Un guide de questions-réponses sur BASE, le cadre qui organise des assistants, leurs processus, leurs fichiers et leurs connexions. Il demande de consulter la documentation de référence avant de répondre.

Il sert à expliquer les agents, les processus, les dossiers de travail, MCP, le routage et la confidentialité.

Il aide à obtenir une réponse courte et fondée au lieu d'une explication improvisée sur un terme ou une règle du cadre.

faq-base — Skill for Claude Code and Codex by ai-swiss: Un guide de questions-réponses sur BASE, le cadre qui…

Install

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.

agentmods

npx agentmods add skills/ai-swiss/base/faq-base

Any agent

npx skills add ai-swiss/base --skill faq-base

Clone the repo

git clone --depth 1 https://github.com/ai-swiss/base

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ai-swiss/base/faq-base.svg)](https://agentmods.dev/skills/ai-swiss/base/faq-base)

Your own site

<a href="https://agentmods.dev/skills/ai-swiss/base/faq-base"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/faq-base.svg" alt="Measured on agentmods" height="20"></a>

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 986 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00046	$0.00986
Opus 5	$0.00023	$0.00493
Sonnet 5	$0.00009	$0.00197
Haiku 4.5	$0.00005	$0.00099

Measured 5d ago against content hash fe1437922244, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

faq-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 5d 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.

.ai/agents/concierge-base/skills/processes/faq-base/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FAQ BASE

Répondre court et juste à une question de base, sans renvoyer l'utilisateur à la doc. La règle: tu lis d'abord la source canonique, puis tu réponds avec tes mots.

Méthode

Identifie le sujet de la question.
Ouvre la ou les sources canoniques listées ci-dessous pour ce sujet.
Réponds en 3 à 8 phrases, simplement.
Dis ce que cela change pour la situation de l'utilisateur.
Propose une action à suivre.

Tu ne te contentes pas d'un lien. Tu lis, puis tu aides à partir de ce que tu as lu.

Sources à lire selon la question

Définitions courtes (source canonique, toujours en premier pour un terme):
- docs/reference/glossaire.md
Vision / pourquoi BASE:
- README.md
- MANIFESTO.md
- docs/learn/pratiques-co-pensee.md
Concepts (agent, process, ressources, routage):
- docs/reference/routage-process-et-ressources.md
- docs/learn/comprendre.md
- docs/reference/framework-public.md
Sécurité / accès / données:
- docs/trust/frontiere-local-vs-sortant.md (la première question: qu'est-ce qui sort de ma machine, et quand)
- docs/trust/securite-et-limites.md
- docs/trust/mecanismes-verifies.md (la table garantie → fonction → test, pour qui veut la preuve)
- docs/trust/securite-donnees-routage.md
- SECURITY.md
Racines / workspace / MCP:
- specs/current/10_core/cli.md
- specs/current/10_core/mcp.md
- mcp/README.md

C'est une simple consigne de process, pas une nouvelle abstraction.

Repères de réponse (à vérifier dans la doc, pas à réciter de mémoire)

Agent: une fiche de poste (AGENT.md) + des skills. Le «qui».
Process: un workflow, une façon de faire étape par étape. Le «comment».
Compétence: une connaissance réutilisable. Le «savoir».
Racine (root): un projet BASE, confiné. Lecture/écriture/exécution restent dedans.
Workspace: plusieurs racines déclarées; le routage peut chercher parmi elles, mais chaque action reste dans la racine choisie.
MCP: expose les primitives BASE aux applications de chat; en HTTP, il est en lecture seule par défaut.
Confidentialité: par défaut, le routage est local; rien ne part vers un fournisseur tant que vous n'avez pas explicitement activé les embeddings.

Read the full file on GitHub · 90 lines

Changes

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.

5d ago First seen · 90 lines · 46 tokens per session scan A fe1437922244

Subscribe to this mod's changes

faq-base is a skill published in the GitHub repository ai-swiss/base (42 stars, last pushed yesterday), licensed Apache-2.0. It adds 46 tokens to every session and 986 once invoked, about $0.0002 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.

Building agents ai ai-agents cli cognitive-sovereignty digital-sovereignty governance

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…

mukul975/Anthropic-Cybersecurity-Skills · 255 tokens

escalation-governance

Assess whether to escalate models. Use when evaluating reasoning depth.

athola/claude-night-market · 19 tokens

implementing-iso-27001-information-security-management

ISO/IEC 27001:2022 is the international standard for establishing, implementing, maintaining, and continually improving an Information Security Management System (ISMS). This skill covers the complete.

xalgorix/xalgorix · 48 tokens

agt-policy-authoring

Create and validate a minimal AGT Copilot CLI policy tailored to the repository being inspected.

microsoft/agent-governance-toolkit · 23 tokens

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…

BofAI/skills · 82 tokens

TRX Staking & SR Voting

Stake TRX, vote for Super Representatives, and claim voting rewards on TRON.

BofAI/skills · 25 tokens