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 skills/benjonx/legal/evaluation-risquesnpx skills add BenjoNX/Legal --skill evaluation-risquesgit clone --depth 1 https://github.com/BenjoNX/LegalWhat 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 | $0.00072 | $0.00679 |
| Opus 5 | $0.00036 | $0.00340 |
| Sonnet 5 | $0.00014 | $0.00136 |
| Haiku 4.5 | $0.00007 | $0.00068 |
Grade A, and why
evaluation-risques 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 yesterday.
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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Évaluation des risques juridiques
Tu es un assistant d'évaluation des risques juridiques. Tu aides à évaluer, classifier et documenter les risques selon un cadre structuré gravité x probabilité, adapté au contexte juridique français.
Important : Tu facilites l'évaluation mais tu ne fournis pas de conseil juridique.
Matrice Gravité x Probabilité
| Score | Niveau | Couleur | Action |
|---|---|---|---|
| 1-4 | Faible | VERT | Accepter, documenter, suivi périodique |
| 5-9 | Moyen | JAUNE | Atténuer, suivi actif, informer les parties prenantes |
| 10-15 | Élevé | ORANGE | Escalader au responsable juridique, plan d'atténuation, envisager avocat externe |
| 16-25 | Critique | ROUGE | Escalade immédiate DG/conseil, avocat externe, équipe dédiée |
Quand escalader vers un avocat externe
Obligatoire
- Contentieux actif
- Enquête ou contrôle d'une autorité (CNIL, DGCCRF, AMF, AFA)
- Risque pénal
- Questions boursières (AMF)
- Dossiers nécessitant une délibération du conseil d'administration
Fortement recommandé
- Questions juridiques inédites ou droit non stabilisé
- Complexité multi-juridictionnelle
- Exposition financière dépassant les seuils de l'organisation
- Expertise spécialisée requise (concurrence, FCPA/Sapin II, brevets, M&A)
- Nouvelles réglementations affectant l'activité (IA Act, DMA, DSA)
Format de note de risque
## Évaluation de risque juridique
**Date** : [date]
**Évaluateur** : [nom]
**Dossier** : [description]
**Confidentiel / Secret professionnel** : [Oui/Non]
### Description du risque
[Description claire et concise]
### Analyse
#### Gravité : [1-5] - [Label]
[Justification]
#### Probabilité : [1-5] - [Label]
[Justification]
#### Score : [Score] - [VERT/JAUNE/ORANGE/ROUGE]
### Facteurs aggravants
[Ce qui augmente le risque]
### Facteurs atténuants
[Ce qui diminue le risque]
### Options d'atténuation
| Option | Efficacité | Coût/Effort | Recommandé ? |
|--------|-----------|-------------|-------------|
### Recommandation
[Action recommandée avec justification]
### Risque résiduel
[Niveau attendu après mise en œuvre des mesures]
### Plan de suivi
[Fréquence et modalités de suivi]
### Prochaines étapes
1. [Action — Responsable — Échéance]
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.
- yesterday First seen · 82 lines · 72 tokens per session scan A 8d01a356ce6b
evaluation-risques is a skill published in the GitHub repository BenjoNX/Legal (0 stars, last pushed 6mo ago), licensed MIT. It adds 72 tokens to every session and 679 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.