jarvis-assistant-vocal: Instructions file for Claude Code

CLAUDE.md

jarvis-assistant-vocal CLAUDE.md is an instructions file for Claude Code from sosoj92/jarvis-assistant-vocal. It costs 1,730 tokens per session, scanned A, original, MIT.

A project instruction file describing Jarvis, a local French voice assistant for Windows 11, and how Claude Code should work on it. It explains the project's mission, architecture, repository layout, and rules for adding or changing tools.

In plain words
What is it for?
It is for guiding development of voice input, speech transcription, local or cloud models, tools, browser or hardware actions, confirmations, and spoken responses.
Why use it?
It gives a coding agent the project context and safety boundaries it needs before editing code, including keeping sensitive actions and credentials under Jarvis's control.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions Claude Code.

This is sosoj92/jarvis-assistant-vocal's own configuration. It tells Claude Code how to work on jarvis-assistant-vocal itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything jarvis-assistant-vocal configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sosoj92/jarvis-assistant-vocal. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sosoj92/jarvis-assistant-vocal/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/sosoj92/jarvis-assistant-vocal

Made for: Claude Code.

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 jarvis-assistant-vocal CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sosoj92/jarvis-assistant-vocal/claude-md/github.svg)](https://agentmods.dev/instructions/sosoj92/jarvis-assistant-vocal/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sosoj92/jarvis-assistant-vocal/claude-md"><img src="https://agentmods.dev/badge/instructions/sosoj92/jarvis-assistant-vocal/claude-md/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.

agentmods 80×15 button for jarvis-assistant-vocal CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sosoj92/jarvis-assistant-vocal/claude-md"><img src="https://agentmods.dev/badge/instructions/sosoj92/jarvis-assistant-vocal/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,730 This file is loaded in full into every session.
When invoked 1,730 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01730 $0.01730
Opus 5.5 $0.00692 $0.00692
Sonnet 5.5 $0.00346 $0.00346
Haiku 4.5 $0.00173 $0.00173

Measured 1mo ago against content hash 1cc58150ec35, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

jarvis-assistant-vocal CLAUDE.md 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.

CLAUDE.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contexte Claude Code — Jarvis

Ce fichier donne à Claude Code le contexte permanent nécessaire pour travailler sur Jarvis sans devoir reconstituer le projet à chaque session.

Mission du projet

Jarvis est un assistant vocal local en français, principalement destiné à Windows 11. Il écoute un mot d'activation, transcrit la voix localement, choisit un modèle local ou cloud, appelle des outils et répond à voix haute.

Le projet privilégie :

  • une exécution locale dès que c'est raisonnable ;
  • des intégrations facultatives qui échouent proprement ;
  • une interaction vocale rapide et naturelle ;
  • une séparation stricte entre raisonnement et actions réelles ;
  • la confidentialité, la confirmation explicite et la maîtrise des coûts.

Doctrine d'architecture

Hermes orchestre et pense ; Jarvis détient les clés et le corps.

  • Hermes : analyse longue, recherche, synthèse, planification, tâches de fond et brouillons.
  • Jarvis : micro, caméra, écran, domotique, navigateur connecté, matériel, credentials, confirmations et exécution réelle.
  • Hermes ne reçoit jamais les credentials de Jarvis et n'exécute jamais une action sensible directement.
  • Une procédure Hermes récurrente, stable et éprouvée peut devenir une skill.

Carte du dépôt

  • jarvis14.py : point d'entrée principal de l'assistant vocal.
  • core/ : orchestration, configuration, voix, LLM, routage, sécurité, serveur, HUD, Hermes, satellites et services transverses.
  • tools/ : capacités appelables par le LLM, généralement une par fichier.
  • core/registre.py : décorateur @outil, découverte des outils et permissions.
  • hud.py et hud.html : interface locale principale.
  • web/ : interfaces web et ressources visuelles.
  • scripts/ : installation, diagnostic, automatisation et maintenance.
  • docs/ : guides par intégration.
  • tests/ : tests unitaires et de sécurité ciblés.
  • config.example.yaml : schéma public et générique de la configuration.
  • config.yaml : configuration locale privée, jamais versionnée.

Read the full file on GitHub · 172 lines

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. 1mo ago First seen · 172 lines · 1,730 tokens per session scan A 1cc58150ec35

Subscribe to this mod's changes

jarvis-assistant-vocal CLAUDE.md is an instructions file published in the GitHub repository sosoj92/jarvis-assistant-vocal (547 stars, last pushed 17d ago), licensed MIT. It adds 1,730 tokens to every session, about $0.0069 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 2026-10-01.

Related

jarvis-assistant-vocal CLAUDE.md compared with instructions from other repositories

jarvis-assistant-vocal CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
jarvis-assistant-vocal CLAUDE.mdsosoj92/jarvis-assistant-vocalInstructions file54717d agoMITA1,730Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode