nouveau-projet

nouveau-projet is a skill for Claude Code from ai-swiss/base. It costs 14 tokens per session (1,225 once invoked), scanned A, original, Apache-2.0.

A guided process for starting and organizing a new project from its initial request through its task breakdown, milestones, and project brief.

In plain words
What is it for?
Use it to clarify what a project must achieve, divide it into three to seven major stages, set milestones, and create its project record.
Why use it?
It turns a vague project idea into a clear plan by checking the context, constraints, people involved, budget, deadline, and success criteria.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to clarify what a project must achieve, divide it into three to seven major stages, set milestones, and create its project record.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ai-swiss/base/nouveau-projet
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ai-swiss/base --skill nouveau-projet
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 nouveau-projet

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ai-swiss/base/nouveau-projet"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/nouveau-projet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,225 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 $0.00014 $0.01225
Opus 5 $0.00007 $0.00613
Sonnet 5 $0.00003 $0.00245
Haiku 4.5 $0.00001 $0.00122

Measured 11d ago against content hash 4d1cc3a0e951, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

nouveau-projet 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 11d 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.

exemples/assistant-projet/.ai/agents/assistant-projet/skills/processes/nouveau-projet/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nouveau projet

Démarrer et structurer un nouveau projet de A à Z: comprendre le besoin, décomposer en tâches, définir les jalons, et créer la fiche projet.

Inputs

Demande à l'utilisateur:

  • Le projet: description libre de ce qu'il doit organiser ou accomplir
  • Le contexte: pourquoi ce projet, pour qui, quelles contraintes

Avant de commencer, vérifie que profil/identite.md est rempli. Sinon, charge skills/processes/configuration/SKILL.md.

Si .ai/journal/ contient des entrées récentes, lis-les pour te remettre en contexte.

Étapes

1. Comprendre le projet

Lis la description et reformule-la clairement:

«Si je comprends bien, votre projet consiste à:

  • [objectif principal]
  • [contexte / destinataires]
  • [contraintes mentionnées]

Est-ce correct? Y a-t-il des précisions à ajouter?»

Clarifie si nécessaire:

  • Y a-t-il une date butoir?
  • Qui sont les parties prenantes?
  • Y a-t-il un budget ou des ressources définies?
  • Quels sont les critères de réussite?

← Reformulation

2. Décomposer en grandes étapes

Lis la compétence skills/competences/methode-projet/SKILL.md pour la méthodologie.

Propose une décomposition en 3 à 7 grandes étapes (pas plus). Pour chaque étape:

  • Un intitulé clair et orienté action
  • Ce qu'elle produit concrètement (livrable ou décision)
  • Les dépendances éventuelles (quelle étape doit être terminée avant)

«Voici comment je propose de structurer votre projet:

  1. [Étape] -> produit: [livrable]
  2. [Étape] -> produit: [livrable]
  3. [Étape] -> produit: [livrable]

Est-ce que cette structure vous convient? Voulez-vous ajouter, regrouper ou détailler certaines étapes?»

← Reformulation

3. Définir les jalons et le calendrier

Pour chaque grande étape, propose:

  • Une date cible (d'après les contraintes connues et le profil de l'utilisateur)
  • Le responsable si plusieurs personnes sont impliquées

Présente sous forme de calendrier:

«Voici un rétroplanning proposé:

Jalon Date cible Responsable
[Étape 1] terminée [date] [qui]
[Étape 2] terminée [date] [qui]
Projet livré [date]

Ces dates sont-elles réalistes pour vous?»

Read the full file on GitHub · 139 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. 11d ago First seen · 139 lines · 14 tokens per session scan A 4d1cc3a0e951

Subscribe to this mod's changes

nouveau-projet is a skill published in the GitHub repository ai-swiss/base (45 stars, last pushed 7d ago), licensed Apache-2.0. It adds 14 tokens to every session and 1,225 once invoked, about $0.0001 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.