agentmods.dev

Legal: Instructions file for Claude Code

CLAUDE.md

Legal CLAUDE.md is an instructions file for Claude Code from BenjoNX/Legal. It costs 540 tokens per session, scanned A, original, MIT.

Project instructions for a French legal research server that uses Légifrance and JudiLibre, including its available searches and command shortcuts.

In plain words
What is it for?
Use them to guide searches of French laws and court decisions, retrieve source texts, and run commands such as /rechercher-droit or /analyser-contrat.
Why use it?
They tell the coding agent how this project is organized and which tools to use when handling French legal questions.

Instructions file for Claude Code

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

This is BenjoNX/Legal's own configuration. It tells Claude Code how to work on Legal 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 Legal configures →

not rated 0repo 8mo ago A scan 540 tokens original MIT
View source ↗ BenjoNX/Legal
Reuse

Borrowing it

Nothing to install: this file belongs to BenjoNX/Legal. 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/BenjoNX/Legal/claude/french-legal-mcp-server-FwIH9/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/BenjoNX/Legal

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 Legal CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/benjonx/legal/claude-md/github.svg)](https://agentmods.dev/instructions/benjonx/legal/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/benjonx/legal/claude-md"><img src="https://agentmods.dev/badge/instructions/benjonx/legal/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 Legal CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/benjonx/legal/claude-md"><img src="https://agentmods.dev/badge/instructions/benjonx/legal/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 540 This file is loaded in full into every session.
When invoked 540 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 $0.00540 $0.00540
Opus 5.5 $0.00216 $0.00216
Sonnet 5.5 $0.00108 $0.00108
Haiku 4.5 $0.00054 $0.00054

Measured 2mo ago against content hash 6479f24164c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Legal 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 · 51 lines

What it actually says

Projet

Serveur MCP interrogeant les API publiques du droit français (Légifrance et JudiLibre) via PISTE, accompagné d'un plugin "LEGAL FR" adapté au droit français.

Serveur MCP — Outils disponibles

Les outils suivants sont exposés via le serveur MCP droit-francais :

Légifrance (textes législatifs et réglementaires)

  • rechercher_legifrance(recherche, fond, type_champ, type_recherche, code, date_debut, date_fin, page, page_taille, tri, operateur) — Recherche multi-critères
  • consulter_legifrance(id) — Texte intégral par ID (LEGIARTI, LEGITEXT, JURITEXT, etc.)

JudiLibre (jurisprudence)

  • rechercher_jurisprudence_judilibre(recherche, juridiction, localisation, chambre, type_decision, theme, solution, date_debut, date_fin, tri, ordre, nombre_resultats, page) — Recherche de décisions
  • consulter_decision_judilibre(decision_id) — Texte intégral d'une décision
  • obtenir_taxonomie_judilibre(taxonomy_id, key, value, context_value) — Valeurs valides des filtres

Commandes slash

  • /rechercher-droit [termes] — Recherche dans les sources officielles
  • /analyser-contrat — Analyse clause par clause selon le droit français
  • /trier-nda — Triage d'accord de confidentialité
  • /veille-juridique [daily|theme|incident] [sujet] — Briefing juridique
  • /repondre [type] — Réponse type juridique

Configuration

  • Identifiants PISTE dans .env (jamais committé)
  • Serveur MCP configuré dans .mcp.json
  • Skills dans .claude/skills/
  • Commandes dans .claude/commands/

Lancer le serveur MCP

source venv/bin/activate
python droit_francais_MCP.py

Tests

# Tests unitaires (pas besoin de réseau)
pytest test_unit_legifrance.py test_unit_judilibre.py -v -m unit

# Tests d'intégration (nécessitent des identifiants PISTE valides)
pytest test_api_legifrance.py test_api_judilibre.py -v -m integration
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 · 51 lines · 540 tokens per session scan A 6479f24164c9

Subscribe to this mod's changes

Legal CLAUDE.md is an instructions file published in the GitHub repository BenjoNX/Legal (0 stars, last pushed 8mo ago), licensed MIT. It adds 540 tokens to every session, about $0.0022 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.

Legal and complianceResearch
Related

Legal CLAUDE.md compared with instructions from other repositories

Legal CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Legal CLAUDE.mdBenjoNX/LegalInstructions file08mo agoMITA540Claude 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