A guided process for designing a business-specific AI assistant from an initial idea. It asks discovery questions and requires approval of the design before creating files.

Use it to define an assistant's business role, tasks, workflow structure, team use, and eventual implementation.

People often know they want an assistant but not what structure or workflows it needs. This process turns the business need into an agreed plan first.

How ai-swiss/base configures Claude Code

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/ai-swiss/base/main/.ai/agents/createur-agent/skills/processes/creer-agent/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/ai-swiss/base

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ai-swiss/base/creer-agent/github.svg)](https://agentmods.dev/skills/ai-swiss/base/creer-agent)

Your own site

<a href="https://agentmods.dev/skills/ai-swiss/base/creer-agent"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/creer-agent/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.

Your own site · 80×15

<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="Reviewed on agentmods" width="80" height="20"></a>

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,270 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.04270
Opus 5.5	$0.00015	$0.01708
Sonnet 5.5	$0.00008	$0.00854
Haiku 4.5	$0.00004	$0.00427

Measured 1mo ago against content hash 7f24bb041ac0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 1mo 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.

.ai/agents/createur-agent/skills/processes/creer-agent/SKILL.md · 289 lines

How it starts

The opening of the file, as written. The whole thing — 289 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, pas même le journal. 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.

Un plan fourni par l'utilisateur qui se déclare explicitement approuvé et autorise la création vaut approbation de l'étape 6. C'est le cas du plan qu'adopter-ce-dossier tire de l'export d'une fiche de proposition remplie. Quand on te remet directement cet export (…_proposition-filled.md), suis d'abord l'étape 6 d'adopter-ce-dossier: c'est elle qui lit l'export et en tire le plan. S'il manque au plan un élément qui change la structure, pose une seule question ciblée; sinon construis sans redemander le même accord. Quand un plan approuvé ou un export te fait commencer à l'étape 7, pose d'abord les étapes qui restent (7 à 12) comme au début: c'est sur ce chemin, le plus long en écritures, qu'une étape glisse le plus facilement.

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 procédures proches;
assistant où BASE choisit automatiquement la bonne procédure;
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

Avant l'étape 1, pose les étapes dans la liste de tâches de l'outil; sans elle, annonce-les une fois, avec les mots de la personne, puis coche-les au fil (compétence journal, Progression).

Read the full file on GitHub · 289 lines

Changes

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.

1mo ago Changed · +39 lines 7f24bb041ac0
1mo ago Changed · +12 lines b2af15a0b8b7
2mo ago First seen · 238 lines · 38 tokens per session scan A 6217a4c4e5e5

Subscribe to this mod's changes

creer-agent is a skill published in the GitHub repository ai-swiss/base (65 stars, last pushed 8d ago), licensed Apache-2.0. It adds 38 tokens to every session and 4,270 once invoked, about $0.0002 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 2026-08-30.

Building agents ai ai-agents cli cognitive-sovereignty digital-sovereignty governance

creer-agent next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
creer-agentai-swiss/base	Skill	65	8d ago	Apache-2.0	A	38	Claude Code
complianceericrisco/rsc-harness	Skill	503	2d ago	MIT	A	96	Claude Code, Codex
wallet-cliBofAI/skills	Skill	164	4d ago	MIT	A	92	Codex
vaultjoelhooks/joelclaw	Skill	65	yesterday	none	A	82	Claude Code
feishuHmbown/CodeWhale	Skill	41k	5d ago	MIT	A	33	Claude Code, Codex
interviewHmbown/CodeWhale	Skill	41k	5d ago	MIT	A	40	Claude Code, Codex
atmos-validationcloudposse/atmos	Skill	1.4k	yesterday	Apache-2.0	A	31	Claude Code

base: Skill for Claude Code