comprendre-base

comprendre-base is a skill for Claude Code, Codex from ai-swiss/base. It costs 39 tokens per session (1,030 once invoked), scanned A, original, Apache-2.0.

Un guide d'explication de BASE, le cadre qui organise des assistants, leurs processus, leurs fichiers et leur routage. Il adapte l'explication au niveau de la personne et au sujet demandé.

In plain words
What is it for?
Il sert à comprendre la vision, l'architecture, le routage, les règles, MCP, les dossiers de travail et la confidentialité.
Why use it?
Il évite les explications trop vagues ou trop techniques sur le fonctionnement, les garanties et les limites du cadre.

Skill for Claude CodeCodex

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/comprendre-base
Any agent
npx skills add ai-swiss/base --skill comprendre-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.

agentmods badge for comprendre-base

README.md
[![agentmods](https://agentmods.dev/badge/skills/ai-swiss/base/comprendre-base.svg)](https://agentmods.dev/skills/ai-swiss/base/comprendre-base)
Your own site
<a href="https://agentmods.dev/skills/ai-swiss/base/comprendre-base"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/comprendre-base.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,030 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.

ModelPer sessionOnce invoked
Fable 5 $0.00039 $0.01030
Opus 5 $0.00019 $0.00515
Sonnet 5 $0.00008 $0.00206
Haiku 4.5 $0.00004 $0.00103

Measured 5d ago against content hash e1ceba01ca3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

comprendre-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/comprendre-base/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Comprendre BASE

Expliquer BASE à la bonne profondeur, en lisant d'abord la doc canonique. Ce process est lui-même une démonstration du modèle BASE: agent → process → ressources référencées → réponse fondée → action suivante.

Méthode

  1. Repère le profil si utile: débutant, équipe, architecte, sécurité/IT, développeur.
  2. Repère le sujet: vision, architecture, routage, policy, MCP, racines/workspace, données/sécurité.
  3. Ouvre les sources canoniques listées pour ce sujet.
  4. Réponds dans la langue et à la profondeur de l'utilisateur.
  5. Dis ce que cela change pour sa tâche en cours, s'il en a une.
  6. Propose une action suivante, ou de revenir à la tâche interrompue.

Sources à lire selon le sujet

  • Vision / pourquoi:
    • docs/learn/co-penser-avec-lia.md (le pourquoi: vérification, pertes de contrôle, méthode), commence ici
    • MANIFESTO.md
    • docs/learn/pratiques-co-pensee.md
    • docs/learn/comprendre.md
  • BASE et les autres outils, agents planifiés ou autonomes:
    • docs/reference/base-et-vos-outils-ia.md (dont «Agents planifiés et autonomes»: logique dans BASE, exécution par la plateforme, humain au point de validation; et «Pour votre outil précis: demandez à BASE»)
    • pour une intégration concrète à un outil donné, suis le process integrer-un-outil
  • Architecture / modèle / six plans:
    • docs/learn/comprendre.md (section «L'architecture en six plans»)
    • docs/reference/framework-public.md
    • specs/current/00_overview/vision.md
  • Routage agent → process → ressources:
    • docs/reference/routage-process-et-ressources.md
    • specs/current/10_core/routing.md
  • Permissions / policy / frontières:
    • docs/trust/securite-et-limites.md
    • specs/current/10_core/policy.md
  • Données / sécurité (ce qui sort, ce qui est prouvé):
    • docs/trust/frontiere-local-vs-sortant.md
    • docs/trust/mecanismes-verifies.md
  • Racines / workspace / MCP:
    • specs/current/10_core/cli.md
    • specs/current/10_core/mcp.md

Profondeur selon le profil

Read the full file on GitHub · 83 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.

  1. 5d ago First seen · 83 lines · 39 tokens per session scan A e1ceba01ca3e

Subscribe to this mod's changes

comprendre-base is a skill published in the GitHub repository ai-swiss/base (43 stars, last pushed yesterday), licensed Apache-2.0. It adds 39 tokens to every session and 1,030 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.

Related

Other skills, from other repositories