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/creer-agent/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/creer-agent)<a href="https://agentmods.dev/skills/ai-swiss/base/creer-agent"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/creer-agent.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.03041 |
| Opus 5 | $0.00019 | $0.01520 |
| Sonnet 5 | $0.00008 | $0.00608 |
| Haiku 4.5 | $0.00004 | $0.00304 |
Grade A, and why
creer-agent 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 8d 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Créer un agent
Guider l'utilisateur de la description de son besoin jusqu'à un agent IA métier fonctionnel.
RÈGLE ABSOLUE
Ne crée AUCUN fichier avant l'étape 7. Les étapes 1 à 6 forment une conversation de découverte et de conception. L'étape 6 s'achève sur un plan complet que l'utilisateur doit approuver explicitement. Si l'utilisateur dit «Crée un assistant pour X», réponds par une question, jamais par la création d'un fichier.
Inputs
Demande à l'utilisateur:
- Son métier ou activité: que fait son entreprise?
- Ce qu'il attend de l'assistant: quelles tâches il aimerait automatiser ou structurer?
Avant de parler de fichiers ou de métadonnées, clarifie le niveau de structure souhaité avec des mots simples:
- assistant unique que l'utilisateur sélectionne lui-même;
- assistant avec plusieurs workflows proches;
- assistant où BASE choisit automatiquement le bon workflow;
- assistant destiné à une équipe ou à une publication.
Si l'utilisateur ne sait pas par où commencer, charge skills/competences/exemples-agents/SKILL.md pour lui montrer des idées.
Étapes
1. Découvrir le besoin
Commence par des questions ouvertes. Le but est de comprendre le quotidien de l'utilisateur, non de parler technique.
«Racontez-moi votre journée type. Quelles tâches vous prennent le plus de temps? Qu'est-ce qui vous frustre dans votre travail quotidien?»
Questions complémentaires:
- «Quelles tâches faites-vous de manière répétitive?»
- «Quels documents rédigez-vous régulièrement?»
- «Quelles informations devez-vous chercher souvent?»
- «Si vous aviez un assistant parfait, que lui demanderiez-vous en premier?»
«Si je comprends bien, vous passez beaucoup de temps à [tâche] et vous aimeriez que l'assistant vous aide à [objectif]. C'est bien cela?»
← Reformulation
2. Identifier les workflows → processes
Pour chaque tâche relevée, approfondis:
«Prenons [tâche]. Quand vous la faites aujourd'hui, quelles sont les étapes? De quoi avez-vous besoin pour commencer? Comment savez-vous que c'est terminé?»
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.
- 8d ago First seen · 238 lines · 38 tokens per session scan A 6217a4c4e5e5
creer-agent is a skill published in the GitHub repository ai-swiss/base (44 stars, last pushed 4d ago), licensed Apache-2.0. It adds 38 tokens to every session and 3,041 once invoked, about $0.0002 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.