Borrowing it
Nothing to install: this file belongs to ai-swiss/base. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ai-swiss/base/main/.ai/agents/createur-agent/skills/processes/activer-voie2/SKILL.mdgit clone --depth 1 https://github.com/ai-swiss/baseWrote 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/ai-swiss/base/activer-voie2)<a href="https://agentmods.dev/skills/ai-swiss/base/activer-voie2"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/activer-voie2/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/ai-swiss/base/activer-voie2"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/activer-voie2.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00075 | $0.02484 |
| Opus 5 | $0.00037 | $0.01242 |
| Sonnet 5 | $0.00015 | $0.00497 |
| Haiku 4.5 | $0.00007 | $0.00248 |
Grade A, and why
activer-voie2 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 10d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Activer la Voie 2 (routage par embeddings)
BASE route de deux façons, et l'utilisateur choisit par la configuration.
- Voie 1 (défaut, déjà active). L'assistant lit l'index généré et choisit; un plancher déterministe par mots-clés sert de filet. Aucun modèle, rien à installer. Pour la plupart des BASE, elle suffit largement.
- Voie 2 (optionnelle, pour l'échelle). Quand le catalogue de process devient grand, les embeddings retrouvent les quelques candidats les plus proches de la demande, puis un petit modèle les lit et tranche (il choisit, ou demande une précision). Le tout en local, souverain, sans clé d'API.
Ce process accompagne quelqu'un qui veut activer la Voie 2. La promesse: c'est, pour l'essentiel, «juste Ollama». Installer l'application, télécharger deux modèles, renseigner les deux dans les Réglages. La Voie 2 ne s'allume qu'une fois les deux modèles renseignés; un seul ne change rien.
Note durable: ce process est une consigne que suit le modèle, pas un script figé. Il ne fige aucune version, aucun nom de modèle exact, aucune commande d'installation, car l'écosystème Ollama évolue. À chaque étape technique, tu consultes la documentation officielle courante (installation, modèles recommandés) au moment où tu agis, puis tu proposes ce qui convient aujourd'hui. Les noms de modèles cités plus bas sont des exemples illustratifs, non une prescription.
Pourquoi c'est utile (à expliquer simplement)
«Aujourd'hui, l'assistant choisit le bon savoir-faire en lisant la liste de vos process. Tant qu'ils sont peu nombreux, ça marche très bien. Quand ils se comptent par dizaines ou centaines, on peut aider: un petit modèle local retrouve d'abord les quelques candidats les plus proches de votre demande, puis tranche. Tout reste sur votre machine, rien ne part dans le nuage.»
D'abord: en avez-vous besoin?
Ne vends pas la Voie 2. Aide à décider, honnêtement.
- Petit ou moyen BASE (quelques agents, quelques dizaines de process au plus) → la Voie 1 suffit. Dis-le clairement: activer la Voie 2 ajouterait une installation pour un gain nul ou marginal.
- Grand BASE (beaucoup de process, ou un routage qui se trompe parce que la liste est trop longue à départager par mots-clés) → la Voie 2 en vaut la peine.
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.
- 10d ago First seen · 127 lines · 75 tokens per session scan A 5ff23b5bb519
activer-voie2 is a skill published in the GitHub repository ai-swiss/base (45 stars, last pushed 6d ago), licensed Apache-2.0. It adds 75 tokens to every session and 2,484 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 2026-08-30.
Other skills, from other repositories
shap
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing…
glycobiology
Glycosylation site prediction and glycobiology analysis. N-glycosylation motif finding, O-glycosylation hotspot prediction, glycan structure resources. Lightweight, pure Python. For protein function queries use uniprot-database; for structure analysis use alphafold-database.
esm
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…
aeon
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard…
llm-as-judge-evaluation
Evaluate LLM outputs using frontier models as judges. Use for pairwise model comparison, quality scoring with custom rubrics, and automated evaluation pipelines. Covers position bias mitigation, statistical significance, and generating preference data for DPO/RLHF.
groq-inference
Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.