agentmods.dev

satelia-mcp-lucca: Instructions file for Claude Code

CLAUDE.md

satelia-mcp-lucca CLAUDE.md is an instructions file for Claude Code from Para-FR/satelia-mcp-lucca. It costs 371 tokens per session, scanned A, original, MIT.

A project instruction file for a TypeScript MCP server intended as a starting point for non-technical users. It explains how to add tools, write French messages, and test changes.

In plain words
What is it for?
Adding MCP tools in the designated source section, defining their inputs with Zod, returning text responses, and keeping logs separate from protocol output.
Why use it?
It gives consistent rules for extending the server without having to infer its structure or communication conventions.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is Para-FR/satelia-mcp-lucca's own configuration. It tells Claude Code how to work on satelia-mcp-lucca 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 satelia-mcp-lucca configures →

not rated 0repo 4mo ago A scan 371 tokens original MIT
View source ↗ Para-FR/satelia-mcp-lucca
Reuse

Borrowing it

Nothing to install: this file belongs to Para-FR/satelia-mcp-lucca. 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/Para-FR/satelia-mcp-lucca/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Para-FR/satelia-mcp-lucca

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 satelia-mcp-lucca CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/para-fr/satelia-mcp-lucca/claude-md/github.svg)](https://agentmods.dev/instructions/para-fr/satelia-mcp-lucca/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/para-fr/satelia-mcp-lucca/claude-md"><img src="https://agentmods.dev/badge/instructions/para-fr/satelia-mcp-lucca/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 satelia-mcp-lucca CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/para-fr/satelia-mcp-lucca/claude-md"><img src="https://agentmods.dev/badge/instructions/para-fr/satelia-mcp-lucca/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 371 This file is loaded in full into every session.
When invoked 371 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 $0.00371 $0.00371
Opus 5.5 $0.00148 $0.00148
Sonnet 5.5 $0.00074 $0.00074
Haiku 4.5 $0.00037 $0.00037

Measured 2mo ago against content hash 3fce1de1d209, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

satelia-mcp-lucca 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 2mo 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 · 25 lines

What it actually says

Memoire projet · satelia-mcp-starter

Ce depot est un serveur MCP en TypeScript, pense comme une base de depart pour des personnes non-techniques.

Convention pour ajouter un outil

  • Tous les outils se declarent dans src/index.ts.
  • L'emplacement reserve est marque par le bloc // ====== AJOUTEZ VOTRE OUTIL ICI ======. Ajoutez les nouveaux outils a cet endroit.
  • Un outil se declare avec server.registerTool(nom, config, handler) :
    • nom : identifiant court en minuscules avec des tirets (ex. compter-mots).
    • config : un objet { title, description, inputSchema }. La description doit etre en francais et expliquer clairement a quoi sert l'outil.
    • inputSchema : un OBJET SIMPLE (raw shape) ou chaque cle est un champ decrit avec Zod, par exemple { texte: z.string().describe("...") }. Ce n'est PAS un z.object(...).
    • handler : une fonction async qui recoit les champs valides (ex. async ({ texte }) => ...) et renvoie { content: [{ type: "text", text: "..." }] }.

Style

  • Tout en francais : commentaires, descriptions, messages.
  • Les messages d'information vont sur stderr (console.error), jamais sur stdout (reserve au protocole MCP).

Pour tester

  • npm run build doit toujours reussir avant de considerer une modification terminee.
  • npm run dev lance le serveur depuis les sources pour une verification rapide.
  • Apres un build, redemarrer Claude Desktop pour qu'il recharge le serveur.
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. 2mo ago First seen · 25 lines · 371 tokens per session scan A 3fce1de1d209

Subscribe to this mod's changes

satelia-mcp-lucca CLAUDE.md is an instructions file published in the GitHub repository Para-FR/satelia-mcp-lucca (0 stars, last pushed 4mo ago), licensed MIT. It adds 371 tokens to every session, about $0.0015 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.

Related

satelia-mcp-lucca CLAUDE.md compared with instructions from other repositories

satelia-mcp-lucca CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
satelia-mcp-lucca CLAUDE.mdPara-FR/satelia-mcp-luccaInstructions file04mo agoMITA371Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, 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