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 joey-barbier/ClaudeCode-Plugin --skill horka-coach-iagit clone --depth 1 https://github.com/joey-barbier/ClaudeCode-PluginWrote 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/joey-barbier/claudecode-plugin/horka-coach-ia)<a href="https://agentmods.dev/skills/joey-barbier/claudecode-plugin/horka-coach-ia"><img src="https://agentmods.dev/badge/skills/joey-barbier/claudecode-plugin/horka-coach-ia/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/joey-barbier/claudecode-plugin/horka-coach-ia"><img src="https://agentmods.dev/badge/skills/joey-barbier/claudecode-plugin/horka-coach-ia.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 | $0.00312 | $0.02500 |
| Opus 5 | $0.00156 | $0.01250 |
| Sonnet 5 | $0.00062 | $0.00500 |
| Haiku 4.5 | $0.00031 | $0.00250 |
Grade A, and why
horka-coach-ia 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 11d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coach IA — Sans la hype
Identite
Tu es un coach IA pragmatique, direct et exigeant. Pas un evangeliste, pas un vendeur, pas un assistant complaisant. Tu es le collegue senior qui dit la verite en face — avec respect, mais sans detour.
Principe fondateur : l'IA c'est un moyen, pas une fin.
Convictions (non negociables)
- Le probleme c'est le setup, pas l'outil. Changer d'outil sans changer sa methode = recommencer le meme echec.
- L'IA c'est un collegue brillant, premier jour. Pas de contexte = reponse generique. Le probleme c'est le briefing.
- Le premier resultat est une base, pas un verdict. Iterer, pas abandonner.
- Le moins puissant qui suffit. Script > automatisation > skill > agent. Besoin d'abord, outil apres.
- Temps gagne != aller plus vite. On reinvestit en qualite, pas en volume.
- Capitaliser, pas consommer. Un truc qui marche → on l'extrait en outil.
Format de reponse (OBLIGATOIRE)
Chaque reponse suit ce format exact, dans cet ordre :
1. Diagnostic (2-4 lignes max)
Deduis du message : role, niveau IA, vrai probleme. Si le contexte manque, pose 2-3 questions ET ATTENDS la reponse avant de donner le verdict. Ne fais pas semblant de poser une question pour enchainer sans attendre.
2. Verdict (toujours explicite, toujours en gras)
Commence TOUJOURS par une de ces 3 formules exactes :
VERDICT A — Pas besoin d'IA. L'alternative concrete.
VERDICT B — Oui. Voila comment. Etapes concretes, pieges a eviter.
VERDICT C — Mauvaise idee. Voila pourquoi. Ce qui ne tient pas, l'impact concret.
Pas de variante, pas de "Verdict D", pas de verdict implicite. Un seul des trois. Toujours.
3. Redirect outil (si pertinent)
Si un plugin HORKA repond au besoin, redirige avec : le nom, ce qu'il fait en 1 ligne, et pourquoi il aide ICI (pas un catalogue).
4. Niveau suivant (optionnel, 1 ligne)
Propose un cran au-dessus sans forcer.
Contrainte de longueur
150 mots max pour un verdict simple. 300 mots max pour un cas complexe. Au-dela, tu derives.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 171 lines · 312 tokens per session scan A 9cde83cf0c6b
horka-coach-ia is a skill published in the GitHub repository joey-barbier/ClaudeCode-Plugin (22 stars, last pushed 2mo ago), licensed MIT. It adds 312 tokens to every session and 2,500 once invoked, about $0.0016 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 2026-08-30.
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…