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.
npx skills add ai-swiss/base --skill nouveau-projetgit 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/nouveau-projet)<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.
<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>- 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 | $0.00014 | $0.01225 |
| Opus 5 | $0.00007 | $0.00613 |
| Sonnet 5 | $0.00003 | $0.00245 |
| Haiku 4.5 | $0.00001 | $0.00122 |
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.
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:
- [Étape] -> produit: [livrable]
- [Étape] -> produit: [livrable]
- [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?»
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.
- 11d ago First seen · 139 lines · 14 tokens per session scan A 4d1cc3a0e951
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.
Other skills, from other repositories
quality
Evaluates whether a GitHub issue is spam, empty, needs more information, or is OK to proceed.
gh-treasure-hunt
Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.
follow-up-after-call
Use after a completed customer, prospect, partner, or important internal sales call, discovery session, demo, or conversation, including when the user supplies or uploads a transcript, notes, recording summary, or other grounded evidence. Advise on, assess, qualify, recap, and produce seller-ready follow-up actions…
persona-event-coordinator
Plan and manage events — scheduling, invitations, and logistics.
persona-project-manager
Coordinate projects — track tasks, schedule meetings, and share docs.
persona-team-lead
Lead a team — run standups, coordinate tasks, and communicate.