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 methode-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/methode-projet)<a href="https://agentmods.dev/skills/ai-swiss/base/methode-projet"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/methode-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/methode-projet"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/methode-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 | $0.00038 | $0.01123 |
| Opus 5.5 | $0.00015 | $0.00449 |
| Sonnet 5.5 | $0.00008 | $0.00225 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade A, and why
methode-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 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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Méthodologie de gestion de projet
Connaissances méthodologiques pour structurer, planifier et suivre des projets de manière pragmatique.
Principes fondamentaux
- Clarifier l'objectif avant de planifier. Un projet sans objectif clair produit un plan sans valeur.
- Découper en étapes gérables. De 3 à 7 grandes étapes, pas davantage. Le détail viendra au fil de l'eau.
- Chaque étape produit quelque chose. Un livrable, une décision, une validation. Pas d'étape floue.
- Les dates sont des engagements. Ne propose une date que si elle est réaliste. Mieux vaut dire «à définir» qu'inventer.
- Réviser régulièrement. Un plan n'est utile que s'il est mis à jour.
Décomposition d'un projet
Structure recommandée
Un projet se découpe en:
- Grandes étapes (3 à 7): les phases principales du projet
- Tâches (par étape): les actions concrètes à réaliser
- Jalons: les moments clés où une décision ou validation est nécessaire
Comment identifier les grandes étapes
Pose-toi ces questions:
- Quel est le résultat final attendu?
- Quelles sont les grandes phases pour y arriver? (préparation, réalisation, livraison)
- Quelles décisions doivent être prises en cours de route?
- Quelles validations sont nécessaires?
Nommage des étapes
Utilise des verbes d'action:
- «Définir le cahier des charges» (pas «Cahier des charges»)
- «Sélectionner le prestataire» (pas «Prestataire»)
- «Valider le budget» (pas «Budget»)
Terminologie
| Terme | Signification |
|---|---|
| Jalon | Moment clé du projet: une livraison, une décision, une validation |
| Livrable | Résultat concret d'une étape (document, produit, décision formalisée) |
| Partie prenante | Personne ou groupe concerné par le projet ou son résultat |
| Dépendance | Lien entre deux tâches: l'une doit être terminée avant que l'autre commence |
| Risque | Événement incertain qui pourrait affecter le projet |
| Rétroplanning | Calendrier construit à partir de la date de fin, en remontant vers le début |
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 First seen · 111 lines · 38 tokens per session scan A 6864728294a8
methode-projet is a skill published in the GitHub repository ai-swiss/base (53 stars, last pushed 12d ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,123 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.
Other skills, from other repositories
quality
Evaluates whether a GitHub issue is spam, empty, needs more information, or is OK to proceed.
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-project-manager
Coordinate projects — track tasks, schedule meetings, and share docs.
persona-event-coordinator
Plan and manage events — scheduling, invitations, and logistics.
persona-team-lead
Lead a team — run standups, coordinate tasks, and communicate.
ulw-execute
Executes a written ulw-plan work plan with Boulder state, evidence ledger, worktree discipline, and parallel subagents. Use when the user says ulw-execute or asks to run a .omo/plans plan.