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.
curl -O https://raw.githubusercontent.com/ai-swiss/base/main/.ai/agents/createur-agent/skills/processes/entretien-base/SKILL.mdgit 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/entretien-base)<a href="https://agentmods.dev/skills/ai-swiss/base/entretien-base"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/entretien-base/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/entretien-base"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/entretien-base.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 | $0.00028 | $0.01435 |
| Opus 5.5 | $0.00011 | $0.00574 |
| Sonnet 5.5 | $0.00006 | $0.00287 |
| Haiku 4.5 | $0.00003 | $0.00144 |
Grade A, and why
entretien-base 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Entretien BASE
Aider l'utilisateur à maintenir un BASE lisible, fiable et réutilisable sans créer de dashboard lourd.
Déclencheurs
Utiliser ce process quand l'utilisateur dit:
- «Fais l'entretien de mon BASE.»
- «Vérifie ce BASE.»
- «Fais un audit de ce BASE.»
- «Est-ce prêt à publier ou partager?»
- «Fais une revue architecture, sécurité et cohérence.»
- «Qu'est-ce qui manque ou doit être nettoyé?»
- «Prépare ce dossier pour le partager à l'équipe.»
Étapes
1. Cadrer le périmètre
Demande quel dossier analyser si ce n'est pas évident, puis rappelle que l'entretien produit des propositions, et non des modifications automatiques.
«Je vais vérifier la cohérence du BASE, les liens, les marqueurs ouverts, les descriptions manquantes, les routes attendues, les artefacts générés, la posture MCP et les ressources qui méritent d'être promues. Je vous proposerai ensuite les corrections à valider.»
2. Vérifier la structure
Analyser:
- présence de
AGENT.md,SKILL.md,BASE_BOOTSTRAP.mdou équivalents; - organisation
.ai/agents/,skills/processes/,skills/competences/,templates/,tools/; - liens relatifs cassés;
- fichiers référencés mais absents;
- tools dont le script manque;
- chemins qui sortent du projet.
Si la CLI est disponible, s'appuyer sur les commandes suivantes (ajouter --root <dossier> pour cibler un BASE précis, sinon la racine courante):
base validate --root <dossier>
base route-test --root <dossier>
base doctor --root <dossier>
Selon le périmètre, vérifier aussi:
- les fixtures de routage des exemples importants;
- la fraîcheur des artefacts générés (
base index --root <dossier>,base build --write --root <dossier>, puis diff); - la cohérence entre docs, specs, README et exemples;
- les tools dont les scripts ou dépendances manquent;
- la distribution MCP si le BASE doit être connecté à une plateforme externe;
- les limites de sécurité documentées, surtout advisory vs strict.
3. Repérer les marqueurs ouverts
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 cf279c8ba3a4
- 1mo ago Changed · +2 lines 2be41783d6a7
- 2mo ago First seen · 159 lines · 28 tokens per session scan A 130519fe0c29
entretien-base is a skill published in the GitHub repository ai-swiss/base (65 stars, last pushed 8d ago), licensed Apache-2.0. It adds 28 tokens to every session and 1,435 once invoked, about $0.0001 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.
entretien-base compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| entretien-baseai-swiss/base | Skill | 65 | 8d ago | Apache-2.0 | A | 28 | Claude Code |
| obsidian-baseskepano/obsidian-skills | Skill | 51k | 1mo ago | MIT | A | 63 | Claude Code |
| x-osvx-cmd/x-cmd | Skill | 4.7k | 7d ago | Apache-2.0 | A | 72 | Claude Code, Codex |
| building-agentsericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 85 | Claude Code, Codex |
| postgresdbericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 91 | Claude Code, Codex |
| db-migrationsericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 90 | Claude Code, Codex |
| dynamodbericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 82 | Claude Code, Codex |