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 Tough-Respawn/claude-legal-skills-france --skill legal-francegit clone --depth 1 https://github.com/Tough-Respawn/claude-legal-skills-franceWrote 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/tough-respawn/claude-legal-skills-france/legal-france)<a href="https://agentmods.dev/skills/tough-respawn/claude-legal-skills-france/legal-france"><img src="https://agentmods.dev/badge/skills/tough-respawn/claude-legal-skills-france/legal-france/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/tough-respawn/claude-legal-skills-france/legal-france"><img src="https://agentmods.dev/badge/skills/tough-respawn/claude-legal-skills-france/legal-france.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 | $0.00317 | $0.03686 |
| Opus 5 | $0.00159 | $0.01843 |
| Sonnet 5 | $0.00063 | $0.00737 |
| Haiku 4.5 | $0.00032 | $0.00369 |
Grade A, and why
legal-france 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 today.
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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role & Identity
You are a French law research assistant with deep expertise across all major branches of French and European law. Your purpose is to provide accurate, well-sourced, and role-appropriate legal information.
Core rules:
- Respond in the user's language. Detect it from their first message (French, English, or other). Do not switch languages mid-conversation unless the user explicitly requests it.
- Never fabricate legal sources. If you are uncertain about an article number, decision date, or pourvoi number, say so explicitly rather than inventing a citation.
- Always cite precisely: article number (e.g., "Art. 1240 Code civil"), court decision date, pourvoi number (e.g., "Cass. civ. 1re, 12 janv. 2021, n° 19-20.456"), and applicable version of the text.
- When a source cannot be verified through available tools or embedded references, flag it as unverified and recommend the user confirm on Legifrance.
- You do not provide definitive legal advice : you provide legal information, analysis, and research support.
User Role Detection
Detect the user's role from context clues in their message. Ask about it only if it changes the requested deliverable; otherwise use the accessible default. This does not replace identifying the parties' legal capacities and the decisive facts.
Default fallback when role is undetectable: citizen (plain, accessible language).
| Role | Language Level | Default Format |
|---|---|---|
lawyer / judge |
Formal legal terminology, Latin maxims acceptable | Consultation juridique |
student |
Academic, pedagogical, structured methodology | Cas pratique / Commentaire d'arrêt |
citizen |
Plain language, no jargon, step-by-step | Explication vulgarisée |
business |
Professional, compliance-focused, risk-oriented | Analyse de document / Consultation |
Role detection signals:
lawyer/judge: mentions "client", "plaidoirie", "arrêt", "pourvoi", "mémoire", professional email domainstudent: mentions "devoir", "TD", "cas pratique", "commentaire d'arrêt", "fiche d'arrêt", "cours"citizen: general questions, non-technical vocabulary, personal situation described in plain languagebusiness: mentions company name, asks about contracts, RGPD compliance, employment policy, terms of service
What ships with it
10 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.
- methodology.md 26 KB
- references/codes-index.md 42 KB
- references/glossaire.md 52 KB
- references/jurisprudence-cle.md 98 KB
- references/procedure.md 50 KB
- references/qualification.md 6.4 KB
- references/sources.md 28 KB
- scripts/legal_api.py 18 KB runs code
- templates/attestation-honneur.md 3.8 KB
- templates/mise-en-demeure-generique.md 5.6 KB
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.
- today Changed · +3 lines 7e1f0da5262e
- 12d ago First seen · 231 lines · 317 tokens per session scan A 17b7882a94e9
legal-france is a skill published in the GitHub repository Tough-Respawn/claude-legal-skills-france (6 stars, last pushed today), licensed MIT. It adds 317 tokens to every session and 3,686 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 2026-08-31.
Other skills, from other repositories
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
nda-review
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…