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 agentmods add instructions/benjonx/legal/claude-mdgit clone --depth 1 https://github.com/BenjoNX/LegalWrote 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/instructions/benjonx/legal/claude-md)<a href="https://agentmods.dev/instructions/benjonx/legal/claude-md"><img src="https://agentmods.dev/badge/instructions/benjonx/legal/claude-md.svg" alt="Measured on agentmods" 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 | $0.00540 | $0.00540 |
| Opus 5 | $0.00270 | $0.00270 |
| Sonnet 5 | $0.00108 | $0.00108 |
| Haiku 4.5 | $0.00054 | $0.00054 |
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 5d 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.
What it actually says
Serveur MCP Droit Français + Plugin LEGAL FR
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-critèresconsulter_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 décisionsconsulter_decision_judilibre(decision_id)— Texte intégral d'une décisionobtenir_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
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.
- 5d ago First seen · 51 lines · 540 tokens per session scan A 6479f24164c9
Legal CLAUDE.md is an instructions file published in the GitHub repository BenjoNX/Legal (0 stars, last pushed 6mo ago), licensed MIT. It adds 540 tokens to every session, about $0.0027 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 instructions, from other repositories
ZATCA AGENTS.md
AGENTS.md instructions for SallaApp/ZATCA: See CLAUDE.md for the full guide. Quick facts.
ayunis-legal-mcp CLAUDE.md
Instructions for ayunis-core/ayunis-legal-mcp, covering legal mcp - architecture and development guide, project overview, architecture, directory structure and key components.
korean-firefighter-law-mcp CLAUDE.md
Claude Code instructions for ssd7830-cmyk/korean-firefighter-law-mcp, covering korean-firefighter-law-mcp, a. 답변 규칙 — 기억이 아니라 이 저장소의 코드가 근거다, b. mcp 도구 사용 and c. 작업 규칙.
uae-regulations-registry AGENTS.md
AGENTS.md instructions for nshield-security/uae-regulations-registry, covering agents.md — instructions for ai agents, what this repo contains, preferred entry points, json schema (data/regulations.json) and stable urls.
spain-ai-kit CLAUDE.md
Instructions for aplaceforallmystuff/spain-ai-kit, a project described as: MCP servers connecting AI applications to Spanish government open data and legal infrastructure.
law-mcp CLAUDE.md
Claude Code instructions for finalchild/law-mcp, covering claude.md, build and development commands, architecture overview, core components and key integration points.