base: Skill for Claude Code

.ai/agents/concierge-base/skills/processes/par-ou-commencer/SKILL.md

par-ou-commencer is a skill for Claude Code from ai-swiss/base. It costs 49 tokens per session (1,281 once invoked), scanned A, original, Apache-2.0.

A French-language guide that directs people to a suitable first entry point based on their profile, such as an individual, small business, developer, institution, or curious reader. It uses existing examples, kits, and demonstrations.

In plain words
What is it for?
Use it to design or follow an onboarding path for different audiences, especially when choosing which existing example, kit, or demonstration someone should open first.
Why use it?
It prevents people from having to understand the whole project before finding something relevant. The guide starts with the person's needs or concerns and points to a ready-made resource.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is ai-swiss/base's own configuration. It tells Claude Code how to work on base itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything base configures →

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/concierge-base/skills/processes/par-ou-commencer/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.

agentmods badge for par-ou-commencer

README.md
[![agentmods](https://agentmods.dev/badge/skills/ai-swiss/base/par-ou-commencer/github.svg)](https://agentmods.dev/skills/ai-swiss/base/par-ou-commencer)
Your own site
<a href="https://agentmods.dev/skills/ai-swiss/base/par-ou-commencer"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/par-ou-commencer/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.

agentmods 80×15 button for par-ou-commencer

Your own site · 80×15
<a href="https://agentmods.dev/skills/ai-swiss/base/par-ou-commencer"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/par-ou-commencer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,281 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.01281
Opus 5.5 $0.00020 $0.00512
Sonnet 5.5 $0.00010 $0.00256
Haiku 4.5 $0.00005 $0.00128

Measured 2mo ago against content hash f9539cf9c355, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

par-ou-commencer 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 2mo 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/concierge-base/skills/processes/par-ou-commencer/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Par où commencer selon votre profil

Orienter une personne vers sa porte d'entrée concrète, selon qui elle est. Le principe: ne jamais réexpliquer ce que fait un exemple (il le montre de lui-même), mais y conduire, en partant de ce que cette personne craint ou cherche. Tu pointes vers une porte déjà prête; tu ne récris pas ce qui se trouve derrière. La source de vérité des parcours de lecture est docs/start/lire-dans-quel-ordre.md: cite-la plutôt que de reconstruire un parcours de mémoire.

Chaque porte ouvre sur quelque chose de réel et déjà là: un exemple à ouvrir, un kit, une démo. Une idée commune à tous les profils: structurer le travail ménage les moments où vous validez ce que produit l'IA, au lieu de signer sans regarder.

Étapes

1. Identifier le profil

Si le profil n'est pas déjà clair dans la demande, pose une seule question:

«Pour vous orienter au plus juste: vous diriez-vous plutôt un particulier, un indépendant ou une PME, un développeur, une personne du secteur public, ou simplement curieux?»

2. Donner la porte qui correspond

Ouvre la bonne porte, en une à trois phrases, en partant de ce qui compte pour ce profil. Ne décris pas l'exemple en détail: conduis-y.

Particulier (réfléchir, décider, en privé)

Ce qui compte: l'IA ne devrait pas vous livrer une réponse toute faite que vous validez sans la regarder. Ouvrez exemples/assistant-reflexion/ et dites «Bonjour, je voudrais configurer mon espace de réflexion»: il décompose une décision et s'arrête là où c'est à vous de trancher. Tout reste local, pour vous seul.

Indépendant ou PME

Ce qui compte: l'IA ne devrait pas envoyer un devis ou un courrier erroné. Ouvrez un exemple proche de votre métier (exemples/assistant-devis-demo/, exemples/assistant-courrier/, exemples/assistant-rh/) et formulez une demande concrète, par exemple «Bonjour, je voudrais configurer mon activité». Quand vous voudrez le vôtre, je passe la main à createur-agent / diagnostic.

Read the full file on GitHub · 80 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.

  1. 2mo ago First seen · 80 lines · 49 tokens per session scan A f9539cf9c355

Subscribe to this mod's changes

par-ou-commencer is a skill published in the GitHub repository ai-swiss/base (65 stars, last pushed 8d ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,281 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.

Related

par-ou-commencer compared with skills from other repositories

par-ou-commencer next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
par-ou-commencerai-swiss/baseSkill658d agoApache-2.0A49Claude Code
complianceericrisco/rsc-harnessSkill5032d agoMITA96Claude Code, Codex
wallet-cliBofAI/skillsSkill1644d agoMITA92Codex
vaultjoelhooks/joelclawSkill65yesterdaynoneA82Claude Code
feishuHmbown/CodeWhaleSkill41k5d agoMITA33Claude Code, Codex
interviewHmbown/CodeWhaleSkill41k5d agoMITA40Claude Code, Codex
atmos-validationcloudposse/atmosSkill1.4kyesterdayApache-2.0A31Claude Code