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 agentmods add skills/ai-swiss/base/configurationnpx skills add ai-swiss/base --skill configurationgit 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/configuration)<a href="https://agentmods.dev/skills/ai-swiss/base/configuration"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/configuration.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00013 | $0.01978 |
| Opus 5 | $0.00006 | $0.00989 |
| Sonnet 5 | $0.00003 | $0.00396 |
| Haiku 4.5 | $0.00001 | $0.00198 |
Grade A, and why
configuration 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 4d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configuration de la communication
Guider l'utilisateur pas à pas pour réunir toutes les informations dont l'assistant communication a besoin pour fonctionner. Ce process se lance à la première utilisation, ou lorsque les fichiers métier contiennent encore des champs à compléter.
Inputs
Avant de commencer, vérifie:
entreprise/identite.md: est-il rempli, ou contient-il encore des champs à compléter ([...])?entreprise/charte-editoriale.md: contient-il des données réelles ou le modèle vide?charte/ton-et-style.md: contient-il des données réelles ou le modèle vide?
Si tout est déjà rempli, signale-le à l'utilisateur et propose de passer directement à la création de contenu.
Si .ai/journal/ contient des entrées récentes, lis-les pour reprendre le contexte.
Étapes
1. Accueil
«Bienvenue! Je suis votre assistant communication. Avant de pouvoir créer du contenu adapté à votre entreprise, j'ai besoin de vous connaître un peu. Je vais vous poser quelques questions, ça prend environ 10 minutes. On commence?»
2. Identité de l'entreprise
Pose les questions une par une. Ne passe à la suivante qu'une fois la réponse claire.
Questions:
- Nom de l'entreprise
- Adresse complète
- Numéro IDE (si applicable)
- Forme juridique (SA, Sàrl, raison individuelle, etc.)
- Activité principale (en une phrase)
- Nombre de personnes dans l'équipe
- Types de clients (particuliers, entreprises, collectivités, etc.)
- Email de contact
- Téléphone
- Site web (si existant)
«Voici ce que j'ai noté: [résumé]. Est-ce correct?»
← Reformulation
⚠ Point de décision - avant écriture:
«Je suis prêt à enregistrer ces informations dans votre fiche entreprise. Confirmez-vous?»
Écris dans entreprise/identite.md. Pour les champs restés vides, utilise [A COMPLETER: ...].
3. Approche éditoriale
«Avant de définir votre ton, parlons de votre approche d'ensemble de la communication.»
Pose les questions une par une:
- Pourquoi communiquez-vous? Quel est l'objectif principal? (ex. partager votre expertise, créer de la confiance, attirer de nouveaux clients)
- Quelle image souhaitez-vous projeter? (ex. une entreprise proche, compétente, innovante)
- Sur quels canaux communiquez-vous? (ex. LinkedIn, newsletter, site web) Et à quelle fréquence?
- Qui relit et valide les contenus avant publication?
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.
- 4d ago First seen · 195 lines · 13 tokens per session scan A 6df42d4d8ade
configuration is a skill published in the GitHub repository ai-swiss/base (42 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 1,978 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
achieving-cmmc-level-2-compliance
Prepare a defense-contractor environment for CMMC Level 2 certification: scope CUI and FCI, implement the 110 NIST SP 800-171 Rev 2 security requirements across 14 families, compute the SPRS score with the DoD Assessment Methodology, manage a compliant POA&M, and ready the organization for a C3PAO assessment. Use when…
escalation-governance
Assess whether to escalate models. Use when evaluating reasoning depth.
agt-policy-authoring
Create and validate a minimal AGT Copilot CLI policy tailored to the repository being inspected.
wallet-cli
Operate the TypeScript TRON wallet CLI for accounts, transfers, staking, governance, contracts, signing, chain queries, and password input with wallet-cli 4.12.0. Refuse wallet passwords in argv and require the supported stdin channel. For Java REPL requests, refuse that entry and offer the TypeScript one-shot CLI…
TRX Staking & SR Voting
Stake TRX, vote for Super Representatives, and claim voting rewards on TRON.
digital-native-governance-check
Assess Azure governance maturity for Digital Natives and startups. Detects the most common anti-patterns from the "Digital Natives on Azure" series: incomplete Service Health alerts, flat subscription topology without Management Groups, excessive RBAC (everyone is Owner), missing budget alerts, no Managed Identity…