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/_template/skills/competences/marqueurs/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/marqueurs)<a href="https://agentmods.dev/skills/ai-swiss/base/marqueurs"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/marqueurs/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/marqueurs"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/marqueurs.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 | $0.00032 | $0.01013 |
| Opus 5.5 | $0.00013 | $0.00405 |
| Sonnet 5.5 | $0.00006 | $0.00203 |
| Haiku 4.5 | $0.00003 | $0.00101 |
Grade A, and why
marqueurs 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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marqueurs
Conventions pour rendre l'état du travail visible à même les fichiers. Un marqueur est un fragment de texte structuré, posé dans les documents générés (devis, fiches clients, rapports) et dans le journal. On n'en met jamais dans les fichiers du cadre (skills, AGENT.md).
À chaque phase de la boucle de co-pensée (Cadrer → Confier → Évaluer → Ajuster) correspond un marqueur.
Les 4 marqueurs
| Marqueur | Phase | Quand l'utiliser |
|---|---|---|
[A COMPLETER: champ] |
Cadrer | Il manque une information pour avancer. L'agent ou l'utilisateur devra la fournir. |
[A VALIDER: description] |
Confier | L'agent propose quelque chose que l'utilisateur n'a pas encore confirmé. |
[ATTENTION: description] |
Évaluer | Un risque, une incohérence ou une alerte à examiner par l'utilisateur. |
[DECISION: choix | raison] |
Ajuster | L'utilisateur a confirmé un choix. Consigné pour la traçabilité. |
Exemples concrets
[A COMPLETER], information manquante:
- **TVA :** [A COMPLETER: numéro IDE si assujetti]
- **Email :** [A COMPLETER]
[A VALIDER], proposition en attente:
[A VALIDER: Prix unitaire estimé à 150 CHF/h basé sur le catalogue]
[A VALIDER: Délai de livraison 3 semaines à confirmer avec le fournisseur]
[ATTENTION], alerte:
[ATTENTION: Montant supérieur à 10'000 CHF, conditions de paiement à vérifier]
[ATTENTION: Numéro TVA toujours manquant dans la fiche entreprise]
[DECISION], choix confirmé:
[DECISION: Remise de 10% | Client fidèle depuis 2 ans]
[DECISION: Arche florale à 1'100 CHF | Pivoines plus coûteuses que les roses standard]
Forme enrichie de [DECISION]
La forme courante suffit le plus souvent. Quand le choix porte à conséquence (montant élevé, engagement ferme, donnée difficile à corriger), la forme enrichie aide à retracer pourquoi il a été fait:
Forme courante (par défaut):
[DECISION: Arche florale à 1'100 CHF | Pivoines plus coûteuses que les roses standard]
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.
- 2mo ago First seen · 92 lines · 32 tokens per session scan A a4f4fa988db7
marqueurs is a skill published in the GitHub repository ai-swiss/base (65 stars, last pushed 8d ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,013 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.
marqueurs compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| marqueursai-swiss/base | Skill | 65 | 8d ago | Apache-2.0 | A | 32 | Claude Code |
| complianceericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 96 | Claude Code, Codex |
| wallet-cliBofAI/skills | Skill | 164 | 4d ago | MIT | A | 92 | Codex |
| vaultjoelhooks/joelclaw | Skill | 65 | yesterday | none | A | 82 | Claude Code |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |
| interviewHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 40 | Claude Code, Codex |
| atmos-validationcloudposse/atmos | Skill | 1.4k | yesterday | Apache-2.0 | A | 31 | Claude Code |