp-braindcode-/mesure-apprentissage-iris"><img src="https://agentmods.dev/badge/skills/prendstapart/plugin-claude-mcp-braindcode-/mesure-apprentissage-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-/mesure-apprentissage-iris"><img src="https://agentmods.dev/badge/skills/prendstapart/plugin-claude-mcp-braindcode-/mesure-apprentissage-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 | $0.00674 |
| Opus 5 | $0.00044 | $0.00337 |
| Sonnet 5 | $0.00017 | $0.00135 |
| Haiku 4.5 | $0.00009 | $0.00067 |
Grade A, and why
mesure-apprentissage-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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mesure & apprentissage (ce qui referme la boucle)
Sans cet étage, Iris est un générateur. Avec lui, elle apprend.
1. Collecter (chiffres réels uniquement)
post_insightspar publication,ingishts_campagnepar campagne (impressions, engagements, clics) — les chiffres se lisent, jamais s'extrapolent : moins de 48 h de vie = « trop tôt pour juger ».- Photo des planifications :
list_scheduled_posts(publié vs en attente).
2. Attribuer (la seule métrique qui compte)
- Croiser chaque publication avec
list_orderssur les 48 h suivantes : commandes du plat mis en avant vs sa moyenne habituelle (list_top_productionspour la base de comparaison). - Honnêteté statistique : sans code promo ni lien tracké (backlog produit, voir docs/FAISABILITE-IRIS.md), l'attribution est une corrélation, pas une preuve — l'écrire tel quel (« +9 commandes du plat vs moyenne, publication la veille — corrélation, pas attribution certaine »).
- Sous 3 commandes d'écart, verdict : « données insuffisantes ».
3. Apprendre (et le montrer)
Tout vit dans ./rapido-kb/iris/apprentissage.md :
- Prompts gagnants : un prompt visuel dont les publications performent
au-dessus de la moyenne de l'établissement est capitalisé via
add_prompt(RapidoCMS) et noté (canal, type de signal, performance). - Motifs de refus : ils pondèrent le scoring des signaux suivants du même type — un type de contenu refusé trois fois de suite cesse d'être proposé (et le journal le dit, pour que le restaurateur puisse le réactiver).
- Rythme : les heures/canaux qui performent remontent dans les
propositions du skill
calendrier-iris.
Sortie attendue
Un tableau [publication | canal | raison d'origine | impressions/engagements | commandes du plat vs moyenne | verdict], puis les enseignements appliqués
(« le format vidéo 9:16 sur les plats du jour surperforme → priorisé »).
Ce que ce skill NE fait PAS
- L'analyse de contenu généraliste multi-comptes → plugin rapidocms (skill
analyse-performance-contenu). - Prédire la viralité d'une vidéo avant publication →
virality_predictordans le skillvideo-virale-plats.
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 · 53 lines · 87 tokens per session scan A 366054100ce4
mesure-apprentissage-iris 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 87 tokens to every session and 674 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…