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-routage/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-routage)<a href="https://agentmods.dev/skills/ai-swiss/base/activer-routage"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/activer-routage/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-routage"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/activer-routage.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 | $0.00059 | $0.01437 |
| Opus 5 | $0.00030 | $0.00718 |
| Sonnet 5 | $0.00012 | $0.00287 |
| Haiku 4.5 | $0.00006 | $0.00144 |
Grade A, and why
activer-routage 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Activer le routage
Donner à l'assistant un routeur fiable: au lieu de deviner quel agent répond à une demande, il interroge un moteur déterministe, testé, capable de dire honnêtement «je ne sais pas». Ce process branche ce moteur par l'une de deux portes: le serveur MCP, pour les applications de chat, ou la CLI, pour les outils dotés d'un terminal.
Pourquoi c'est utile (à expliquer simplement)
«Aujourd'hui, l'assistant choisit le bon savoir-faire en lisant des instructions; cela fonctionne, mais il peut se tromper sans le dire. Une fois le routage activé, il s'appuie sur un moteur qui tranche toujours de la même façon et qui signale clairement quand la demande sort de son périmètre. Cinq minutes pour le brancher, et il gagne en fiabilité pour de bon.»
Inputs
Interroge l'utilisateur, une question à la fois:
- Quel outil utilisez-vous? Une application de chat (ChatGPT, Claude Desktop) ou un outil avec terminal (Claude Code, Cursor)?
- Au besoin: disposez-vous d'un terminal et de Node.js?
Si l'utilisateur l'ignore, propose de regarder ensemble; ne présume rien.
Étapes
1. Choisir la porte
Deux chemins, un même moteur:
- Application de chat sans terminal (ChatGPT, Claude Desktop) → serveur MCP (étape 2).
- Outil avec terminal (Claude Code, Cursor) → CLI, plus simple (étape 3).
«D'après votre outil, je propose [MCP / la CLI]. On y va?»
← Reformulation (confirmer le chemin)
2. Porte MCP (apps de chat)
Le serveur MCP expose le routeur comme un outil que l'application peut appeler.
- Construire le serveur (une seule fois). Si tu disposes d'un terminal, propose d'exécuter les commandes; sinon, transmets-les à l'utilisateur:
cd mcp && npm install && npm run build - Brancher dans l'app:
- Claude Code / Desktop:
claude mcp add base -- node <chemin>/mcp/dist/index.js --root <chemin>/votre-projet - ChatGPT (Mode Développeur): le lancer en HTTP avec un jeton, puis l'ajouter comme connecteur; voir
mcp/README.md.
- Claude Code / Desktop:
- Vérifier:
claude mcp listdoit afficherbase … ✓ Connected.
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 · 109 lines · 59 tokens per session scan A db2974c72aee
activer-routage is a skill published in the GitHub repository ai-swiss/base (45 stars, last pushed 6d ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,437 once invoked, about $0.0003 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
wallet-cli
Operate the TypeScript TRON wallet CLI for accounts, transfers, staking, governance, contracts, signing, chain queries, and password input with wallet-cli 4.13.0. Refuse wallet passwords in argv and require the supported stdin channel. For Java REPL requests, refuse that entry and offer the TypeScript one-shot CLI…
compliance
Use when scoping which regulatory frameworks bind a business — SOC 2, ISO 27001, HIPAA, PCI DSS, EU AI Act, DORA, NIS2 — building a control register with owners and evidence, or standing up the cadence that keeps it audit-ready. NOT drafting privacy-policy/ROPA/DPA or ToS text (that is gdpr-privacy, terms-conditions)…
vault
Operate Joel's Obsidian Vault through the joelclaw CLI. Use when reading ADRs/projects, searching notes, listing PARA sections, or auditing ADR hygiene with vault adr commands. Triggers on: 'check the vault', 'read ADR', 'find this note', 'vault search', 'ADR collisions', 'ADR audit', 'decision inventory', or any…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.