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 mauryaland/mcp-magistrat-civil --skill raisonnement-juridiquegit clone --depth 1 https://github.com/mauryaland/mcp-magistrat-civilWrote 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/mauryaland/mcp-magistrat-civil/raisonnement-juridique)<a href="https://agentmods.dev/skills/mauryaland/mcp-magistrat-civil/raisonnement-juridique"><img src="https://agentmods.dev/badge/skills/mauryaland/mcp-magistrat-civil/raisonnement-juridique/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/mauryaland/mcp-magistrat-civil/raisonnement-juridique"><img src="https://agentmods.dev/badge/skills/mauryaland/mcp-magistrat-civil/raisonnement-juridique.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 | $0.00141 | $0.04704 |
| Opus 5.5 | $0.00056 | $0.01882 |
| Sonnet 5.5 | $0.00028 | $0.00941 |
| Haiku 4.5 | $0.00014 | $0.00470 |
Grade A, and why
raisonnement-juridique 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 14d 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.
How it starts
The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Raisonnement Juridique - Méthodologie du Magistrat Civil
Ce skill guide Claude pour analyser des dossiers juridiques civils en appliquant la méthodologie du magistrat français, basée sur les fiches méthodologiques de l'ENM/Cour de cassation (2023).
Capacités
- Analyser un litige : identifier les questions juridiques, qualifier les faits
- Construire un raisonnement juridique : syllogisme majeure/mineure/conclusion
- Rédiger une motivation : motivation complète, fidèle, impartiale, précise
- Rechercher les sources : jurisprudence (Judilibre) et textes (Légifrance)
- Distinguer prétentions/moyens/arguments : répondre correctement à chaque élément
- Évaluer la hiérarchie des décisions : pondérer les arrêts selon leur formation et publication
Outils MCP disponibles
Judilibre (jurisprudence)
judilibre_search: rechercher des décisions par mots-clés, chambre, date. Les filtres en liste (chamber,publication,formation,solution,jurisdiction...) acceptent plusieurs valeurs dans une seule requête (OU logique) :chamber=["pl", "mi"]interroge à la fois l'assemblée plénière et les chambres mixtes.judilibre_get_decision: récupérer le texte intégral d'une décisionjudilibre_get_taxonomy: obtenir les listes de référence (chambres, solutions, formations, publications)
Légifrance (textes légaux)
rechercher_code: rechercher dans les codes (Code civil, Code du travail...)rechercher_dans_texte_legal: rechercher dans les lois et décretsrecherche_journal_officiel: rechercher dans le JORFrecuperer_article: récupérer le texte intégral et les métadonnées d'un article par son ID (la version que désigne cet ID)recuperer_article_a_date: récupérer la version d'un article applicable à une date donnée (date des faits, du contrat...), avec la frise de toutes ses versions. Voir « Version applicable dans le temps » ci-dessous.
Hiérarchie des Décisions de la Cour de cassation
Formations de jugement (par ordre d'autorité décroissant)
What ships with it
5 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.
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.
- 14d ago Changed · +51 lines · +15 tokens per session fb7951415b75
- 2mo ago First seen · 326 lines · 126 tokens per session scan A 41ab4cc669c4
raisonnement-juridique is a skill published in the GitHub repository mauryaland/mcp-magistrat-civil (11 stars, last pushed 15d ago), licensed MIT. It adds 141 tokens to every session and 4,704 once invoked, about $0.0006 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.
raisonnement-juridique compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| raisonnement-juridiquemauryaland/mcp-magistrat-civil | Skill | 11 | 15d ago | MIT | A | 141 | Claude Code, Codex |
| fto-triageanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 81 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 68 | Claude Code |
| specification-writingwanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 49 | Claude Code |
| terms-of-servicegenspark-ai/genoffice | Skill | 12k | yesterday | Apache-2.0 | A | 32 | Claude Code, Codex |
| x-scorecardx-cmd/x-cmd | Skill | 4.7k | 7d ago | Apache-2.0 | A | 57 | Claude Code, Codex |
| gesellschaftsrechtliche-satzungen-agbKlotzkette/claude-fuer-deutsches-recht | Skill | 1.8k | yesterday | Apache-2.0 | A | 69 | Claude Code |