base: Skill for Claude Code

.ai/agents/createur-agent/skills/competences/outils-connus/SKILL.md

outils-connus is a skill for Claude Code, Codex from ai-swiss/base. It costs 15 tokens per session (1,195 once invoked), scanned A, original, Apache-2.0.

A French-language reference describing known configurations for several AI tools when current web documentation is unavailable. It explains how tools can provide persistent context, discoverable skills, path-based rules, permissions, and protection for their framework files.

In plain words
What is it for?
Use it to compare how different AI coding tools implement shared agent settings and controls.
Why use it?
It gives a fallback reference when online documentation cannot be consulted, while warning that the information may be out of date.

Skill for Claude CodeCodex

Written for Claude Code and Codex: allowed-tools in frontmatter, but also reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is ai-swiss/base's own configuration. It tells Claude Code and Codex how to work on base itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything base configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/ai-swiss/base/main/.ai/agents/createur-agent/skills/competences/outils-connus/SKILL.md
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 outils-connus

README.md
[![agentmods](https://agentmods.dev/badge/skills/ai-swiss/base/outils-connus/github.svg)](https://agentmods.dev/skills/ai-swiss/base/outils-connus)
Your own site
<a href="https://agentmods.dev/skills/ai-swiss/base/outils-connus"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/outils-connus/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.

agentmods 80×15 button for outils-connus

Your own site · 80×15
<a href="https://agentmods.dev/skills/ai-swiss/base/outils-connus"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/outils-connus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,195 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 35
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 5.1 $0.00015 $0.01195
Opus 5 $0.00008 $0.00598
Sonnet 5 $0.00003 $0.00239
Haiku 4.5 $0.00002 $0.00120

Measured 9d ago against content hash a7b505405393, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

outils-connus 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 9d 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/createur-agent/skills/competences/outils-connus/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Outils connus: référence de base

Dernière vérification: avril 2026.

Ce fichier sert de secours quand le créateur-agent n'a pas accès au web pour consulter la documentation à jour d'un outil. Toujours préférer la documentation en ligne: les outils évoluent vite et ces repères peuvent être périmés.

Rappel: les 5 primitives abstraites

Tout outil IA a besoin de 5 choses pour faire vivre un agent BASE:

  1. Contexte permanent: charger AGENT.md à chaque session
  2. Skills découvrables: l'outil trouve et invoque les SKILL.md
  3. Règles par chemin: garde-fous activés selon le fichier touché
  4. Permissions: contrôler ce que l'agent peut faire
  5. Protection du cadre: empêcher la modification de .ai/

Claude Code

Primitive Implémentation
Contexte permanent CLAUDE.md à la racine avec @.ai/agents/[nom]/AGENT.md (import mécanique)
Skills découvrables Copier les skills dans .claude/skills/ (auto-découverte, dossiers plats)
Règles par chemin .claude/rules/*.md avec frontmatter paths: ["chemin/**"]
Permissions .claude/settings.json avec permissions.allow et permissions.deny
Protection du cadre Hook PreToolUse ou permission deny sur .ai/** dans settings.json

Structure résultante:

CLAUDE.md                              ← @.ai/agents/[nom]/AGENT.md
.claude/
  settings.json                        ← permissions + hooks
  rules/
    guardrails.md                      ← paths: ["devis/**", "clients/**"]
  skills/                              ← copie aplatie de tous les SKILL.md
    nouveau-devis/SKILL.md
    configuration/SKILL.md
    metier-devis/SKILL.md
    communication/SKILL.md
    marqueurs/SKILL.md
    journal/SKILL.md

Codex (OpenAI)

Primitive Implémentation
Contexte permanent AGENTS.md à la racine (contenu généré depuis AGENT.md, pas d'import)
Skills découvrables .codex/skills/ ou .agents/skills/ (enregistrés dans config.toml)
Règles par chemin AGENTS.md imbriqué dans les sous-dossiers (ex. devis/AGENTS.md)
Permissions .codex/config.toml avec sandbox_mode et approval_policy
Protection du cadre Filesystem permissions dans config.toml

Read the full file on GitHub · 99 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. 9d ago First seen · 99 lines · 15 tokens per session scan A a7b505405393

Subscribe to this mod's changes

outils-connus is a skill published in the GitHub repository ai-swiss/base (45 stars, last pushed 5d ago), licensed Apache-2.0. It adds 15 tokens to every session and 1,195 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.